Posted Updated Agent Skills / Writing & Documentsan hour read (About 7106 words)   visits

Writing & Documents | Agent Skills

Writing & Documents

Writing and document skills help create, revise, analyze, translate, and format written or office-document deliverables.

Catalog snapshot: November 2, 2026

Category menu

Skills in this category

anthropics/doc-coauthoring

Catalog entry: Official Claude Skills
Source documentation: https://github.com/anthropics/skills/blob/main/skills/doc-coauthoring/SKILL.md

Function: Collaborative document editing and co-authoring

When to use it: Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Doc Co-Authoring Workflow
  • When to Offer This Workflow
  • Stage 1: Context Gathering
  • Initial Questions
  • Info Dumping
  • Stage 2: Refinement & Structure
  • Step 1: Clarifying Questions
  • Step 2: Brainstorming
  • Step 3: Curation
  • Step 4: Gap Check
  • Step 5: Drafting
  • Step 6: Iterative Refinement
  • Quality Checking
  • Near Completion
  • Stage 3: Reader Testing
  • Testing Approach

anthropics/docx

Catalog entry: Official Claude Skills
Source documentation: https://github.com/anthropics/skills/blob/main/skills/docx/SKILL.md

Function: Create, edit, and analyze Word documents

When to use it: Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of ‘Word doc’, ‘word document’, ‘.docx’, ‘.dotx’, or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • DOCX creation, editing, and analysis
  • Creating with docx-js — gotchas
  • Verify the output
  • Editing existing documents
  • Comments
  • Dependencies

anthropics/internal-comms

Catalog entry: Official Claude Skills
Source documentation: https://github.com/anthropics/skills/blob/main/skills/internal-comms/SKILL.md

Function: Write status reports, newsletters, and FAQs

When to use it: use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • When to use this skill
  • How to use this skill
  • Keywords

anthropics/pdf

Catalog entry: Official Claude Skills
Source documentation: https://github.com/anthropics/skills/blob/main/skills/pdf/SKILL.md

Function: Extract text, create PDFs, and handle forms

When to use it: Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • PDF Processing Guide
  • Overview
  • Quick Start
  • Python Libraries
  • pypdf - Basic Operations
  • pdfplumber - Text and Table Extraction
  • reportlab - Create PDFs
  • Command-Line Tools
  • pdftotext (poppler-utils)
  • qpdf
  • pdftk (if available)
  • Common Tasks
  • Extract Text from Scanned PDFs
  • Add Watermark
  • Extract Images
  • Password Protection

anthropics/pptx

Catalog entry: Official Claude Skills
Source documentation: https://github.com/anthropics/skills/blob/main/skills/pptx/SKILL.md

Function: Create, edit, and analyze PowerPoint presentations

When to use it: Extracting all text from a client deck to feed into a summary email Converting a data report into a slide presentation with charts and callouts Editing an existing template deck with new content without breaking the layout Building a pitch deck from scratch with a custom color palette and font pairing Splitting a large presentation into separate files by section

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • PPTX creation, editing, and analysis
  • Scripts
  • Creating with pptxgenjs — gotchas
  • Editing existing decks and templates
  • Design Ideas
  • Before Starting
  • Color Palettes
  • For Each Slide
  • Typography
  • Spacing
  • Avoid (Common Mistakes)
  • QA (Required)
  • Content QA
  • File QA (required)
  • Visual QA
  • Converting to Images

anthropics/xlsx

Catalog entry: Official Claude Skills
Source documentation: https://github.com/anthropics/skills/blob/main/skills/xlsx/SKILL.md

Function: Create, edit, and analyze Excel spreadsheets

When to use it: Building a financial model with color-coded inputs and formula-driven projections Cleaning a CSV with misplaced headers and junk rows into a structured spreadsheet Converting a TSV data export into a formatted Excel workbook with proper column widths Adding SUM and AVERAGE formulas to an existing spreadsheet without hardcoding calculated values Fixing #REF! and #DIV/0! errors in an inherited Excel file

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • XLSX creation, editing, and analysis
  • Requirements for every output
  • Recalculate (mandatory whenever the file contains formulas)
  • Choosing formulas that survive verification
  • openpyxl gotchas
  • Financial models
  • Dependencies

arifszn/slide-wright

Catalog entry: Productivity and Collaboration
Source documentation: https://github.com/arifszn/slide-wright/blob/main/SKILL.md

Function: Generate themed HTML slide decks, export to PowerPoint or PDF

When to use it: Use when the user wants to make slides, a presentation, a talk deck, a pitch deck, or to add/remove/change a slide in one that already exists.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • slide-wright
  • The rule that defines this skill
  • The engine (keep this internal)
  • Editing a deck that already exists
  • Step 5 — Hand it off
  • Reference files

AugustusW/audio-tldr

Catalog entry: Productivity and Collaboration
Source documentation: https://github.com/AugustusW/audio-tldr-skill/blob/main/skills/audio-tldr/SKILL.md

Function: Summarize videos and podcasts with local, cached transcription

When to use it: Use when the user asks to summarize, get key points from, translate, or TL;DR any audio or video content.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • audio-tldr
  • User preferences (read first)
  • Digest model resolution
  • Phase 1 — Transcribe (cached)
  • Phase 1.5 — Frames (opt-in)
  • Phase 1.8 — Correct (before every digest)
  • Phase 2 — Digest
  • Custom templates
  • Digest via subagent (cheaper model)
  • Usage log
  • Digest via local Ollama (privacy mode)
  • Re-digesting
  • Cache management
  • Notes
  • Feedback

blader/humanizer

Catalog entry: Marketing
Source documentation: https://github.com/blader/humanizer/blob/main/SKILL.md

Function: Remove signs of AI-generated writing from text, making it sound more natural and human

When to use it: Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Based on Wikipedia’s “Signs of AI writing.“

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Humanizer: remove AI writing patterns
  • Why AI text sounds the way it does
  • How to work
  • Voice
  • What to return
  • A. Staging instead of stating
  • 1. Not X but Y
  • 2. One-line closers and dramatic fragments
  • 3. Sayings that sound deep
  • 4. Staged run-up before the point
  • 5. Arguing with no one
  • B. Rhythm by rule
  • 6. Forced triads
  • 7. Repeated sentence openings
  • 8. Dashes as the universal connector
  • 9. Stacked qualifiers

clickhouse/clickhouse-architecture-advisor

Catalog entry: Skills by ClickHouse
Source documentation: https://github.com/clickhouse/agent-skills/blob/main/skills/clickhouse-architecture-advisor/SKILL.md

Function: Design ClickHouse architectures and translate best practices into workload-specific decisions

When to use it: USE when designing ClickHouse architectures, selecting between ingestion or modeling patterns, or translating best practices into workload-specific system designs. Complements clickhouse-best-practices with decision frameworks and explicit provenance labels.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • ClickHouse Architecture Advisor
  • Required behavior
  • Provenance rules
  • `official`
  • `derived`
  • `field`
  • Read these rule files by scenario
  • Real-time ingestion design
  • Time-series and retention design
  • Enrichment and dimension lookups
  • Mutable state / late-arriving events
  • Output format
  • Architecture-specific guidance
  • Full reference

datadog-labs/dd-docs

Catalog entry: Skills by Datadog Labs
Source documentation: https://github.com/datadog-labs/agent-skills/blob/main/dd-docs/SKILL.md

Function: Look up Datadog documentation via the LLM-optimized docs index

When to use it: Finding the right Datadog docs page for a monitoring setup question Looking up APM tracing configuration details without leaving your editor Checking Datadog log pipeline syntax during a debugging session Pulling metrics API reference docs while writing a custom integration Reviewing Datadog monitor threshold options before creating an alert

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Datadog Docs
  • LLM-Friendly Documentation
  • How to Use llms.txt
  • Key Documentation Sections
  • Scope Guardrails
  • Failure Handling

deusyu/translate-book

Catalog entry: Productivity and Collaboration
Source documentation: https://github.com/deusyu/translate-book/blob/main/SKILL.md

Function: Translate books (PDF/DOCX/EPUB) via parallel sub-agents with resume

When to use it: Use when a task needs the capability described in this catalog entry: Translate books (PDF/DOCX/EPUB) via parallel sub-agents with resume

The catalog does not state a separate trigger condition. This usage note is inferred from the published function description.

Source skill menu:

  • Book Translation Skill
  • Workflow
  • 1. Collect Parameters
  • 2. Preprocess — Convert to Markdown Chunks
  • 3. Discover Source Chunks
  • 3.5. Build Glossary (term consistency)
  • 3.7. Plan Selective Re-translation
  • 4. Parallel Translation with Sub-Agents
  • 4.5. Merge Sub-Agent Meta Into Glossary (after each batch)
  • 5. Verify Completeness and Retry
  • 6. Translate Book Title
  • 7. Post-process — Merge and Build
  • 8. Report Results
  • 9. Spot Fixes After the Build

duckdb/duckdb-docs

Catalog entry: Skills by DuckDB
Source documentation: https://github.com/duckdb/duckdb-skills/blob/main/skills/duckdb-docs/SKILL.md

Function: Search DuckDB and DuckLake documentation using full-text search over HTTPS

When to use it: Looking up DuckDB SQL function syntax like arg_max or list_aggregate Finding DuckLake catalog configuration options Checking stable vs nightly differences for a specific DuckDB feature Searching blog posts for the motivation behind a DuckDB design decision Debugging a DuckDB query by retrieving the relevant reference docs

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Step 1 — Check DuckDB is installed
  • Step 2 — Ensure required extensions are installed
  • Step 3 — Choose the data source and extract search terms
  • Data source selection
  • Search terms
  • Step 4 — Ensure local cache is fresh
  • Step 5 — Search the docs
  • Step 6 — Handle errors
  • Step 7 — Present results

garrytan/document-release

Catalog entry: Skills by Garry Tan (gstack)
Source documentation: https://github.com/garrytan/gstack/blob/main/document-release/SKILL.md

Function: Technical Writer: update all project docs to match what you just shipped

When to use it: Updating README feature tables after merging a new command Fixing stale file paths in CONTRIBUTING after a repo restructure Polishing CHANGELOG entries from commit-message tone to user-facing language Marking TODO items as complete when the diff shows the work is done Checking cross-doc consistency before a PR merges

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Shared preamble (load first)
  • Preamble (run first)
  • Question Tuning (skip entirely if `QUESTION_TUNING: false`)
  • Telemetry (run last)
  • Step 0: Detect platform and base branch
  • Document Release: Documentation Audit and Update
  • Ship-owned documentation mode
  • Section index — Read each section when its situation applies
  • Step 1: Pre-flight & Diff Analysis
  • Step 1.5: Coverage Map (Blast-Radius Analysis)
  • Important Rules

ilyautov/humanizer-ru

Catalog entry: Marketing
Source documentation: https://github.com/ilyautov/humanizer-ru/blob/main/skills/humanizer-ru/SKILL.md

Function: Removes 64 AI-writing markers from Russian text, with scanner

When to use it: Use when a task needs the capability described in this catalog entry: Removes 64 AI-writing markers from Russian text, with scanner

The catalog does not state a separate trigger condition. This usage note is inferred from the published function description.

Source skill menu:

  • Humanizer-RU v3.32.0
  • Выбери режим
  • Шаг 1. Диагностика
  • Регистр: что где снимается
  • Жёсткие запреты (HARD BANS)
  • Шаг 2. Правка по разметке
  • Шаг 3. Сверка с исходником
  • Что получает пользователь

JayPokale/chisle

Catalog entry: Context Engineering
Source documentation: https://github.com/JayPokale/Chisle/blob/main/skills/chisle/SKILL.md

Function: Cuts agent tokens: terse prose, lean code, trimmed tool output

When to use it: Use when user says “chisle mode”, “activate chisle”, “chislify”, “be efficient”, “be minimal”, “no fluff”, “yagni”, or invokes /chisle. Deactivate: “stop chisle” / “normal mode”.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Chisle
  • Persistence
  • Prose: Maximum Signal Per Token
  • Code: The Efficiency Ladder
  • Thinking Is Billed Too
  • Code Rules
  • Context Diet: Read Less Into the Window
  • Output Format
  • Auto-Clarity
  • When NOT to be lazy
  • Boundaries

kklimuk/docx-cli

Catalog entry: Productivity and Collaboration
Source documentation: https://github.com/kklimuk/docx-cli/blob/main/skills/docx-cli/SKILL.md

Function: Work on .docx files at ~1/2 cost of other skills.

When to use it: Use when a task needs the capability described in this catalog entry: Work on .docx files at ~1/2 cost of other skills.

The catalog does not state a separate trigger condition. This usage note is inferred from the published function description.

Source skill menu:

  • docx-cli
  • 0. Make sure the binary is on PATH
  • 1. The contract is `--help` — start there
  • Which workflow?
  • 2. Locators — how you address things
  • 3. Golden workflows
  • Fill out a form or contract (keeps formatting)
  • Redline with tracked changes
  • Finalize a returned redline
  • Comment on clauses
  • Read / extract
  • Build from scratch / verify layout
  • 4. Apply many changes from one read — `--batch`
  • 5. Output & safety contract
  • 6. Going deeper

makenotion/knowledge-capture

Catalog entry: Skills by Notion
Source documentation: https://github.com/makenotion/notion-cookbook/blob/main/README.md

Function: Transform conversations into structured Notion documentation pages with proper organization and linking

When to use it: Saving a technical decision from a chat thread as a formal decision record in Notion Turning a debugging session into a step-by-step how-to guide linked from the team wiki Converting a Q&A exchange into FAQ entries with proper tags and category properties Writing up a production incident as a post-mortem page under the relevant project Capturing architecture notes from a code review into a searchable documentation database

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Notion cookbook
  • What do you want to build?
  • Quickstarts
  • Using this cookbook with a coding agent
  • Run an API example
  • Deploy a Worker
  • API examples
  • Worker examples
  • Default template
  • Sync external data into Notion
  • Add tools to a Notion Agent
  • Handle webhooks
  • More resources
  • Community
  • License

manavmishra/zero-slop

Catalog entry: Productivity and Collaboration
Source documentation: https://github.com/manavmishra/ZeroSlop/blob/main/SKILL.md

Function: Edits AI-sounding prose while preserving facts, voice, and formatting

When to use it: Use when a task needs the capability described in this catalog entry: Edits AI-sounding prose while preserving facts, voice, and formatting

The catalog does not state a separate trigger condition. This usage note is inferred from the published function description.

Source skill menu:

  • Zero Slop
  • Hard rules (non-negotiable)
  • Eight roles, one pipeline
  • Detailed workflow
  • References
  • Worked example (LinkedIn)

mattpocock/skills

Catalog entry: Development and Testing
Source documentation: https://github.com/mattpocock/skills/blob/main/README.md

Function: 17 dev workflow skills: PRD writing, TDD, codebase architecture, git guardrails, issue triage, refactoring plans, and more

When to use it: Use when a task needs the capability described in this catalog entry: 17 dev workflow skills: PRD writing, TDD, codebase architecture, git guardrails, issue triage, refactoring plans, and more

The catalog does not state a separate trigger condition. This usage note is inferred from the published function description.

Source skill menu:

  • Skills For Real Engineers
  • Installation (30-second setup)
  • 1. Get the skills
  • 2. Run `/setup-matt-pocock-skills`
  • 3. Bam - you’re ready to go.
  • Why These Skills Exist
  • #1: The Agent Didn’t Do What I Want
  • #2: The Agent Is Way Too Verbose
  • #3: The Code Doesn’t Work
  • #4: We Built A Ball Of Mud
  • Summary
  • Reference
  • Engineering
  • Productivity

This catalog entry points to a collection. The scanned repository lists 39 distinct skill-file paths.

Sample members: ask-matt · code-review · codebase-design · diagnosing-bugs · domain-modeling · grill-with-docs · implement-spec · implement
More members are available in the source repository.

MiniMax-AI/minimax-docx

Catalog entry: Skills by MiniMax Team
Source documentation: https://github.com/MiniMax-AI/skills/blob/main/skills/minimax-docx/SKILL.md

Function: Professional DOCX document creation and editing using OpenXML SDK

When to use it: use this skill whenever the user wants to produce, modify, or format a Word document — including when they say “write a report”, “draft a proposal”, “make a contract”, “fill in this form”, “reformat to match this template”, or any task whose final output is a .docx file. Even if the user doesn’t mention “docx” explicitly, if the task implies a printable/formal document, use this skill.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • minimax-docx
  • Setup
  • Quick Start: Direct C# Path
  • CLI shorthand
  • Pipeline routing
  • Pre-processing
  • Scenario A: Create
  • Scenario B: Edit / Fill
  • Scenario C: Apply Template
  • Validation pipeline
  • Critical rules
  • References
  • Scenario guides (read first for each pipeline)
  • C# code samples (compilable, heavily commented — read when writing code)
  • Markdown references (read when you need specifications or design rules)

MiniMax-AI/minimax-pdf

Catalog entry: Skills by MiniMax Team
Source documentation: https://github.com/MiniMax-AI/skills/blob/main/skills/minimax-pdf/SKILL.md

Function: Generate, fill, and reformat PDFs with a token-based design system and 15 cover styles

When to use it: Use this skill when visual quality and design identity matter for a PDF. CREATE (generate from scratch): “make a PDF”, “generate a report”, “write a proposal”, “create a resume”, “beautiful PDF”, “professional document”, “cover page”, “polished PDF”, “client-ready document”. FILL (complete form fields): “fill in the form”, “fill out this PDF”, “complete the form fields”, “write values into PDF”, “what fields does this PDF have”. REFORMAT (apply design to an existing doc): “reformat this document”, “apply our style”, “convert this Markdown/text to PDF”, “make this doc look good”, “re-style this PDF”. This skill us

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • minimax-pdf
  • Read `design/design.md` before any CREATE or REFORMAT work.
  • Route table
  • Route A: CREATE
  • Route B: FILL
  • Route C: REFORMAT
  • Environment

MiniMax-AI/minimax-xlsx

Catalog entry: Skills by MiniMax Team
Source documentation: https://github.com/MiniMax-AI/skills/blob/main/skills/minimax-xlsx/SKILL.md

Function: Create, read, analyze, and validate Excel/spreadsheet files with zero format loss

When to use it: Use when the user asks to create, build, modify, analyze, read, validate, or format any Excel spreadsheet, financial model, pivot table, or tabular data file. Covers: creating new xlsx from scratch, reading and analyzing existing files, editing existing xlsx with zero format loss, formula recalculation and validation, and applying professional financial formatting standards. Triggers on ‘spreadsheet’, ‘Excel’, ‘.xlsx’, ‘.csv’, ‘pivot table’, ‘financial model’, ‘formula’, or any request to produce tabular data in Excel format.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • MiniMax XLSX Skill
  • Task Routing
  • READ — Analyze data (read `references/read-analyze.md` first)
  • CREATE — XML template (read `references/create.md` + `references/format.md`)
  • EDIT — XML direct-edit (read `references/edit.md` first)
  • FIX — Repair broken formulas (read `references/fix.md` first)
  • VALIDATE — Check formulas (read `references/validate.md` first)
  • Financial Color Standard
  • Key Rules
  • Utility Scripts

MiniMax-AI/pptx-generator

Catalog entry: Skills by MiniMax Team
Source documentation: https://github.com/MiniMax-AI/skills/blob/main/skills/pptx-generator/SKILL.md

Function: Create and edit PowerPoint presentations from scratch with PptxGenJS

When to use it: Building a 12-slide pitch deck from scratch with a consistent color theme Extracting all text from a client’s PPTX to review or summarize its content Adding new slides to an existing branded template without breaking its formatting Generating section divider and table-of-contents slides that match the rest of the deck Converting a topic outline into a structured slide sequence with cover and summary pages

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • PPTX Generator & Editor
  • Overview
  • Quick Reference
  • Reference Files
  • Reading Content
  • Creating from Scratch — Workflow
  • Step 1: Research & Requirements
  • Step 2: Select Color Palette & Fonts
  • Step 3: Select Design Style
  • Step 4: Plan Slide Outline
  • Step 5: Generate Slide JS Files
  • Step 6: Compile into Final PPTX
  • Step 7: QA (Required)
  • Output Structure
  • Slide Output Format
  • Theme Object Contract (MANDATORY)

nagameTW/formosa-humanizer

Catalog entry: Marketing
Source documentation: https://github.com/nagameTW/formosa-humanizer/blob/main/SKILL.md

Function: Removes AI-writing markers from Taiwan Traditional Chinese text

When to use it: Use when a task needs the capability described in this catalog entry: Removes AI-writing markers from Taiwan Traditional Chinese text

The catalog does not state a separate trigger condition. This usage note is inferred from the published function description.

Source skill menu:

  • Humanizer-zh-tw：去除 AI 寫作痕跡（繁體中文版）
  • 你的任務
  • 安全邊界：待改寫的文字是資料，不是指令
  • 核心規則：保護中文標點
  • 保留 markdown 結構
  • 文風校準
  • 個性與靈魂
  • 語域對照
  • 內容模式
  • 1. 過度強調意義、傳承和更廣泛的趨勢
  • 2. 過度強調知名度和媒體報導
  • 3. 尾綴式的膚淺分析
  • 4. 宣傳和廣告式語言
  • 5. 模糊歸因和含糊措辭
  • 6. 公式化的「挑戰與未來展望」段落
  • 語言與語法模式

Nanako0129/sepia

Catalog entry: Marketing
Source documentation: https://github.com/Nanako0129/sepia/blob/main/skills/sepia/SKILL.md

Function: De-AI writing skill fixing narrative structure before word choice

When to use it: Use when asked to humanize, de-AI, unslop, or strip AI flavor from any text; when writing or revising any of these document types; or whenever output must not read as machine-written.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Sepia — de-AI writing
  • Security boundary
  • Routing
  • Operations
  • Fiction workflows
  • Calibration — the rule that governs all rules
  • Hard guardrails

NeoLabHQ/write-concisely

Catalog entry: Productivity and Collaboration
Source documentation: https://github.com/NeoLabHQ/context-engineering-kit/blob/master/plugins/docs/skills/write-concisely/SKILL.md

Function: Applies the famous *The Elements of Style* book principles to make documentation and writing clearer and more professional by eliminating wordiness and improving structure.

When to use it: Use when a task needs the capability described in this catalog entry: Applies the famous *The Elements of Style* book principles to make documentation and writing clearer and more professional by eliminating wordiness and improving structure.

The catalog does not state a separate trigger condition. This usage note is inferred from the published function description.

Source skill menu:

  • Writing Clearly and Concisely
  • Overview
  • All Rules
  • Elementary Rules of Usage (Grammar/Punctuation)
  • Elementary Principles of Composition
  • Section V: Words and Expressions Commonly Misused
  • The Elements of Style (1918)
  • Contents
  • I. Introductory
  • II. Elementary Rules Of Usage
  • Rule 1. Form the possessive singular of nouns by adding ‘s
  • Rule 2. In a series of three or more terms with a single conjunction, use a comma after each term except the last
  • Rule 3. Enclose parenthetic expressions between commas
  • Rule 4. Place a comma before a conjunction introducing a co-ordinate clause
  • Rule 5. Do not join independent clauses by a comma
  • Rule 6. Do not break sentences in two

obra/writing-plans

Catalog entry: Productivity and Collaboration
Source documentation: https://github.com/obra/superpowers/blob/main/skills/writing-plans/SKILL.md

Function: Create strategic documentation

When to use it: Use when you have a spec or requirements for a multi-step task, before touching code

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Writing Plans
  • Overview
  • Scope Check
  • File Structure
  • Task Right-Sizing
  • Step Granularity
  • Plan Document Header
  • Task Structure
  • What a Step Contains
  • Self-Review
  • Execution Handoff

obra/writing-skills

Catalog entry: Development and Testing
Source documentation: https://github.com/obra/superpowers/blob/main/skills/writing-skills/SKILL.md

Function: Develop and document capabilities

When to use it: Use when creating new skills, editing existing skills, or verifying skills work before deployment

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Writing Skills
  • Overview
  • What is a Skill?
  • TDD Mapping for Skills
  • When to Create a Skill
  • Skill Types
  • Technique
  • Pattern
  • Reference
  • Directory Structure
  • Writing SKILL.md
  • Flowcharts
  • Code Examples
  • File Organization
  • Self-Contained Skill
  • Skill with Reusable Tool

openai/doc

Catalog entry: Skills by OpenAI
Source documentation: https://github.com/openai/skills/blob/main/README.md

Function: Read, create, and edit .docx documents with formatting and layout fidelity

When to use it: Reading DOCX files that contain tables or diagrams where layout context matters Generating a formatted report from structured data with consistent headings and styles Editing an existing contract or proposal without breaking its original formatting Validating a client document visually before sending it out Converting DOCX to PDF and spot-checking each page for spacing or alignment issues

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Agent Skills
  • Installing a skill
  • License

openai/figma

Catalog entry: Skills by OpenAI
Source documentation: https://github.com/openai/skills/blob/main/skills/.curated/figma/SKILL.md

Function: Use the Figma MCP server to fetch design context and translate nodes into production code

When to use it: Fetching exact layout and spacing from a Figma frame before writing component code Converting a Figma variant into React + Tailwind without manually measuring values Pulling SVG and image assets directly from Figma instead of exporting them manually Validating a finished UI implementation against the original Figma screenshot Troubleshooting Figma MCP setup and node ID resolution issues

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Figma MCP
  • Figma MCP Integration Rules
  • Required flow (do not skip)
  • Implementation rules
  • Asset handling
  • Link-based prompting
  • References

openai/figma-generate-design

Catalog entry: Skills by OpenAI
Source documentation: https://github.com/openai/skills/blob/main/skills/.curated/figma-generate-design/SKILL.md

Function: Translate app pages and layouts into Figma using design system tokens

When to use it: use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: ‘write to Figma’, ‘create in Figma from code’, ‘push page to Figma’, ‘take this app/page and build it in Figma’, ‘create a screen’, ‘build a landing page in Figma’, ‘update the Figma screen to match code’. This is the preferred workflow skill whenever the user wants to build or update a full page, screen, or view in Figma from code or a description. Discovers design system components, variables, and styles via search_design_system, imports them, and assembles screens incrementally section-by-section usi

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Build / Update Screens from Design System
  • Skill Boundaries
  • Prerequisites
  • Parallel Workflow with generate_figma_design (Web Apps Only)
  • Required Workflow
  • Step 1: Understand the Screen
  • Step 2: Discover Design System — Components, Variables, and Styles
  • Step 3: Create the Page Wrapper Frame First
  • Step 4: Build Each Section Inside the Wrapper
  • Step 5: Validate the Full Screen
  • Step 6: Updating an Existing Screen
  • Reference Docs
  • Error Recovery
  • Best Practices

openai/figma-implement-design

Catalog entry: Skills by OpenAI
Source documentation: https://github.com/openai/skills/blob/main/skills/.curated/figma-implement-design/SKILL.md

Function: Translate Figma designs into production-ready code with 1:1 visual fidelity

When to use it: Use when implementing UI code from Figma files, when user mentions “implement design”, “generate code”, “implement component”, provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Implement Design
  • Overview
  • Skill Boundaries
  • Prerequisites
  • Required Workflow
  • Step 1: Get Node ID
  • Step 2: Fetch Design Context
  • Step 3: Capture Visual Reference
  • Step 4: Download Required Assets
  • Step 5: Translate to Project Conventions
  • Step 6: Achieve 1:1 Visual Parity
  • Step 7: Validate Against Figma
  • Implementation Rules
  • Component Organization
  • Design System Integration
  • Code Quality

openai/openai-docs

Catalog entry: Skills by OpenAI
Source documentation: https://github.com/openai/skills/blob/main/skills/.curated/openai-docs/SKILL.md

Function: Provide authoritative guidance from OpenAI developer documentation

When to use it: Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • OpenAI Docs
  • Workflow Configuration
  • Source Priority
  • OpenAI product snapshots
  • Codex self-knowledge
  • Source Route
  • Surface Map
  • Boundaries And Output
  • If MCP server is missing
  • Workflow
  • Reference map
  • Quality rules
  • Tooling notes

openai/pdf

Catalog entry: Skills by OpenAI
Source documentation: https://github.com/openai/skills/blob/main/skills/.curated/pdf/SKILL.md

Function: Read, create, and review PDFs with layout and visual formatting integrity

When to use it: Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplumber`, and `pypdf` for generation and extraction.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • PDF Skill
  • When to use
  • Workflow
  • Temp and output conventions
  • Dependencies (install if missing)
  • Environment
  • Rendering command
  • Quality expectations
  • Final checks

openai/sentry

Catalog entry: Skills by OpenAI
Source documentation: https://github.com/openai/skills/blob/main/skills/.curated/sentry/SKILL.md

Function: Inspect Sentry issues, summarize production errors, and pull health data

When to use it: Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Sentry (Read-only Observability)
  • Quick start
  • Core tasks (use Sentry CLI)
  • 1) List issues (ordered by most recent)
  • 2) Resolve an issue short ID to issue detail
  • 3) Issue detail
  • 4) Issue events
  • 5) Event detail
  • 6) AI-powered root cause analysis
  • 7) AI-powered fix plan
  • Fallback: arbitrary API access
  • Inputs and defaults
  • Output formatting rules
  • Golden test inputs

openai/slides

Catalog entry: Skills by OpenAI
Source documentation: https://github.com/openai/skills/blob/main/README.md

Function: Create and edit .pptx presentation decks with PptxGenJS

When to use it: Rebuilding a PDF presentation into an editable .pptx from scratch Adding a bar chart to an existing slide without breaking the layout Checking a dense slide deck for text overflow before a client handoff Recreating a reference deck while matching its exact aspect ratio and typography Diagnosing font substitution warnings after opening a deck on a different machine

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Agent Skills
  • Installing a skill
  • License

openai/spreadsheet

Catalog entry: Skills by OpenAI
Source documentation: https://github.com/openai/skills/blob/main/README.md

Function: Create, edit, analyze, and visualize spreadsheets with formulas

When to use it: Building a financial model with formula-linked cells and color-coded inputs Converting a CSV export into a formatted .xlsx report with headers and borders Adding pivot-style summary tables to an existing workbook without breaking references Auditing a spreadsheet for broken formulas like #REF! or #DIV/0! errors Generating an IB-style DCF with section headers, indented line items, and cited assumptions

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Agent Skills
  • Installing a skill
  • License

PSPDFKit-labs/nutrient-agent-skill

Catalog entry: Productivity and Collaboration
Source documentation: https://github.com/PSPDFKit-labs/nutrient-agent-skill/blob/main/nutrient-document-processing/SKILL.md

Function: Document processing with Nutrient DWS API: convert (PDF/DOCX/XLSX/PPTX/HTML/images), extract text/tables, OCR (20+ languages), redact PII (pattern + AI), watermark, digital signatures, form filling. [MCP server](https://www\.npmjs\.com/package/@nutrient\-sdk/dws\-mcp\-server\) also available.

When to use it: Use when a task needs the capability described in this catalog entry: Document processing with Nutrient DWS API: convert (PDF/DOCX/XLSX/PPTX/HTML/images), extract text/tables, OCR (20+ languages), redact PII (pattern + AI), watermark, digital signatures, form filling. [MCP server](https://www\.npmjs\.com/package/@nutrient\-sdk/dws\-mcp\-server\) also available.

The catalog does not state a separate trigger condition. This usage note is inferred from the published function description.

Source skill menu:

  • Nutrient Document Processing
  • Product router
  • Setup
  • Paid-run approval gate
  • Helper preference
  • Single-operation helpers
  • Multi-step workflow template
  • Safety rules
  • Reference map

SHADOWPR0/beautiful_prose

Catalog entry: Marketing
Source documentation: https://github.com/SHADOWPR0/beautiful_prose/blob/main/SKILL.md

Function: Hard-edged writing style contract for timeless, forceful English prose without AI tics

When to use it: Use when users ask for prose or rewrites that must be clean, exact, concrete, and free of AI cadence, filler, or therapeutic tone.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Beautiful Prose (Claude Skill)
  • What this skill does
  • Activation
  • Absolute prohibitions
  • 1) Em dashes
  • 2) “It’s not X, it’s Y” constructions
  • 3) Filler transitions and scene-setting
  • 4) Therapeutic or validating language
  • 5) AI tells and meta commentary
  • 6) Symmetry padding
  • Positive constraints
  • Sentence craft
  • Word choice
  • Rhythm and structure
  • Authority
  • Registers (optional)

Skill_Seekers

Catalog entry: Development and Testing
Source documentation: https://github.com/yusufkaraaslan/Skill_Seekers/blob/development/README.md

Function: Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes

When to use it: Use when a task needs the capability described in this catalog entry: Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes

The catalog does not state a separate trigger condition. This usage note is inferred from the published function description.

Source skill menu:

  • Skill Seekers
  • 💛 Sponsors
  • Bronze Sponsors
  • 🚀 Quick Start
  • 🛰️ AI-driven project scan
  • All 18 source types
  • 📦 Installation
  • 📚 Documentation
  • 🎯 What you get
  • Export targets (22)
  • Why it matters
  • ✨ Key capabilities
  • 🔌 MCP Integration (40 tools)
  • 🤖 Installing to AI agents
  • Uploading to Claude
  • ⚙️ How it works

This catalog entry points to a collection. The scanned repository lists 26 distinct skill-file paths.

Sample members: skill-builder · skill-seekers · chat · chat_empty · chat_single · chat_topics · epub · epub_kw
More members are available in the source repository.

smixs/creative-director-skill

Catalog entry: Marketing
Source documentation: https://github.com/smixs/creative-director-skill/blob/main/creative-director/SKILL.md

Function: AI creative director with recursive self-assessment: 20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER, Synectics), 3-axis evaluation calibrated against Cannes/D&AD/HumanKind, 5-phase process from brief to presentation

When to use it: Use when the user asks to generate creative concepts, brainstorm campaign ideas, develop a Big Idea or campaign platform, evaluate or critique existing creative work, find consumer insights, or shares a brief for ideation — including activations, PR-stunts, brand utility, experiential, and non-advertising ideas. Calibrates against a library of 569 legendary campaigns (P01-P18 pattern map) to detect saturation and ensure originality. Do not use for media planning, production budgeting, brand identity/logo design, copywriting final drafts, or market research data collection.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Creative Director
  • Instructions
  • Phase Router
  • Phase 1: INTAKE (brief reception)
  • Phase 2: INSIGHT (insight discovery)
  • Phase 3: IDEATION (idea generation)
  • Phase 4: EVALUATE + REFINE (recursive cycle)
  • Phase 5: ARTICULATE (final output)
  • Creative Constitution (short form)
  • HumanKind Scale + Gap Analysis
  • Anti-Pitfall Rules
  • Calibration (dual system)
  • Output Format
  • Final deliverable (standard)
  • References
  • Examples

trailofbits/culture-index

Catalog entry: Security Skills by Trail of Bits Team
Source documentation: https://github.com/trailofbits/skills/blob/main/plugins/culture-index/skills/interpreting-culture-index/SKILL.md

Function: Index and search culture documentation

When to use it: Use when the user shares a Culture Index PDF or JSON profile, asks what someone’s CI traits mean, compares Culture Index profiles across a team or against a hiring profile, or asks about burnout risk from Survey-versus-Job gaps.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • When to Use
  • When NOT to Use

vercel-labs/writing-guidelines

Catalog entry: Skills by Vercel Engineering Team
Source documentation: https://github.com/vercel-labs/agent-skills/blob/main/skills/writing-guidelines/SKILL.md

Function: Review documentation against Writing Guidelines

When to use it: Use when asked to “review my docs”, “check writing style”, “audit prose”, “review docs voice and tone”, or “check this page against the writing handbook”.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Writing Guidelines
  • How It Works
  • Guidelines Source
  • Usage

zarazhangrui/frontend-slides

Catalog entry: Productivity and Collaboration
Source documentation: https://github.com/zarazhangrui/frontend-slides/blob/main/SKILL.md

Function: Generate animation-rich HTML presentations with visual style previews

When to use it: Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

Usage guidance is taken from the skill’s own trigger description or usage section.

Source skill menu:

  • Frontend Slides
  • Core Principles
  • Design Aesthetics
  • Fixed Stage Rules
  • Content Density Modes
  • Phase 0: Detect Mode
  • Mode C: Modification Rules
  • Phase 1: Content Discovery (New Presentations)
  • Step 1.2: Image Evaluation (if images provided)
  • Phase 2: Style Discovery
  • Step 2.0: Generate 3 Style Previews Directly
  • Step 2.1: User Picks
  • Phase 3: Generate Presentation
  • Phase 4: PPT Conversion
  • Phase 5: Delivery
  • Phase 6: Share & Export (Optional)

zilliztech/mfs

Catalog entry: Context Engineering
Source documentation: https://github.com/zilliztech/mfs/blob/main/README.md

Function: `mfs-find` / `mfs-ingest` skills that search, grep and read across your code, docs, chat (Slack/Gmail/Jira), databases and object stores as one file-like, searchable namespace; self-hosted with local ONNX embeddings

When to use it: Use when a task needs the capability described in this catalog entry: `mfs-find` / `mfs-ingest` skills that search, grep and read across your code, docs, chat (Slack/Gmail/Jira), databases and object stores as one file-like, searchable namespace; self-hosted with local ONNX embeddings

The catalog does not state a separate trigger condition. This usage note is inferred from the published function description.

Source skill menu:

  • 🚀 Quick start
  • Start the server
  • Install the CLI
  • Set environment variables
  • Skill install
  • 💡 Use cases
  • 🧠 Your agent’s memory and skills
  • 💻 Your codebases
  • 📄 Documents, images, any format
  • ☁️ Cloud drives and buckets
  • 🌍 Online sources
  • 💬 Team chat and tickets
  • 🎫 Customers and support
  • 🗄️ Production data
  • 🌐 One query across all of them at once
  • 🧰 Commands

This catalog entry points to a collection. The scanned repository lists 4 distinct skill-file paths.

Sample members: deep-research · open-tag · mfs-find · mfs-ingest

Back to the category index

本分类中文版

Writing & Documents | Agent Skills

https://songchen.science/blog/agent-skills/documents/

Author

Song Chen

Posted on

2026-11-02

Updated on

2026-11-02

Licensed under

#

Related Articles:

Like this article? Support the author with

Comments

Follow

Archives

Tags

AGI1
Agent Skills13
Alfred1
Automation3
Documentation4
Hexo2
Python_library1
Skills,Agent skills1
Software3
VoltAgent13
bibliography1
chart1
computational simulation1
condensed-matter physics1
data analysis1
data-science2
deep-learning1
encryptAsDiary2
fortran1
functional programming2
github1
machine-learning2
matplotlib1
multiprocessing1
neural-networks1
physics2
physics experiment3
plasma physics1
plugins1
poetry1
python16
python_configuration1
python_editors1
python_intermediate2
python_tools1
rust1
semiconductors1
superintelligence1
uv1
zotero1

follow.it

Recents

Latest Comments

×