AGENT SKILL

doc

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

License 许可
Apache-2.0
最近更新
2026-11-14
Stars
★ 3.3w
Forks
3.9k

01 前言 Front Matter

name
doc
metadata
{ "author": "openai" }
description
Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

02 资源文件 5

03 SKILL.md 正文

DOCX Skill

When to use

  • Read or review DOCX content where layout matters (tables, diagrams, pagination).
  • Create or edit DOCX files with professional formatting.
  • Validate visual layout before delivery.

Workflow

  1. Prefer visual review (layout, tables, diagrams).
    • If soffice and pdftoppm are available, convert DOCX -> PDF -> PNGs.
    • Or use scripts/render_docx.py (requires pdf2image and Poppler).
    • If these tools are missing, install them or ask the user to review rendered pages locally.
  2. Use python-docx for edits and structured creation (headings, styles, tables, lists).
  3. After each meaningful change, re-render and inspect the pages.
  4. If visual review is not possible, extract text with python-docx as a fallback and call out layout risk.
  5. Keep intermediate outputs organized and clean up after final approval.

Temp and output conventions

  • Use tmp/docs/ for intermediate files; delete when done.
  • Write final artifacts under output/doc/ when working in this repo.
  • Keep filenames stable and descriptive.

Dependencies (install if missing)

Prefer uv for dependency management.

Python packages:

uv pip install python-docx pdf2image

If uv is unavailable:

python3 -m pip install python-docx pdf2image

System tools (for rendering):

# macOS (Homebrew)
brew install libreoffice poppler

# Ubuntu/Debian
sudo apt-get install -y libreoffice poppler-utils

If installation isn't possible in this environment, tell the user which dependency is missing and how to install it locally.

Environment

No required environment variables.

Rendering commands

DOCX -> PDF:

soffice -env:UserInstallation=file:///tmp/lo_profile_$$ --headless --convert-to pdf --outdir $OUTDIR $INPUT_DOCX

PDF -> PNGs:

pdftoppm -png $OUTDIR/$BASENAME.pdf $OUTDIR/$BASENAME

Bundled helper:

python3 scripts/render_docx.py /path/to/file.docx --output_dir /tmp/docx_pages

Quality expectations

  • Deliver a client-ready document: consistent typography, spacing, margins, and clear hierarchy.
  • Avoid formatting defects: clipped/overlapping text, broken tables, unreadable characters, or default-template styling.
  • Charts, tables, and visuals must be legible in rendered pages with correct alignment.
  • Use ASCII hyphens only. Avoid U+2011 (non-breaking hyphen) and other Unicode dashes.
  • Citations and references must be human-readable; never leave tool tokens or placeholder strings.

Final checks

  • Re-render and inspect every page at 100% zoom before final delivery.
  • Fix any spacing, alignment, or pagination issues and repeat the render loop.
  • Confirm there are no leftovers (temp files, duplicate renders) unless the user asks to keep them.

04 同仓库更多 Skills

davila7
davila7/claude-code-templates

wealthville-pool-scoring

Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter/Hold/Exit/Reduce/Avoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.

Skill与智能体开发
★ 3.3w
davila7
davila7/claude-code-templates

technical-debt-auditor

Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO/FIXME/HACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like "where should I focus refactoring", "find code smells", "audit my codebase", "what technical debt do we have", "prioritize cleanup work", or asks about code quality metrics. Also trigger when the user mentions "code rot", "legacy cleanup", "refactoring priorities", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say "technical debt" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.

Skill与智能体开发
★ 3.3w
davila7
davila7/claude-code-templates

readonly-sql-guard

Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production/ERP/analytics database (a "query" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write/DDL/side-effect/transaction-escape risks. Checks what a statement CALLS, not just its shape.

数据分析师后端与接口Skill与智能体开发
★ 3.3w
davila7
davila7/claude-code-templates

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 3.3w
davila7
davila7/claude-code-templates

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

测试与质量前端开发
★ 3.3w
davila7
davila7/claude-code-templates

discernment-nudge

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.

内容创作者写作与文案Skill与智能体开发
★ 3.3w