菜单
Read a Google Docs document, Google Slides presentation, or Google Sheets spreadsheet and output as Markdown or CSV. Use this skill when asked to read, fetch, import, or convert a Google Doc, Google Slides, or Google Sheets URL.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Documentation workflow orchestrator. Reads the step list from .agent_workspace/docs-workflow.yaml (or the plugin default). Runs steps sequentially, manages progress state, handles iteration and confirmation gates. Claude is the orchestrator — the YAML is a step list, not a workflow engine.
Write documentation from a documentation plan. Dispatches the docs-writer agent. Supports AsciiDoc (default) and MkDocs formats. Default placement is UPDATE-IN-PLACE; use --draft for staging area. Also supports fix mode for applying technical review corrections.
Score documentation quality and intent alignment using LLM judge agents (Opus). Dispatches two judge agents in parallel (doc_quality, intent_alignment), extracts specific gaps from AC coverage analysis, and cross-references against scope-req-audit evidence. Produces pass/fail gate with actionable gap list. Iteration logic is owned by the orchestrator, not this skill.
Run code-learner analysis on a source repository for the docs orchestrator workflow. Dispatches a subagent to run learn-code, keeping the heavy orchestration out of the main context. Produces ONBOARDING.md, module registry, per-module summaries, and cross-module relationship data.
Classify JIRA requirements by code evidence status before planning. Uses learn-code analysis data and source code inspection to determine if each requirement is grounded, partial, or absent. Fans out one subagent per requirement for isolated classification. Prevents hallucinated documentation for unimplemented features and surfaces gaps for implemented ones. Conditional on has_source_repo.
Technical accuracy review with optional code-learner claim validation. Iteration logic owned by the orchestrator.
| name | docs-convert-gdoc-md |
| description | Read a Google Docs document, Google Slides presentation, or Google Sheets spreadsheet and output as Markdown or CSV. Use this skill when asked to read, fetch, import, or convert a Google Doc, Google Slides, or Google Sheets URL. |
| model | claude-haiku-4-5@20251001 |
| allowed-tools | Bash, Read, Write |
Export Google content using gcloud CLI or Google Application Default Credentials for authentication:
.md).md) via PPTX with slide titles, bullet points, tables, and speaker notes.csv)gcloud CLI installed and authenticated via gcloud auth login --enable-gdrive-accessGOOGLE_APPLICATION_CREDENTIALS to a service-account JSON path, run gcloud auth application-default login, or use attached workload/metadata credentialspython-pptx is installed for Slides export (python3 -m pip install python-pptx)The script is at ${CLAUDE_SKILL_DIR}/scripts/gdoc2md.py.
Always quote the URL and output file arguments:
uv run --script ${CLAUDE_SKILL_DIR}/scripts/gdoc2md.py [--comments] [--include-resolved] "<url>" ["<output_file>"]
/document/d/ → Google Docs → Markdown/presentation/d/ → Google Slides → Markdown (via PPTX)/spreadsheets/d/ → Google Sheets → CSV<id>.md or <id>.csv.Use --comments to pull comment threads from the document and insert them as Markdown footnotes:
uv run --script ${CLAUDE_SKILL_DIR}/scripts/gdoc2md.py --comments "<google-doc-url>"
--include-resolved to include them.--comments flag only applies to Google Docs. The script ignores it for Slides and Sheets.gcloud auth login --enable-gdrive-access.gcloud nor ADC is configured. Tell the user to set up one of the methods described in Prerequisites.python-pptx not installed. Tell the user to run python3 -m pip install python-pptx.