aiskillstore/marketplace / skills/0xhiroki/doc-writer
doc-writer
VerifiedCreate or update numbered task docs using repo context, DOC_TEMPLATE.md, and naming conventions.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.5 KB |
| skill-report.json | config | 12.5 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-04T13:29:54.681Z",
"slug": "0xhiroki-doc-writer",
"source_url": "https://github.com/0xhiroki/tassp/tree/main/.factory/skills/doc-writer",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "3715085546333f41bac3acc60bc3d97e337153d29a074d343ecc35b6f65f02a9",
"tree_hash": "ced043044c34e76ef0ede83e9cc60a69024d843019670fe1666bd80bfa3a94cc",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "doc-writer",
"description": "Create or update numbered task documents using repository context, a shared template, and established naming rules.",
"summary": "Creates structured task documents from repository plans, templates, and existing documentation.",
"icon": "π¦",
"version": "1.0.1",
"author": "0xhiroki",
"license": "MIT",
"tags": [
"documentation",
"task-planning",
"markdown",
"repository-docs"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands"
],
"category": "documentation"
},
"security_audit": {
"risk_level": "safe",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "The static findings are false positives caused by Markdown inline code around file paths and naming examples in SKILL.md. I found no prompt injection, data exfiltration intent, or unsafe command construction in the reviewed skill instructions.",
"remediation": [],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 9,
"line_end": 9
},
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 13
},
{
"file": "SKILL.md",
"line_start": 14,
"line_end": 14
},
{
"file": "SKILL.md",
"line_start": 19,
"line_end": 19
},
{
"file": "SKILL.md",
"line_start": 24,
"line_end": 24
}
]
}
],
"static_findings": [
{
"id": "external_commands:SKILL.md:9:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 9,
"line_end": 9,
"snippet": "Generate or refresh `docs/planned/XX-*.md` and `docs/completed/XX-*.md` files using the mandated tem"
},
{
"id": "external_commands:SKILL.md:13:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 13,
"line_end": 13,
"snippet": "- Read `docs/DOC_TEMPLATE.md` for structure expectations."
},
{
"id": "external_commands:SKILL.md:14:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 14,
"line_end": 14,
"snippet": "- Gather context from `PLAN.md`, `AGENTS.md`, and any existing task doc being updated."
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 19,
"line_end": 19,
"snippet": "5. Save the file under the correct directory (`docs/planned/` or `docs/completed/`) with the naming "
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 24,
"line_end": 24,
"snippet": "- Ensure the new/updated doc passes markdown lint (if configured) and adheres to `docs/DOC_TEMPLATE."
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:9:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "Line 9 uses Markdown inline code for documentation paths and a template path. It does not contain executable Ruby, shell expansion, or a command invocation."
},
{
"id": "external_commands:SKILL.md:13:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 13 refers to docs/DOC_TEMPLATE.md as a file to read. The backticks are Markdown formatting, not shell backtick execution."
},
{
"id": "external_commands:SKILL.md:14:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 14 lists repository documents to inspect using Markdown inline code. There is no command string, interpreter call, or user-controlled execution path."
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "Line 19 formats target directories and a filename convention with Markdown backticks. It describes where to save documentation files and does not execute commands."
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 24 uses Markdown inline code around the template path. The text is a documentation verification instruction, not Ruby or shell backtick execution."
}
],
"semantic_findings": [],
"critical_findings": [],
"high_findings": [],
"medium_findings": [],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 1,
"total_lines": 26,
"audit_model": "codex",
"audited_at": "2026-07-04T13:29:54.681Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Create Structured Task Documentation",
"value_statement": "Teams often lose task context when plans, requirements, and validation steps are scattered. This skill creates consistent task documents from repository context and templates.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"task documentation",
"markdown documentation",
"repository planning",
"DOC_TEMPLATE",
"developer workflow",
"technical writing",
"project documentation"
],
"actual_capabilities": [
"Reads docs/DOC_TEMPLATE.md to follow the required task document structure.",
"Uses PLAN.md, AGENTS.md, and existing task documents as repository context.",
"Creates numbered files under docs/planned or docs/completed with the NN-task-name.md format.",
"Drafts required sections for objectives, dependencies, implementation steps, validation, and completion criteria.",
"Links to related repository files instead of copying long excerpts.",
"Records validation commands when file changes require linting or tests."
],
"limitations": [
"Requires the repository to provide the expected docs/DOC_TEMPLATE.md file.",
"Does not define project strategy without source plans or task context.",
"May need human review for acceptance criteria and scheduling decisions.",
"Validator execution depends on the tools configured in the repository."
],
"use_cases": [
{
"title": "Plan a New Engineering Task",
"description": "Create a planned task document with clear objectives, dependencies, steps, validation, and completion criteria.",
"target_user": "Engineering leads"
},
{
"title": "Update an Existing Task Record",
"description": "Refresh a task document so it reflects current repository state, latest decisions, and completed validation work.",
"target_user": "Maintainers"
},
{
"title": "Standardize Documentation Before Review",
"description": "Align task notes with the shared template before opening a pull request or handing work to another contributor.",
"target_user": "Contributors"
}
],
"prompt_templates": [
{
"title": "Create a Basic Task Doc",
"scenario": "Beginner request for a new planned task.",
"prompt": "Create a new planned task document for [task name]. Use docs/DOC_TEMPLATE.md and relevant repository context."
},
{
"title": "Refresh an Existing Task Doc",
"scenario": "Update a document after requirements or code changed.",
"prompt": "Update docs/planned/[file name].md using PLAN.md, AGENTS.md, and current repository files. Keep the required template sections."
},
{
"title": "Document Completion Evidence",
"scenario": "Prepare a completed task record.",
"prompt": "Create a completed task document for [task name]. Include implemented changes, validation commands, completion criteria, and follow-up notes."
},
{
"title": "Reconcile Numbering and Scope",
"scenario": "Advanced request for a larger documentation pass.",
"prompt": "Review existing docs/planned and docs/completed numbering. Create the next task document for [scope] with unique numbering and repository links."
}
],
"output_examples": [
{
"input": "Create a planned task document for adding OAuth callback validation.",
"output": "A numbered planned task document with objective, dependencies, implementation steps, validation, completion criteria, and repository links."
},
{
"input": "Update the completed task document after linting and tests passed.",
"output": "A refreshed completed task document that records validation commands, current status, and any remaining follow-up work."
},
{
"input": "Prepare documentation for a handoff to another maintainer.",
"output": "A template-aligned task document that explains scope, context, next steps, and acceptance criteria for the maintainer."
}
],
"best_practices": [
"Provide the task name, target directory, and relevant repository files before asking for a new document.",
"Review generated acceptance criteria against actual project requirements before relying on them.",
"Run configured markdown linting or tests when documentation changes affect repository workflows."
],
"anti_patterns": [
"Do not ask the skill to invent missing requirements without project context.",
"Do not copy large source excerpts into task documents when relative links are enough.",
"Do not skip numbering checks when creating a new planned or completed task file."
],
"faq": [
{
"question": "What files does this skill use for context?",
"answer": "It uses docs/DOC_TEMPLATE.md, PLAN.md, AGENTS.md, and existing task documents when they are present."
},
{
"question": "Can it create both planned and completed task documents?",
"answer": "Yes. It writes documents under docs/planned or docs/completed according to the requested task status."
},
{
"question": "Does it choose the next task number?",
"answer": "Yes. It checks prior numbering and uses a unique two-digit prefix for new task files."
},
{
"question": "Does it run tests automatically?",
"answer": "It may run configured validators when file changes require them, then records the commands that were executed."
},
{
"question": "Can it replace project planning?",
"answer": "No. It structures known task information, but project owners should provide goals and approve final scope."
},
{
"question": "Which AI tools are supported?",
"answer": "The marketplace metadata lists support for Claude, Codex, and Claude Code."
}
]
},
"file_structure": [
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 26
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product β it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product β not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial β a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK β model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER β read BEFORE opening the target file; don't skip because it "looks like a one-liner" β whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) β never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named β don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. 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. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |