New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Documentation Writing

by pavel-molyanov in pavel-molyanov/molyanov-ai-dev

Creates and maintains project documentation in .claude/skills/project-knowledge/: interview, initial Project Knowledge, audit, edit, consistency, and feature finalization.

MITAuto-check passedWriting & Content

Install Documentation Writing

skills CLI
$ npx skills add pavel-molyanov/molyanov-ai-dev --skill documentation-writing -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install pavel-molyanov/molyanov-ai-dev documentation-writing --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/pavel-molyanov/molyanov-ai-dev.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/documentation-writing .claude/skills/documentation-writing && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
documentation-writing
GitHub stars
297
Token cost
~2.7k tokens
SKILL.md length
1,324 words
Files
4 (incl. references, assets)
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Creates and maintains project documentation in .claude/skills/project-knowledge/: interview, initial Project Knowledge, audit, edit, consistency, and feature finalization.

  • Works in 3 steps: Select the Evidence Source → Establish Durable Facts → Update or Report
  • : заполни документацию проекта
  • SKILL.md covers Manual Project Documentation…, Documentation Principles, Phase 1: Select the Evidence… and Phase 2: Establish Durable Facts, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Documentation Writing is an agent skill from pavel-molyanov/molyanov-ai-dev. Creates and maintains project documentation in .claude/skills/project-knowledge/: interview, initial Project Knowledge, audit, edit, consistency, and feature finalization. Use when: "заполни документацию проекта", "опиши проект", "создай Project Knowledge", "проведи интервью по проекту", "проверь документацию", "обнови документацию", "аудит документации", "plan a new project", "fill project documentation", "check docs", "audit documentation", "update docs" For reading docs or explaining concepts, read…

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files and assets (for example `assets/project-knowledge-interview.yml`, `references/create-project-knowledge.md` and `references/project-knowledge-structures.md`).

It sits in Writing & Content, covering Technical writing. The repository describes itself as: Intent-driven AI-First development methodology for Claude Code and Codex — Project Knowledge, user-spec planning, focused execution, and evidence-gated reviews. The licence is MIT.

When your agent uses it

  • : заполни документацию проекта
  • Создай Project Knowledge
  • Проведи интервью по проекту
  • Проверь документацию

Example prompts

  • “создай Project Knowledge”
  • “plan a new project”
  • “fill project documentation”
  • “/documentation-writing”

Requirements

  • Docker

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Select the Evidence Source
  2. Establish Durable Facts
  3. Update or Report

What it can do on your machine

Read from SKILL.md and the folder at commit b5db526. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Documentation Writing loads about 2.7k tokens when it runs, and up to ~5.2k if it reads all its reference files. Until then it costs about 141 tokens; SKILL.md has 1,324 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~141
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pavel-molyanov/molyanov-ai-dev at commit b5db526, republished under its MIT licence (© pavel-molyanov). 1,324 words, ~2,697 tokens.

Download SKILL.mdSave it as .claude/skills/documentation-writing/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
documentation-writing
description
Creates and maintains project documentation in .claude/skills/project-knowledge/: interview, initial Project Knowledge, audit, edit, consistency, and feature finalization. Use when: "заполни документацию проекта", "опиши проект", "создай Project Knowledge", "проведи интервью по проекту", "проверь документацию", "обнови документацию", "аудит документации", "plan a new project", "fill project documentation", "check docs", "audit documentation", "update docs" For reading docs or explaining concepts, read project-knowledge skill directly.

Documentation Management

Create and maintain .claude/skills/project-knowledge/ from the evidence source the user named.

Outside Feature Finalization Mode, follow create-project-knowledge.md when the user starts or continues initial documentation and either its interview is still in progress or Project Knowledge is missing, still a template, or only partially filled. Apply project-knowledge-structures.md for content ownership and structure. After writing, run the manual sync and continue at Documentation Review.

When the user explicitly asks to reorganize existing Project Knowledge, apply project-knowledge-structures.md. Ordinary updates preserve the filled structure already in use.

Manual Project Documentation Sync

Project documentation source of truth is Claude-side: CLAUDE.md and .claude/**. Codex-side AGENTS.md and .codex/** are generated runtime files. No scheduled job performs this conversion. The agent that changes the Claude source runs the matching command immediately and reviews the generated result before finishing the task.

After changing a project CLAUDE.md or any project-local .claude/** file, immediately run:

bash
~/.claude/scripts/sync-to-codex.sh --project "$PWD" --apply

If sync reports a conflict, stop and report it. Commit generated project .codex/** / AGENTS.md changes with their Claude sources, except .codex/.sync/**, which is host-local runtime state. When an approved deletion or rename produces orphaned managed outputs, verify that every reported path corresponds to that approved source change, then remove those generated leftovers with:

bash
~/.claude/scripts/sync-to-codex.sh --project "$PWD" --apply --prune --confirm-delete

If the orphan list contains anything else, stop and report it instead of pruning unrelated output.

Nested Agent Workspaces

Some projects keep an agent workspace under a subdirectory (for example nested-workspace/.claude/**) while the repository root exposes selected skills or agents through symlinks in root .claude/**. In that case, sync both levels:

bash
~/.claude/scripts/sync-to-codex.sh --project "$PWD/nested-workspace" --apply
~/.claude/scripts/sync-to-codex.sh --project "$PWD" --apply

Verify root .codex/agents / .codex/skills include every root-exposed agent or skill. A generated file existing only inside the nested workspace is not enough when the root runtime must invoke it. Treat .codex/.sync/** as host-local evidence: do not commit or synchronize it.

Documentation Principles

The reader should understand the project's purpose, structure, decisions, and operation without reconstructing them from code. Record durable project-specific facts: purpose and business logic; architecture, components, and their relationships; lasting agreements, decisions, and why those decisions were made; security rules and configuration names; deployment, operations, monitoring, recovery, where key code lives, and operational details an agent cannot infer from configuration alone.

Do not list functions, classes, local control flow, or implementation details that can be read from code. Treat an important non-obvious rule that applies only to a particular code path as code-owned: keep it out of Project Knowledge, and change a nearby code comment only when the user also requested source changes.

Keep generic framework, Git, Linux, SSH, Docker, journalctl, and systemctl explanations out of Project Knowledge. For operations, preserve facts such as host, user, non-default port, SSH alias, service or container name, log location, monitoring URL, environment-variable names, and emergency recovery behavior. Store an exact command only when the procedure is non-standard and cannot be recovered from project configuration.

Use source links instead of code snippets or pseudocode. Each fact has one owner file; update the existing section and cross-reference it elsewhere instead of appending a duplicate. patterns.md contains project-specific conventions, not general implementation advice.

Plans, user specs, tech specs, handoffs, and other work/ artifacts are evidence, not owners of current project state. Keep changing inventories in their authoritative registry, configuration, or runtime source; Project Knowledge records the durable rule, not current counts or members. If a Project Knowledge claim depends on a completed work artifact, correct that boundary instead of expanding the artifact.

File size alone is not a finding. Report a size-related issue only when evidence demonstrates duplication, stale content, implementation-level detail, or a structure that prevents useful selective loading.

Phase 1: Select the Evidence Source

Use the narrowest mode that matches the user's request:

  1. One current change: inspect the changed lines, the files they affect, and related callers or contracts needed to understand the durable result.
  2. Named commit or range: inspect exactly that commit or range plus the related files needed to interpret it.
  3. Recent history: when the user asks for the last N commits, inspect those N commits and their resulting current code.
  4. Full update or audit: inspect current code, all Project Knowledge, and CLAUDE.md.
  5. Specific documentation edit, consistency check, or status: inspect the named section and the documentation it can contradict.
  6. Feature finalization: use this mode only when the user explicitly asks to finish a feature (including /done) and provides or identifies work/{feature}/.

Do not search for user-spec.md or require it outside feature-finalization mode. A normal "update documentation" request does not archive work or create a finalization commit.

Phase 2: Establish Durable Facts

  1. Read the selected evidence and current target documentation before editing.
  2. Trace names, versions, service boundaries, data model, environment variables, deployment triggers, and operational facts to current sources. For full audits, also check placeholders, duplication, stale links, generic tutorial content, inconsistent terminology, and facts that no longer match the code.
  3. If Project Knowledge has no writable owner in the selected non-creation mode, report that no documentation target exists. Feature finalization keeps its explicit missing-documentation behavior below rather than starting an initial project interview from feature evidence.
Show full SKILL.md (487 more words)Show less

Phase 3: Update or Report

  1. For an edit/update request, integrate facts into existing sections and update any directly contradicting references.
  2. For an audit, consistency check, or status request, report evidence-backed issues without changing files unless the user also asked for fixes. Status classifications are filled, partial, template, or missing; size alone does not determine status.
  3. After changing a project CLAUDE.md or project-local .claude/**, run the manual sync described above. For a nested workspace, sync the nested source first and the repository root second.

Documentation Review

  1. Run no more than two review waves. After documentation edits, run wave 1 with a fresh documentation-reviewer with no model override. Give it the complete touched documents, the selected evidence boundary, related code and contracts, and the user's request. It returns its JSON result directly. Include reviewers required by other active skills in these same waves instead of starting a separate wave sequence.
  2. Review findings are diagnoses, not a work queue. Check the evidence and exact correction; apply only an authorized local correction to agreed normal documentation. If the scenario is rare or unagreed, or the correction adds behavior, state, entities, contracts, dependencies, architecture, or material complexity, reject it with a short reason or ask the user before editing. user_decision_required: false does not replace this check. Surface unrelated pre-existing defects without changing them.
  3. If an accepted correction changes the reviewed documentation, run wave 2 with a fresh reviewer. Stop after a clean wave or when no authorized correction changes the documentation.
  4. After wave 2, do not launch another reviewer automatically. Make only remaining local corrections inside the requested documentation change, run the applicable direct checks and manual sync, and show the user any remaining findings or required decisions.

Feature Finalization Mode

  1. Read user-spec.md, decisions.md when present, the implementation, and the relevant Git history. Compare the implemented result with the agreed spec.
  2. If the feature is evidently incomplete, explain the concrete gap and ask whether to continue finalization.
  3. Update only affected Project Knowledge through Phases 2-3 and Documentation Review. If Project Knowledge is missing, report that the documentation update was skipped and continue archival and finalization.
  4. Remove active Project Knowledge and backlog links that treat work/{feature}/ as a current source; do not add current operational inventory to completed artifacts.
  5. Move work/{feature}/ to work/completed/{feature}/ after documentation review.
  6. Commit the Project Knowledge changes and archive move with a concise documentation commit, then report the updated files and completed-feature path.

This is the only mode that reads feature artifacts by default, archives a feature, or creates the finalization commit.

Agent Entry Point

Keep CLAUDE.md minimal: project name, one-line description, reference to the Project Knowledge skill, backlog path, and default branch. Detailed project information belongs in Project Knowledge. Template: ~/.claude/skills/project-initialization/assets/new-project/CLAUDE.md.

Self-Verification

  • The requested documentation outcome matches the selected evidence and remains within scope.
  • No unresolved material deviation or contradiction is hidden from the user.

© pavel-molyanov, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references, assets) in skills/documentation-writing of pavel-molyanov/molyanov-ai-dev.

  • SKILL.md
  • assets/project-knowledge-interview.yml
  • references/create-project-knowledge.md
  • references/project-knowledge-structures.md

Open the folder on GitHubat commit b5db526

Compare with similar skills

Documentation Writing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Documentation Writing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Documentation Writing this skillpavel-molyanov/molyanov-ai-dev297—~2.7kAutomated safety check: PassMIT
JavaScript Concept Fact Checkerleonardomso/33-js-concepts67k1 repos~5kAutomated safety check: PassMIT
Beads Documentation Style Guidegastownhall/beads28k—~3.2kAutomated safety check: PassMIT
JavaScript Concept Page Workflowleonardomso/33-js-concepts67k—~3.9kAutomated safety check: PassMIT
Technical Writing Standardcursor/plugins11k10 repos~2.3kAutomated safety check: PassNone
JS Concept Resource Curatorleonardomso/33-js-concepts67k—~4.9kAutomated safety check: PassMIT

Similar skills

  • JavaScript Concept Fact Checker

    leonardomso/33-js-concepts

    Verifies the technical accuracy of JavaScript concept pages by checking code examples, MDN and ECMAScript claims and external links through a five-phase method.

    67k GitHub starsUsed in 1 repo~5k tokens
    Writing & ContentAuto-check passed

  • Beads Documentation Style Guide

    gastownhall/beads

    Sets the house style for the beads user docs: the canonical concept model, required terminology, prose and diagram conventions, and checks before docs work is done.

    28k GitHub stars~3.2k tokensUpdated today
    Writing & ContentAuto-check passed

  • JavaScript Concept Page Workflow

    leonardomso/33-js-concepts

    Orchestrates five skills to produce a complete JavaScript concept documentation page, from resource curation through writing, tests, fact-checking and SEO.

    67k GitHub stars~3.9k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

  • Technical Writing Standard

    cursor/plugins

    Official

    Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.

    11k GitHub starsUsed in 10 repos~2.3k tokens
    Writing & ContentAuto-check passed

  • JS Concept Resource Curator

    leonardomso/33-js-concepts

    Finds, vets, writes up and maintains external articles, videos and courses for JavaScript concept pages, including audits for broken and outdated links.

    67k GitHub stars~4.9k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

  • Writing Docs

    nukeop/nuclear

    A skill your agent uses when writing or editing documentation in packages/docs.

    19k GitHub stars~907 tokensUpdated 5 days ago
    Writing & ContentAuto-check passed

More from pavel-molyanov/molyanov-ai-dev

All 13 skills in this repo

  • User Spec Planning

    pavel-molyanov/molyanov-ai-dev

    Creates user-spec.md through adaptive interview, codebase research, and three-lane validation.

    297 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Infrastructure Setup

    pavel-molyanov/molyanov-ai-dev

    Provides project infrastructure conventions and review criteria for local setup, Docker, Git hooks, CI/CD, service delivery, release artifacts, monitoring, backups, and operations.

    297 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check: notes

  • Layout Writing

    pavel-molyanov/molyanov-ai-dev

    Reproduces and adjusts web layouts from Figma, Claude Design exports, screenshots, or an existing project style with high visual fidelity and proportional verification.

    297 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Skill Master

    pavel-molyanov/molyanov-ai-dev

    Guides skill creation and updates with specialized knowledge and workflows.

    297 GitHub stars~3.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Project Initialization

    pavel-molyanov/molyanov-ai-dev

    Initializes a project from the standard dual-runtime template, preserves existing files, configures Git hooks, and creates or connects a private GitHub repository with main and dev branches.

    297 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check: notes

  • Methodology

    pavel-molyanov/molyanov-ai-dev

    Explains the current AI-First development methodology: skill routing, Project Knowledge, user-spec planning and execution, evidence-gated reviews, feature finalization, and the Claude/Codex dual…

    297 GitHub stars~3.8k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Documentation Writing

What does Documentation Writing do?

Creates and maintains project documentation in .claude/skills/project-knowledge/: interview, initial Project Knowledge, audit, edit, consistency, and feature finalization. Documentation Writing is an agent skill from pavel-molyanov/molyanov-ai-dev.claude/skills/project-knowledge/: interview, initial Project Knowledge, audit, edit, consistency, and feature finalization.

When should I use Documentation Writing?

Documentation Writing fits situations like: : заполни документацию проекта; Создай Project Knowledge; Проведи интервью по проекту; Проверь документацию.

How do I install Documentation Writing in Claude Code?

Run `npx skills add pavel-molyanov/molyanov-ai-dev --skill documentation-writing -a claude-code`. Or copy the skill folder (skills/documentation-writing in pavel-molyanov/molyanov-ai-dev) into .claude/skills/documentation-writing in your project. Claude Code loads it when a task matches its description.

How do I install Documentation Writing in Codex?

Run `npx skills add pavel-molyanov/molyanov-ai-dev --skill documentation-writing -a codex`. Or copy the skill folder (skills/documentation-writing in pavel-molyanov/molyanov-ai-dev) into .agents/skills/documentation-writing in your project. Codex loads it when a task matches its description.

Can I use Documentation Writing in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pavel-molyanov/molyanov-ai-dev --skill documentation-writing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/documentation-writing, .gemini/skills/documentation-writing, .github/skills/documentation-writing and .opencode/skills/documentation-writing in your project.

What does Documentation Writing need to run?

SKILL.md names no scripts, command-line tools or credentials: Documentation Writing is instructions for the agent only. Our summary lists: Docker.

Does Documentation Writing access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Documentation Writing safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Documentation Writing use?

Documentation Writing is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Documentation Writing use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.5k tokens, read only when the agent opens those files.

What are the alternatives to Documentation Writing?

Skills that share tags, products or a category with Documentation Writing: JavaScript Concept Fact Checker (leonardomso/33-js-concepts, 67k stars), Beads Documentation Style Guide (gastownhall/beads, 28k stars), JavaScript Concept Page Workflow (leonardomso/33-js-concepts, 67k stars) and Technical Writing Standard (cursor/plugins, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Documentation Writing?

pavel-molyanov (a GitHub user) maintains it in pavel-molyanov/molyanov-ai-dev, which has 297 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on August 23, 2026.

Source: pavel-molyanov/molyanov-ai-dev on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.