Syncs project documentation with the current codebase and sprint status.
Install
mkdir -p .claude/skills/update-readme && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14635" && unzip -o skill.zip -d .claude/skills/update-readme && rm skill.zipInstalls to .claude/skills/update-readme
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Read the current project state by examining:Key capabilities
- →Read project context from `CLAUDE.md`
- →Examine `docs/mvp_strategy.md` for architecture
- →Check sprint specs in `docs/sprints/` for deliverables
- →Read `CURRENT_STATE.md` for active sprint and blockers
- →Analyze the actual source tree for existing files
- →Generate or update `README.md` with project details
How it works
This skill reads various project documentation files and the current source tree to synthesize an accurate `README.md` that reflects the project's current status, architecture, capabilities, and roadmap.
Inputs & outputs
When to use update-readme
- →Updating project status
- →Synchronizing documentation with sprint deliverables
- →Generating project summaries
About this skill
Read the current project state by examining:
CLAUDE.md— project context, stack, layers, directory structuredocs/mvp_strategy.md— architecture, sprint-to-stack mapping, MVP scopedocs/sprints/— all sprint specs, check which deliverables are marked [x] vs [ ]CURRENT_STATE.md— active sprint, blockers, what's next- The actual source tree — what files/modules exist right now
Then write or update README.md at the project root. The README should contain:
- Project name and one-line description — what Murmur is
- Status — which sprint is active, what's complete, what's next
- Architecture — the layer diagram from mvp_strategy.md, simplified
- Quick start — how to set up and run (uv sync, murmur init-db, murmur ingest --sample, pytest)
- Project structure — actual directory tree of what exists NOW (not aspirational), with one-line descriptions
- Current capabilities — what the system can actually do today
- Roadmap — remaining sprints with one-line descriptions
- Development — how to run tests, branch naming convention, CI info
- Standards — include this section at the end, always:
This project is built and maintained under Peyara engineering standards — a structured methodology for AI-assisted development covering session handoff, hypothesis-driven sprint phasing, TDD discipline, and living documentation. Standards are maintained at the Peyara organization level.
Rules:
- Only describe what EXISTS in the codebase right now. Do not document aspirational features as if they're built.
- Keep it concise. A senior engineer should be able to understand the project in 2 minutes.
- No badges, no emojis, no fluff. Clean, professional, informative.
- If README.md already exists, update it in place. Preserve any manually-added sections.
- After writing, present the HIGH PRIVILEGE ACTION block for commit sign-off.
When not to use it
- →When documenting aspirational features as if they are built
- →When adding badges, emojis, or fluff to the README
Limitations
- →Only describes what exists in the codebase
- →Requires specific project documentation files (`CLAUDE.md`, `mvp_strategy.md`, `CURRENT_STATE.md`)
- →Preserves manually-added sections in an existing `README.md`
How it compares
This skill automates the generation of a concise and professional `README.md` by directly querying project metadata and the codebase, ensuring the documentation is always synchronized with the actual project state, unlike manual updates.
Compared to similar skills
update-readme side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| update-readme (this skill) | 0 | 4mo | No flags | Intermediate |
| deepwiki-rs | 25 | 9mo | Review | Intermediate |
| codex-cli-bridge | 9 | 9mo | Review | Intermediate |
| skill-development | 17 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
deepwiki-rs
sopaco
AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.
codex-cli-bridge
alirezarezvani
Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools
skill-development
anthropics
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
skill-writer
pytorch
Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
openapi-spec-generation
wshobson
Generate and maintain OpenAPI 3.1 specifications from code, design-first specs, and validation patterns. Use when creating API documentation, generating SDKs, or ensuring API contract compliance.
korean-skill-creator
clwmfksek
한글 기반 클로드 스킬 자동 생성 도구. 사용자가 "클로드 스킬을 만들어줘" 또는 "[요구사항] 스킬 만들어줘"라고 요청할 때 사용. Progressive disclosure 원칙을 따르는 한글 문서 구조(SKILL.md + references/)를 자동으로 생성하고, 실전 예시를 포함한 일관성 있는 스킬 템플릿을 제공.