By cosgroveb
README writing skill that verifies repo facts before drafting or reviewing.
Claude Code plugin for README files that verify repo facts, get users to a first run, and push detail into the right docs.
/plugin marketplace add cosgroveb/agent-readme-skill
/plugin install agent-readme-skill@agent-readme-skill
/reload-plugins
Invoke directly:
/agent-readme-skill:agent-readme-skill
Or describe what you need and the skill picks up from context:
Rewrite this README so a new user can run the tool in a minute
Review README.md for install path, license, and quick start problems
Draft a README for this CLI and link the full flag reference instead of dumping it inline
The skill reads repo facts first: package metadata, docs, examples, license, build files, and release artifacts. It treats unverified README claims as bugs.
Source of truth is skills/. Reference docs live inside the skill directory at skills/agent-readme-skill/doc/.
make dist builds to dist/claude-plugin/ (Claude Code plugin bundle) and dist/agents/ (.agents skill bundle). CI owns dist/; do not edit it by hand.
For skill behavior, edit skills/** and .claude-plugin/**. Leave dist/** to CI.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimDebian packaging skill covering policy, debhelper, and language-specific packaging for Ruby, Python, Rust, and Go.
Persist project roadmap and feature memory in atuin, with optional cross-project priming memory.
Persist project roadmap and feature memory in atuin, with optional cross-project priming memory.
Ousterhout's Philosophy of Software Design applied to Go. Strategic design principles for writing deep modules, hiding information, and fighting complexity in Go codebases.
Expert prompt engineering for LLM coding agents
npx claudepluginhub cosgroveb/agent-readme-skill --plugin agent-readme-skillUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).