Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
npx claudepluginhub pcollinsonline/claude-asana --plugin plugins-claudeGenerate detailed technical documentation for a Claude Code skill. Use when the user asks to "document a skill", "document skill", "write docs for a skill", "create skill documentation", or references documenting anything in a .claude/skills/ directory.
Show status of loaded Claude Code reference documentation
Load Claude Code reference documentation into context for a task (e.g. creating skills, hooks, sub-agents, etc.)
Claude Code plugins for pnpm monorepos: plugins-utility (lifecycle logging), plugins-claude (reference-doc enforcement), and plugins-dev-tools (developer-workflow skills, agents, and an MCP server). Distributed as an org-wide marketplace from this repo — bundles are committed alongside source, so consumers install with no clone or build.
Paste this into your project's .claude/settings.json (or ~/.claude/settings.json for user scope):
{
"extraKnownMarketplaces": {
"claude-asana": {
"source": {
"source": "github",
"repo": "pcollinsonline/claude-asana"
}
}
},
"enabledPlugins": {
"plugins-utility@claude-asana": true,
"plugins-claude@claude-asana": true,
"plugins-dev-tools@claude-asana": true
}
}
Run claude and check /plugin list — the three plugins should appear and be enabled. No clone, no build, no auth (this repo is public).
To pick a subset, drop entries from enabledPlugins. To pin to a specific commit or branch, add "ref": "<sha-or-branch>" next to "repo" in the source.
| Path | Purpose |
|---|---|
.claude-plugin/marketplace.json | Plugin registry — root-level so the github source resolves with no path field |
marketplaces/monorepo-marketplace/ | Committed bundle output (one subdir per plugin) — what consumers fetch |
marketplaces/plugins-claude/ | Plugin source: Claude Code reference docs and README enforcement |
marketplaces/plugins-dev-tools/ | Plugin source: developer workflow skills, agents, and MCP server for pnpm monorepos |
marketplaces/plugins-utility/ | Plugin source: logging hooks for all Claude Code lifecycle events |
marketplaces/docs/ | Architecture documentation (plugins.md) — start here for plugin internals |
packages/plugins-base/ | Shared build pipeline (buildPlugin) and runtime utilities (readStdin, parseHookInput, etc.) used by every plugin |
scripts/claude-dev.sh | Launch Claude Code with --plugin-dir so plugins load directly from build output (bypasses cache) |
scripts/plugins-refresh.sh | Rebuild + reinstall enabled marketplace plugins |
For working on the plugins themselves (rather than consuming them), point your settings at the local checkout via the directory source:
{
"extraKnownMarketplaces": {
"claude-asana": {
"source": {
"source": "directory",
"path": "<path-to-this-repo>"
}
}
},
"enabledPlugins": {
"plugins-utility@claude-asana": true,
"plugins-claude@claude-asana": true,
"plugins-dev-tools@claude-asana": true
}
}
Then:
pnpm install
pnpm build
For day-to-day iteration, use scripts/claude-dev.sh instead — it launches Claude Code with --plugin-dir flags pointing directly at build output (no cache).
See marketplaces/docs/plugins.md for the full design — discovery, build pipeline, MCP servers, hook conventions, tool permissions, and orchestration patterns.
| Command | What it does |
|---|---|
pnpm build | Bundle every plugin into marketplaces/monorepo-marketplace/<plugin>/ via esbuild |
pnpm test | Run the vitest suites across all workspaces |
pnpm lint | Run eslint across all workspaces |
pnpm typecheck | Run tsc --noEmit across all workspaces |
pnpm clean | Remove .turbo and coverage from each workspace |
pnpm format | Run prettier on the entire repo |
scripts/claude-dev.sh | Launch Claude Code with plugins loaded from disk |
scripts/plugins-refresh.sh | Rebuild and reinstall enabled marketplace plugins |
Shared ESLint, TypeScript, and Vitest configuration comes from the dr-mike npm package (dr-mike/eslint, dr-mike/tsconfig/node, dr-mike/vitest).
This repo uses Conventional Commits and is set up with husky + lint-staged + commitlint. See CLAUDE.md for AI-assistant guidance.
UNLICENSED — internal use.
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Upstash 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).
Logging hooks for all Claude Code lifecycle events
Developer workflow skills and hooks for pnpm monorepos
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim