canvascoding/canvas-notebook / .claude/skills
opensrc
VerifiedFetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for", "read the source of", "how does X work internally", "get the implementation of", "opensrc path", or any task requiring access to dependency source code beyond types and docs.
Source Code Fetching with opensrc
Fetches dependency source code so agents can read implementations, not just types. Clones repositories at the correct version tag and caches them globally at ~/.opensrc/.
Core Pattern
rg "parse" $(opensrc path zod)
cat $(opensrc path zod)/src/types.ts
find $(opensrc path zod) -name "*.test.ts"
opensrc path <pkg> prints the absolute path to cached source. If not cached, it fetches automatically. Progress goes to stderr, path to stdout, so $(opensrc path ...) works in subshells.
Fetching Source Code
opensrc path zod
opensrc path pypi:requests
opensrc path crates:serde
opensrc path facebook/react
# Multiple packages at once
opensrc path zod react next
opensrc path pypi:requests pypi:flask
opensrc path crates:serde crates:tokio
# Specific versions
opensrc path zod@3.22.0
opensrc path pypi:flask@3.0.0
opensrc path owner/repo@v1.0.0
opensrc path owner/repo#main
Version Resolution
For npm packages, opensrc auto-detects the installed version from lockfiles (package-lock.json, pnpm-lock.yaml, yarn.lock). Use --cwd to resolve from a different project:
opensrc path zod --cwd /path/to/project
For PyPI and crates.io, explicit versions or latest are used. For repos, use @ref or #ref to pin a branch, tag, or commit.
Managing the Cache
Source is cached globally at ~/.opensrc/ (override with OPENSRC_HOME).
opensrc list # show all cached sources
opensrc list --json # JSON output
opensrc remove zod # remove a package
opensrc remove facebook/react # remove a repo
opensrc clean # remove everything
opensrc clean --npm # only npm packages
opensrc clean --pypi # only PyPI packages
opensrc clean --crates # only crates.io packages
opensrc clean --packages # all packages, keep repos
opensrc clean --repos # all repos, keep packages
When to Fetch Source
Fetch source when you need to:
- Understand internal behavior that types don't reveal
- Debug unexpected library behavior
- Learn patterns from well-known implementations
- Verify how a function handles edge cases
Don't fetch source for simple API usage questions that docs or types can answer.
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: 465k | 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 — 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 — 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 — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — 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) — 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 — don't Read the file). | Stars: 196k | 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: 196k | Updated | Claude CodeCodex | Verified | Install |