source-investigator
Source Investigator
Inspect real source when that is the most reliable way to answer the question. Keep the main thread focused on synthesis and decisions, not on carrying around large amounts of raw source code.
Workflow
- Decide whether source inspection is warranted.
- Prefer source over docs when the question depends on real control flow, defaults, edge cases, or version-specific behavior.
- Prefer docs first for public API overviews or setup instructions. If docs are still useful, have a subagent use
find-docsrather than loading long documentation into the main thread. - If the user named a specific repo, library, or framework version, treat that as a strong signal to inspect the exact source.
- Create a project-local temp workspace before cloning.
- Work from the current project root.
- Create
.tmp/if it does not exist. - Create or update
.gitignoreso.tmp/is ignored. Do not assume a.gitignorefile already exists. - Keep disposable investigation clones under
.tmp/repos/. - Keep any generated notes or scratch outputs under
.tmp/work/.
- Clone the exact repository and ref you need.
More from sjunepark/custom-skills
summarize
Use the steipete/summarize CLI to summarize URLs, local files, stdin, YouTube links, podcasts, and media with LLM models. Trigger when users ask to install or run summarize, configure model/provider API keys, tune output flags (length/language/json/extract/slides), set defaults in ~/.summarize/config.json, or troubleshoot summarize CLI errors.
42skills-cli
Operate the skills CLI to discover, install, list, update, remove, and initialize skills for Codex, Claude Code, and Pi. Use when users ask to manage skills from skills.sh, restore from lock files, sync skills from node_modules, or troubleshoot agent/installation scope (project vs global).
37post-implementation-review
Manually review already-implemented code for design flaws, abstraction issues, structural problems, or refactors that only became clear in real code. Use only when the user explicitly asks for a post-implementation review, explicitly asks whether recent implementation work revealed design or structure problems, or explicitly wants refactor recommendations after the code exists. Do not auto-trigger for ordinary implementation, debugging, explanation, or generic code review requests. Prefer embedded snippets with file-path comments over editor-oriented file and line references. Treat findings as signals about code shape and quality; prioritize root-cause design, ownership, abstraction, and organization improvements, including broad refactors when warranted, over bandage fixes such as tiny helper extractions or local polish.
30architecture-md-writer
Create, update, review, and split ARCHITECTURE.md files that explain a codebase's shape, major components, runtime flow, code map, and important invariants. Use when a repository lacks architecture docs, an existing ARCHITECTURE.md is stale or too detailed, a subsystem needs its own nested ARCHITECTURE.md, or a root architecture doc should link to deeper module architecture docs.
27agents-md-writer
Create, edit, review, and improve AGENTS.md files for repositories used by agentic coding tools with concise, actionable instructions and correct precedence behavior. Use whenever AGENTS.md content is being changed, including updating existing guidance, drafting a new AGENTS.md, migrating legacy instruction files, defining nested overrides in monorepos, or debugging why tools load the wrong guidance.
26briefing
Manually brief the user on the current task or session so they can make the next decision without reloading the whole codebase. Use only when the user explicitly asks for a briefing, catch-up, current state, relevant architecture, or implementation context. Prefer this skill for task-scoped context recovery when the conversation is long, the code has changed, or the user wants the relevant details without a long explanation.
22