Loading...
Loading...
Found 22 Skills
Execute bash commands against any public GitHub repository without cloning it locally. Use when the user needs to explore, search, or analyze external repos, check dependency source code, or investigate implementation details in third-party code.
Conversationally guides the user to a CLAUDE.md file. Starts by inferring what it can from the repo, asks ~8 core questions, then offers optional depth across business, voice, and working-style topics. Use when the user wants a CLAUDE.md but would rather have a conversation than fill out a form.
Multi-repo synthesis and reimagination. Load reverse-engineering docs from multiple repositories, extract a unified capability map, identify duplication and inefficiency, then brainstorm with the user to reimagine how those capabilities could work together in a new, better way. Generates new specifications for the reimagined system. The killer feature for enterprise modernization.
Analyze an unfamiliar repository and explain what it does, how it runs, what architectural choices define it, where the important code lives, and what deserves deeper inspection next. Use this whenever a user has just cloned a repo, wants onboarding help, asks for a repo walkthrough, or needs a reliable first-pass architecture analysis.
Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or non-security ownership questions.
Evidence-grounded legacy-repository understanding with recurrent human feedback and bounded skill convergence. Activates when the user asks to understand, map, document, onboard to, refactor, modify, or assess a repository.
Performs Technical Due Diligence on startups. Analyzes code (if available) or evaluates public signals (hiring, blogs) to assess technical risk and team maturity.
Srcwalk is the agent's code navigator: one tree-sitter CLI for repo maps, token-aware large-file reads, symbol search, callers/callees, deps, impact checks, and precise drill-ins. Use it before raw reads or grep for code-structure work. Run `srcwalk guide` first. Must use! It is the installed binary's source of truth.
Codebase Onboarding
Audit how agent context (CLAUDE.md / AGENTS.md / rules / skills) lines up with the code across a set of repositories and generate a self-contained HTML report — a short list of specific "things to check" (context behind the code, thin coverage for the codebase, oversized files, no per-area context), plus per-repo raw metrics and a folder tree comparing folder LOC to context coverage. Use when the user wants to audit context coverage across repos, "which repos are missing CLAUDE.md", "where is our agent context thin or stale", "context coverage across my org / projects folder", or "/context-coverage". Works on a local folder of clones or a whole GitHub org via the gh CLI.