Loading...
Loading...
Found 545 Skills
PASS, FLAG, and BLOCK review discipline for workflow review, QA verification, release checks, and issue closeout.
Use when writing, fixing, editing, reviewing, or refactoring any Python code. Enforces Robert Martin's complete Clean Code catalog—naming, functions, comments, DRY, and boundary conditions.
Consult an advisory council of three AI personas — Cato (skeptic), Ada (optimist), Marcus (pragmatist) — backed by different frontier LLM agents (Gemini, Claude, Codex). Each persona runs as a separate agent process with full repo context and returns independent feedback. Use when the user says "/council", asks for a second opinion, wants feedback on code changes, needs a premortem, wants to pressure-test a decision, or asks "what do you think about this approach?" Claude may also proactively suggest consulting the council before major architectural decisions, risky deploys, or ambiguous trade-offs (but should ask for user approval first).
Submit pull request (PR) review from chat session to PR conversations. Use when asked to "submit PR review" or "submit review to PR #123". Identifies issues in the current chat session, creates line-specific review comments, avoids duplication with existing comments, and submits the review via GitHub CLI.
Shared Python best practices for LlamaFarm. Covers patterns, async, typing, testing, error handling, and security.
Add line-specific review comments to pull requests using GitHub CLI API
Iteratively review changes, run automated tests, and apply targeted fixes until issues are resolved (or a stop condition is reached).
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
Detect and remediate Go anti-patterns: premature interface abstraction, goroutine overkill, context soup, error wrapping mistakes, generic abuse, channel misuse, unnecessary function extraction, and interface pollution. Use when reviewing Go code for quality, detecting over-engineering, or when user mentions "anti-pattern", "code smell", "Go mistake", or "bad Go". Do NOT use for feature implementation, performance optimization without a code smell, or non-Go languages.
Comprehensive codebase reading engine. Systematically reads actual source code line by line through a 6-phase protocol — scoping, structural mapping, execution tracing, deep reading, pattern synthesis, and structured reporting. Source code is the source of truth. Use when needing to truly understand how code works, not just what documentation claims.
Follow up on an existing PR by rebasing on the base branch, addressing reviewer comments, fixing CI issues, and pushing updates. Use when the user provides a PR URL or number and wants to get it ready for merge.
Generate Stage chapters for the current local git branch and open them in a browser for review.