Loading...
Loading...
Found 199 Skills
Analytical thinking patterns for comprehensive evaluation, code audits, security analysis, and performance reviews. Provides structured templates for thorough investigation with extended thinking support.
Captures quality metrics baseline (tests, coverage, type errors, linting, dead code) by running quality gates and storing results in memory for regression detection. Use at feature start, before refactor work, or after major changes to establish baseline. Triggers on "capture baseline", "establish baseline", or PROACTIVELY at start of any feature/refactor work. Works with pytest output, pyright errors, ruff warnings, vulture results, and memory MCP server for baseline storage.
Run a structured, adversarial multi-agent bug review pipeline on a codebase. Use this skill whenever the user wants to find bugs, audit code quality, review a codebase for issues, or run any kind of bug-finding or code analysis workflow. Also trigger when the user asks to 'review my code for bugs', 'find all issues in this repo', 'audit this codebase', or any similar request. The pipeline uses three sequential phases: a Bug Finder that maximizes issue discovery, a Bug Adversary that challenges false positives, and an Arbiter that issues final verdicts — producing a clean, high-confidence bug report.
Write and audit Python code comments using antirez's 9-type taxonomy. Two modes - write (add/improve comments in code) and audit (classify and assess existing comments with structured report). Use when users request comment improvements, docstring additions, comment quality reviews, or documentation audits. Applies systematic comment classification with Python-specific mapping (docstrings, inline comments, type hints).
Code review and audit system with specialized sub-skills covering SOLID principles, security, performance, architecture, error handling, testing, code smells, design patterns, and framework best practices. Generates severity-scored findings with copy-pasteable fix prompts. Strictly read-only — never modifies user code. Use when user says "review", "audit", "code review", "check my code", "security scan", "code smells", "SOLID check".
System Audit - Proactively identify bug risks, security vulnerabilities, performance issues, maintainability debt, and architecture drift from code, and generate a batch list of findings. Triggers: Users say "review the system", "audit code", "scan for issues", "find bugs", "what can be optimized".
Find composition and state-lifting refactor opportunities in a React codebase. Audits for boolean-prop bloat, monolith components with variant explosion, sibling clusters that should share lego-brick subcomponents, render-prop slots that can't reach outside the box, and state synced between siblings via useEffect. Use when the user wants to improve react code, audit react components, find react refactor opportunities, run a react composition review, or asks "improve react", "audit react", "react architecture review".
Use when code has been written and needs validation before committing, or when the user asks for a code review or security check.
Deep retrospective audit of everything merged to main over a window - code quality against the stand-* skills, introduced bugs, unsafe changes, merges over red signals, hollow thread resolutions, and untracked deferrals - with a tabbed HTML report as the deliverable. Use when asked to audit merges, review what landed on main, or verify automated/agent-authored merges were up to standard.
When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).
Audit a web codebase for security, performance, correctness, and refactoring improvements WITHOUT changing any outward-facing behavior. Fans out parallel read-only reviewers, scores findings on two axes (severity × confidence), suppresses predictable false positives, validates survivors with an INDEPENDENT wave (not self-recheck), classifies safe vs. gated, and writes a report. Applies only behavior-preserving fixes, and only on request. Use when: 'rigorous review', 'hardening audit', 'security and performance audit', 'internal audit', 'harden the codebase', 'audit for security/perf/refactoring', 'tech-debt audit', 'review this codebase without changing behavior'.
Code principles audit worker (L3). Checks DRY (7 types), KISS/YAGNI, TODOs, error handling, DI patterns. Returns findings with severity, location, effort, recommendations.