Loading...
Loading...
Found 199 Skills
Research-first, evidence-first implementation planning in seven gated phases: frame the task, inventory the real codebase, verify ground truth from vendor source or official docs, adversarially audit existing code, analyze gaps, commit to design decisions, and write a phased plan document with timeline, risks, and verification. Enforces "no claim without evidence, no design before research". Use when the user asks to plan, design, architect, audit, or review before implementing a feature, refactor, migration, or system, or mentions deep-plan, /deep-plan, or Plan mode.
Audit a codebase for dead code, unreachable branches, duplicated logic, and vestigial abstractions, then remove them safely with proof. Use to reduce sprawl, pay down tech debt, or clean up after a feature is retired or migrated.
Audit and remove dead code, AI residue, and unnecessary complexity after iteration.
Run a bounded, evidence-first audit-fix-review-verify loop on a codebase when the user asks to improve, harden, overhaul, or fix all confirmed defects. Use only with explicit edit authority in a git repository. Do not use for advisory-only reviews, a single narrow bug, or when the worktree is dirty and the owner has not chosen how to preserve it.
Audit Claude Code configuration against latest features and best practices. Use when user says "evolve", "self-improve", "audit config", "what's new in claude code", "upgrade configuration", "check for improvements", "are we up to date".
Audits Move contracts for security vulnerabilities before deployment using 7-category checklist. Triggers on: 'audit contract', 'security check', 'review security', 'check for vulnerabilities', 'security audit', 'is this secure', 'find security issues'.
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.
4-phase code review methodology: UNDERSTAND changes, VERIFY claims against code, ASSESS security/performance/architecture risks, DOCUMENT findings with severity classification. Use when reviewing pull requests, auditing code before release, evaluating external contributions, or pre-merge verification. Use for "review PR", "code review", "audit code", "check this PR", or "review my changes". Do NOT use for writing new code or implementing features.
Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says "judgment day", "judgment-day", "review adversarial", "dual review", "doble review", "juzgar", "que lo juzguen".
Review code for security issues before merge — authz gaps, injection, secrets, unsafe defaults, SSRF, path traversal. Use when reviewing a PR, auditing a diff, shipping auth/payments/uploads, or when the user asks for a security review or OWASP check.
Review Go and TypeScript code for performance problems — allocations, GC pressure, O(n²) algorithms, N+1 queries, unbounded concurrency, blocked event loops, re-render storms. Works on uncommitted changes, a commit range, a branch, or a full PR. Use when the user says "perf review", "check performance", "find bad allocs", "is this slow", "review allocations", "will this scale", or asks for a performance pass on a diff, branch, or PR. Do not use for general correctness review or style review — this skill only hunts performance.
Audit UI code for audio feedback best practices. Use when reviewing sound implementation, checking audio UX decisions, or auditing accessibility. Outputs file:line findings.