224 skills · sorted by relevance
Full codebase health assessment. Use when diagnosing project health or starting a rescue workflow on legacy code — OR when evaluating an external GitHub repo for dependency / fork / contribution decisions (--external mode). Analyzes complexity, dependencies, dead code, tech debt, and git hotspots. Produces a health score and rescue plan.
The English summary is being prepared. Showing the original description.
Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.
The English summary is being prepared. Showing the original description.
Use before opening a PR, or whenever asked to self-review a diffusers contribution. Applies the same rubric as the `@claude` CI (checks the diff against references/review-rules.md, traces call paths for dead code). Reports findings grouped by severity, flagging what to fix before submitting (blocking issues + dead code) vs what to leave for the actual review. Report-only — does not edit files.
The English summary is being prepared. Showing the original description.
Use when asking whether something in imp is actually finished - hunting stubs, placeholders, request fields that are parsed and then ignored, code paths or kernels that never run, gate-based features that silently no-op, tests that assert nothing. Triggers on "is this implemented", "unfinished", "stub", "placeholder", "dead path", "does this flag do anything", "accepted but ignored", "kernel never launched", "test asserts nothing", "neutral A/B on a gated feature". Do NOT use for structural debt / god files / duplication (codebase-audit) or for who-calls-what (code-graph).
The English summary is being prepared. Showing the original description.
Compiler-level code intelligence via native LSP — definitions, references, types, call hierarchies, and diagnostics.
The English summary is being prepared. Showing the original description.
Simplify working code while preserving behavior—remove dead paths, flatten nesting, clarify names, reduce duplication. Use after features work but code feels over-engineered.
The English summary is being prepared. Showing the original description.
Run a focused tech debt reduction sprint — inventories all technical debt (TODOs, outdated deps, missing tests, god objects), fixes code smells, removes dead code, then hardens with a review pass. Use when a codebase feels sluggish, before a major feature push, or on a regular maintenance cadence.
The English summary is being prepared. Showing the original description.
Run comprehensive code audit for architecture, dead code, and test quality. Use when reviewing overall codebase health, checking for architectural violations, or before marking a feature complete.
The English summary is being prepared. Showing the original description.
Checks unreachable code, unused imports/variables/functions, commented-out code, backward compatibility shims, deprecated patterns. Returns findings.
The English summary is being prepared. Showing the original description.
Perform comprehensive technical reviews of Ruby on Rails applications. Runs automated analysis tools (RubyCritic, Brakeman, bundler-audit, Gitleaks, Debride, linters, SimpleCov, Rails stats, Rails ERD), analyzes code for architecture, security, authorization (Pundit/CanCanCan), dead code, and design issues, and produces a structured markdown report with prioritized findings and a 0-10 score. Use when the user requests a tech review, code audit, project assessment, or quality analysis of a Rails application.
The English summary is being prepared. Showing the original description.
Audit agent runtimes and their tests for lifecycle inference, capability overload, context pollution, correlated verification, prompt-only control, false success, dead compatibility paths, test-only seams, and complexity without contribution. Use for whole-repository agent audits, slop or dead-code triage, test contribution reviews, large refactors, tool/context simplification, and cleanup requests that need proof before deleting code or tests.
The English summary is being prepared. Showing the original description.
Use when a diff needs a readability review — naming, single-responsibility, DRY, dead code, mismatch with codebase conventions — dispatched by /review-changes, /do-and-judge, /judge.
The English summary is being prepared. Showing the original description.
Route codebase-structure questions (who calls X, where used, change-impact) to an existing code-graph first: impact, tests-for, dead cheaper, never more precise; grep routine. Also 'call graph'.
The English summary is being prepared. Showing the original description.
Use when the user asks to verify a story or ticket implementation against its spec - per-AC verdicts, code reuse and design conformance, dead code, then adversarial maintainer verification. Requires the qa/review agent roles registered by scripts/install-codex.sh. Keywords: story QA, acceptance criteria, spec conformance, AC coverage, QA this branch, verify story.
The English summary is being prepared. Showing the original description.
Refactor code to remove dead code, useless comments, unused variables, and unused imports. Use when asked to declutter a class, clean up noisy code, remove cruft, or run `/refactor:declutter`.
The English summary is being prepared. Showing the original description.
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.
The English summary is being prepared. Showing the original description.
Review Solidity automated market makers, liquidity pools, and token swaps using security checklists and safer code examples. Check repeated calls during transfers, manipulated prices, share calculations, swap limits, and administrator permissions.
Analyze malware communication with command servers to understand periodic check-ins, message formats, encoded data, and backup destinations. Produces a structured analysis report and network detection rules based on captured traffic and malware code.
Review a development milestone using sprint reports, feature status, bugs, and risks. Summarize completion, quality, and delivery pace, then recommend whether to proceed, proceed with conditions, or stop, with scope choices and action items.
Read PDFs, Office files, web documents, and large text files to answer questions, summarize content, compare sources, or extract tables and key points. Use OCR, text recognition from images, when vision tools cannot read document text.
Provides a reference for reviewing DeFi smart contracts, programs that manage blockchain transactions. It organizes vulnerability types with causes, code examples, search patterns, and fixes to help investigate accounting, permissions, boundary conditions, and pricing logic.
Turn meeting transcripts, rough notes, or long meeting chats into structured notes with decisions, open questions, risks, and action items. Include task owners and deadlines, with an optional short summary for Slack or email.
Help an agent run terminal commands, follow long-running jobs, retrieve logs, and cancel work. It explains result fields, execution deadlines, retained output, and operating-system differences so the agent can interpret command outcomes and choose appropriate tools.
Create and manage tasks and task lists in 飞书. Assign people, set deadlines, find unfinished work, mark tasks complete or reopen them, and control list membership for collaboration within your access permissions.