代码评审
自动化代码审查与分析
code-review-excellence
wshobson
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
high-dynamic-video-choreographer
amao2001
Analyzes a theme or image to design a sequence of 5 high-energy, logically connected action beats for AI video generation. Features a recursive optimization process to ensure physical momentum and visual diversity.
pdf-processing-openai
lawvable
"Toolkit for comprehensive PDF reading, reviwing, and creation with visual quality control. Use to work with PDFs (.pdf files) for: (1) Reading or extracting content from existing PDFs, (2) Creating new PDF documents with professional formatting, (3) Generating reports, documents, or layouts that require precise typography and design, or any other PDF reading or generation tasks."
backlog-technical-project-manager
MrLesk
Technical project management for Backlog.md workstreams using coordinated sub-agents. Use only when the user explicitly asks Codex to take over one or more existing Backlog.md tasks (for example: "act as TPM", "coordinate these tasks", "delegate to sub-agents"). Orchestrate planning, implementation, and finalization; manage dependencies and overlapping code areas; review and approve sub-agent plans before implementation.
context-hunter
MrLesk
MUST run before any code implementation task. Classifies complexity, discovers local conventions, finds reusable patterns, and prevents blind coding. Invoke this skill before writing or modifying code.
investigate
TokenRollAI
"Use when user asks 'what is X', 'how does X work', 'find out about', 'analyze', 'explain the code', or needs quick codebase investigation. Returns findings directly in conversation without saving files. Prefer this over Explore agent."
commit
TokenRollAI
"Use when user says 'commit', 'save changes', 'wrap up', 'done with changes', or wants to create a git commit. Analyzes staged/unstaged changes and generates conventional commit messages based on project history."
ticktick
NeverSight
Manage TickTick tasks and projects for JMO. Use when the user asks to add, create, or capture a task or todo; list, show, or review pending tasks; complete or check off a task; update a task's priority, due date, notes, or tags; delete a task or list; create or manage a project/list; or see what's due today or overdue. Also handles quick captures like "remind me to..." or "don't let me forget...".
remotion
NeverSight
Use when generating or modifying Remotion video code, creating demo videos, or working with the demo-video/ directory
address-pr-comments
elie222
Resolve active pull request comments and prepare replies
polish
elie222
Remove lint and low-risk code quality issues from current branch changes
pr-loop
elie222
Review, commit, create PR, then auto-address review comments in a loop.
review
elie222
Review code changes, auto-fix safe issues, and report bugs
create-pr
elie222
Commit changes and open a pull request with safe metadata
web-design-guidelines
openstatusHQ
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
seo-audit
openstatusHQ
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," or "SEO health check." For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup.
hugging-face-evaluation
huggingface
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
bundle-barrel-imports
TheOrcDev
Import directly from source files instead of barrel files. Apply when using libraries like lucide-react, @mui/material, or @radix-ui/react-* to reduce bundle size and improve dev boot time.
js-set-map-lookups
TheOrcDev
Use Set and Map for O(1) membership lookups instead of array.includes(). Apply when checking membership repeatedly or performing frequent lookups against a collection.
nemo-guardrails
Orchestra-Research
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
pr-writer
getsentry
ALWAYS use this skill when creating or updating pull requests — never create or edit a PR directly without it. Follows Sentry conventions for PR titles, descriptions, and issue references. Trigger on any create PR, open PR, submit PR, make PR, update PR title, update PR description, edit PR, push and create PR, prepare changes for review task, or request for a PR writer.
code-simplifier
getsentry
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify code", "clean up code", "refactor for clarity", "improve readability", or review recently modified code for elegance. Focuses on project-specific best practices.
claude-settings-audit
getsentry
Analyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only bash commands to allow. Detects tech stack, build tools, and monorepo structure.
find-bugs
getsentry
Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.