Depuració
Detecció i correcció de problemes i anàlisi d’errors
thinking-model-router
tjboudreaux
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
okx-ai-support
nirholas
"Route users to OKX.AI customer support / Help Center. Use when the user wants to contact support, talk to a human, file a complaint, give feedback, report a system error or bug, or find the FAQ / help docs. Triggers: 'contact support', 'talk to a human', 'customer service', 'file a complaint', 'give feedback', 'help center', 'FAQ', 'user guide', 'system error', 'system bug', 'something is broken', 'find help docs', 'OKX AI support', 'OnchainOS support', 'human agent'."
gcp-triage
nirholas
Monitor three.ws production on Google Cloud Run and fix what the sweep finds. Use when the user asks to check production, diagnose an outage or error, "what's wrong with three.ws", read production logs, or run the monitoring loop. Broad questions get the deep sweep (healthz + all-service logs + version, TLS, fleet readiness, live pages, crons, DB migrations, wallets), then the fixes each class allows.
caveman
JuliusBrussee
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
git-workflow
bobmatnyc
Essential Git patterns for effective version control, eliminating redundant Git guidance per agent.
lyric-reviewer
bitwize-music-studio
Reviews lyrics against a quality checklist before Suno generation. Use before generating tracks to catch rhyme, prosody, pronunciation, and structural issues.
researchers-verifier
bitwize-music-studio
Performs quality control, citation validation, and fact-checking before human review. Use after research is complete to verify all sources and claims before production.
rename
bitwize-music-studio
Renames an album or track, updating slugs, titles, and all mirrored paths. Use when the user wants to rename an album or track.
import-track
bitwize-music-studio
Moves track markdown files to the correct album location. Use when the user has track files in Downloads or other locations that need to be placed in an album.
test
bitwize-music-studio
Runs automated tests to validate plugin integrity across 14 categories. Use before creating PRs, after making changes to skills or templates, or to verify plugin health.
add-node-sdk
gotempsh
Integrate the Temps Node.js SDK for server-side analytics, KV storage, blob storage, and platform management. Use when the user wants to: (1) Track server-side events, (2) Use Temps KV (key-value) storage, (3) Use Temps Blob storage for files, (4) Access Temps API from Node.js, (5) Server-side analytics integration, (6) Backend event tracking. Triggers: "temps node sdk", "server-side analytics", "temps kv", "temps blob", "backend integration", "node.js temps".
git-batch-commit
cat-xierluo
智能 Git 批量提交工具。当用户说 "git 提交"、"git commit"、"批量提交"、"拆分提交"、"整理提交" 时使用，或者当用户暂存了多个不同类型的文件需要分开提交时使用。自动将混合的文件修改按类型分类（依赖管理、文档更新、license 文件、配置、源代码等），并创建多个清晰聚焦的提交，使用标准化的提交信息格式。帮助保持清晰的 Git 历史，确保每个提交都有单一、明确的目的。使用英文前缀（docs:、feat:、fix: 等）加中文内容，支持 GitHub 彩色标签显示。
tdd
ccusage
Guides t-wada Red-Green-Refactor TDD for ccusage logic changes. Use when implementing a feature, writing a regression test for a bug, or refactoring Rust or TypeScript behavior test-first.
nnsight-remote-interpretability
Orchestra-Research
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
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.
commit
getsentry
ALWAYS use this skill when committing code changes — never commit directly without it. Creates commits following Sentry conventions with proper conventional commit format and issue references. Trigger on any commit, git commit, save changes, or commit message task.
iterate-pr
getsentry
Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.
blog-writing-guide
getsentry
Write, review, and improve blog posts for the Sentry engineering blog following Sentry's specific writing standards, voice, and quality bar. Use this skill whenever someone asks to write a blog post, draft a technical article, review blog content, improve a draft, write a product announcement, create an engineering deep-dive, or produce any written content destined for the Sentry blog or developer audience. Also trigger when the user mentions "blog post," "blog draft," "write-up," "announcement post," "engineering post," "deep dive," "postmortem," or asks for help with technical writing for Sentry. Even if the user just says "help me write about [feature/topic]" — if it sounds like it could become a Sentry blog post, use this skill.
brand-guidelines
getsentry
Write copy following Sentry brand guidelines. Use when writing UI text, error messages, empty states, onboarding flows, 404 pages, documentation, marketing copy, or any user-facing content. Covers both Plain Speech (default) and Sentry Voice tones.
qa
BuilderIO
Autonomous multi-app QA sweep that drives template apps with Playwright MCP. Use only when the user explicitly runs /qa or asks for an end-to-end QA sweep. Do not load it for ordinary feature work, single-page checks, or one-off bug fixes.
unblock
unblocked
Structures coding tasks around Unblocked MCP context. Hydrates a plan with organizational knowledge (PRs, Slack, Jira, docs, code history), submits it for critical review against team patterns, then generates and reviews code. Two mandatory review gates prevent pattern mismatches and reinvented wheels. Use for any code change: features, bug fixes, refactors, or investigations.
supabase-sdk-patterns
CoWork-OS
Execute apply production-ready Supabase SDK patterns for TypeScript and Python. Use when implementing Supabase integrations, refactoring SDK usage, or establishing team coding standards for Supabase. Trigger with phrases like "supabase SDK patterns", "supabase best practices", "supabase code patterns", "idiomatic supabase".
golang-http-frameworks
bobmatnyc
"Go HTTP API development with net/http, Chi, Gin, Echo, and Fiber frameworks"
fix-chinese
brycewang-stanford
PROACTIVE SKILL — automatically apply whenever writing, generating, or editing any text that is mainly in Chinese. No user trigger needed. Also use when the user explicitly asks to "fix Chinese", "修改中文", "去翻译腔", "去AI味", "fix Chinese formatting", or "review Chinese text". Eliminates AI-sounding expressions and translation artifacts. Enforces Chinese-English mixed formatting rules (spacing, punctuation, bold formatting).