调试
定位并修复问题，分析错误
reverse
unitarylab
Reverse-mode statevector gradient and QGT computation for parameterized circuits using Qiskit Algorithms classes ReverseEstimatorGradient and ReverseQGT.
qdrift
unitarylab
QDrift randomized Hamiltonian simulation, approximating e^{-iHt} by stochastically sampling Pauli-term evolutions with probability proportional to coefficient magnitude.
superpowers-review
anthonylee991
Reviews changes for correctness, edge cases, style, security, and maintainability with severity levels (Blocker/Major/Minor/Nit). Use before finalizing changes.
superpowers-rest-automation
anthonylee991
Builds reliable automations that integrate with REST APIs: auth, pagination, retries, rate limits, idempotency, webhooks, data mapping, and safe error handling. Use when calling external APIs, syncing systems, or building ETL-style workflows.
superpowers-finish
anthonylee991
Finalizes work: runs verification, summarizes changes, notes follow-ups, and ensures repo hygiene. Use at the end of an implementation or debugging session.
superpowers-debug
anthonylee991
Systematic debugging: reproduce, isolate, form hypotheses, instrument, fix, and add regression tests. Use when troubleshooting errors, failing tests, or unexpected behavior.
fix-sentry-issues
brianlovin
Use Sentry MCP to discover, triage, and fix production issues with root-cause analysis. Use when asked to fix Sentry issues, triage production errors, investigate error spikes, or clean up Sentry noise. Requires Sentry MCP server. Triggers on "fix sentry", "triage errors", "production bugs", "sentry issues".
audit-deps
helderberto
Check dependencies for vulnerabilities. Use when user asks to "audit dependencies", "/audit-deps", "check for vulnerabilities", or wants to check dependency health.
caching-strategy
aj-geddes
Implement efficient caching strategies using Redis, Memcached, CDN, and cache invalidation patterns. Use when optimizing application performance, reducing database load, or improving response times.
lint
helderberto
Run linting and formatting checks. Use when user asks to "run linter", "/lint", "check linting", "fix lint errors", or requests code linting/formatting.
typescript-advanced-types
jasonraimondi
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.
visual-verify
edwinhu
"This skill should be used when the user asks to 'verify visual output', 'check how it looks', 'render and review', 'visual verify', 'check the slide', 'does this look right', or when any task produces rendered visual output (slides, charts, documents, UI). Starts a render-vision-fix loop using Gemini vision."
continuous-learning
edwinhu
"This skill should be used when the user asks to 'extract patterns from this session', 'save what we learned', 'create a skill from this workflow', 'learn from this conversation', 'capture reusable knowledge', or wants to turn session patterns into reusable skills."
frontend-react-doctor
jasonraimondi
Run after making React changes to catch issues early. Use when reviewing code, finishing a feature, or fixing bugs in a React project.
planning-review-prd
jasonraimondi
Review PRD plans as a principal software engineer. Analyzes task quality, missing edge cases, phase ordering, track coverage, and architectural gaps. Auto-fixes obvious issues (missing tdd/headed flags, key ordering, weak verbs) and asks clarifying questions for non-obvious concerns. Use when user says "review my plan", "review the PRD", "check my tasks", or wants feedback on plans/ output.
writing-revise
edwinhu
"This skill should be used when the user asks to 'revise writing', 'fix review issues', 'polish draft', 'apply review feedback', 'complete writing workflow', or after /writing-review produces REVIEW.md with issues to fix."
dev-debug
edwinhu
"This skill should be used when the user asks to 'debug', 'fix bug', 'investigate error', 'why is it broken', 'trace root cause', 'find the bug', or needs systematic debugging and course-correction with verification-driven methodology using ralph loops."
ds-fix
edwinhu
"This skill should be used when the user asks to 'fix analysis', 'wrong results', 'notebook error', 'reviewer feedback', 'data changed', 'debug notebook', or needs mid-analysis course-correction for wrong results, notebook errors, or data changes."
notebook-debug
edwinhu
This skill should be used when the user asks to "debug notebook", "inspect notebook outputs", "find notebook error", "read traceback from ipynb", "why did notebook fail", or needs to understand runtime errors in executed Jupyter notebooks from any source (marimo, jupytext, papermill).
docx-footnotes
edwinhu
"Repair DOCX footnote damage from Google Docs or Word Online round-trips, and convert hardcoded supra/infra note references to auto-updating NOTEREF field codes. Use this skill whenever a user's .docx footnotes are broken after editing in a cloud editor — common symptoms include missing footnote separator lines, stripped paragraph styles (pStyle), author bio custom marks (*, †, ‡) replaced with numbers, footnote numbering starting at the wrong number, or TOC separator paragraphs that inflate to fill a whole page. Also use this skill when the user wants to convert 'supra note N' cross-references to NOTEREF fields, fix footnote numbering offsets caused by customMarkFollows bio footnotes, or perform any OOXML-level footnote surgery on a Word document. Even if the user doesn't mention OOXML or XML directly — if they describe footnote formatting problems in a .docx that was edited in Google Docs or Word Online, this is the right skill."
marimo
edwinhu
This skill should be used when the user asks to "use marimo", "create a marimo notebook", "debug a marimo notebook", "inspect cells", "understand reactive execution", "fix marimo errors", "convert from jupyter to marimo", or works with marimo reactive Python notebooks.
dev-test-chrome
edwinhu
"This skill should be used when testing web applications with Chrome MCP tools, debugging console errors, monitoring network requests, executing JavaScript in browser, recording GIF test evidence, or when dev-test routes to Chrome-based browser testing."
dev-ralph-loop
edwinhu
"Per-task ralph loop pattern for implementation and debugging. One loop per task, not one loop per feature."
ccxt
2025Emma
CCXT cryptocurrency trading library. Use for cryptocurrency exchange APIs, trading, market data, order management, and crypto trading automation across 150+ exchanges. Supports JavaScript/Python/PHP.