调试
定位并修复问题，分析错误
receiving-code-review
alffei
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
traffic-analysis
chaterm
流量分析与抓包
trace-audit
joyco-studio
Analyze a Chrome DevTools Performance trace JSON file for performance anomalies, producing a structured audit report with critical issues, warnings, metrics, timeline hotspots, and actionable recommendations.
Skill: Android Gradle Build (tg-ws-proxy-android)
ComradeSwarog
OutOfMemory Increase org.gradle.jvmargs=-Xmx4096m in gradle.properties
dwarf-expert
lv416e
Provides expertise for analyzing DWARF debug files and understanding the DWARF debug format/standard (v3-v5). Triggers when understanding DWARF information, interacting with DWARF files, answering DWARF-related questions, or working with code that parses DWARF data.
ai-evals
oldwinter
"Create an AI Evals Pack (eval PRD, test set, rubric, judge plan, results + iteration loop). Use for LLM evaluation, benchmarks, rubrics, error analysis/open coding, and ship/no-ship quality gates for AI features."
code-simplify
PaulRBerg
This skill should be used when the user asks to "simplify code", "clean up code", "refactor for clarity", "reduce complexity", "improve readability", "make this easier to maintain", or asks to simplify recently modified code.
nexus-sdk-setup
availproject
Set up and initialize Nexus SDK in any JS/TS frontend project. Use when configuring wallet provider, SDK instance lifecycle, network selection, or adding a minimal wallet connection path.
payment-integration
mgd34msu
"Load PROACTIVELY when task involves payments, billing, or subscriptions. Use when user says \"add payments\", \"integrate Stripe\", \"set up subscriptions\", \"add a checkout flow\", or \"handle billing webhooks\". Covers Stripe, LemonSqueezy, and Paddle integration, checkout sessions, subscription lifecycle management, webhook verification and handling, customer portal, metered billing, refunds, and PCI compliance considerations."
nexus-sdk-hooks-events
availproject
Configure Nexus SDK intent/allowance/swap intent hooks and event streaming. Use when integrating approval flows, intent previews, or real-time progress events (NEXUS_EVENTS).
code-change-verification
EYH0602
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.
verification-before-completion
futuregerald
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
ai-evals
oldwinter
"Create an AI Evals Pack (eval PRD, test set, rubric, judge plan, results + iteration loop). Use for LLM evaluation, benchmarks, rubrics, error analysis/open coding, and ship/no-ship quality gates for AI features."
debugging
mgd34msu
"Load PROACTIVELY when task involves investigating errors, diagnosing failures, or tracing unexpected behavior. Use when user says \"debug this\", \"fix this error\", \"why is this failing\", \"trace this issue\", or \"it's not working\". Covers error message and stack trace analysis, runtime debugging, network request inspection, state debugging, performance profiling, type error diagnosis, build failure resolution, and root cause analysis with memory-informed pattern matching against past failures."
ai-following-rules
lebsral
Make your AI follow rules and policies. Use when your AI breaks format rules, violates content policies, ignores business constraints, outputs invalid JSON, exceeds length limits, includes forbidden content, or doesn't comply with your specifications. Covers DSPy Assert/Suggest for hard and soft rules, content policies, format enforcement, retry mechanics, and composing multiple constraints.
service-integration
mgd34msu
"Load PROACTIVELY when task involves connecting external services or third-party APIs. Use when user says \"add email sending\", \"integrate a CMS\", \"set up file uploads\", \"add analytics\", or \"connect to S3\". Covers email services (Resend, SendGrid), CMS platforms (Sanity, Contentful, Payload), file upload solutions (UploadThing, Cloudinary, S3), analytics integration, webhook handling, error recovery, and credential management."
embedding-ft
tiangong-lca
Execute and troubleshoot Supabase edge function embedding_ft that consumes PGMQ embedding jobs, calls AWS SageMaker embeddings, and writes vectors back to Postgres. Use when validating job payload handling, investigating failed embeddings, tuning ack semantics, or adjusting worker auth/environment.
receiving-code-review
futuregerald
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
refactoring
mgd34msu
"Load PROACTIVELY when task involves improving code structure without changing behavior. Use when user says \"refactor this\", \"clean up this code\", \"remove dead code\", \"reduce duplication\", \"reorganize the files\", or \"extract this into a function\". Covers extract function/component, rename symbol, simplify conditionals, improve type safety, dependency inversion, dead code removal, circular dependency resolution, and database query refactoring with automated safety validation (typecheck, tests) at each step."
write-tests
v1-io
Use when writing unit tests for code changes or new functionality. Triggers on "write tests", "add tests", "test this code".
command-parser
robertmsale
Summarize large CLI output via a temp workspace + codex exec to extract errors (and optional warnings) with file/line anchors.
commit
PaulRBerg
This skill should be used when the user asks to "commit changes", "craft a commit message", "stage and commit", "commit only session edits", or run a commit workflow with flags like --all, --deep, or --push. Creates atomic git commits with heuristic analysis, conventional-commit formatting, staging rules, optional deep analysis, and optional push.
dispatching-parallel-agents
futuregerald
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
debug
v1-io
Use when debugging errors, diagnosing failures, or tracing root causes from error output. Triggers on "debug this", "why is this failing", "trace the error".