调试
定位并修复问题，分析错误
go-documentation
cxuu
Guidelines for Go documentation including doc comments, package docs, godoc formatting, runnable examples, and signal boosting. Use when writing or reviewing documentation for Go packages, types, functions, or methods.
go-testing
cxuu
Go testing patterns from Google and Uber style guides including test naming, table-driven tests, subtests, parallel tests, test helpers, test doubles, and assertions. Use when writing or reviewing Go test code, creating test helpers, or setting up table-driven tests.
go-naming
cxuu
Go naming conventions for packages, functions, methods, variables, constants, and receivers from Google and Uber style guides. Use when naming any identifier in Go code—choosing names for types, functions, methods, variables, constants, or packages—to ensure clarity, consistency, and idiomatic style.
go-context
cxuu
Go context.Context usage patterns including parameter placement, avoiding struct embedding, and proper propagation. Use when working with context.Context in Go code for cancellation, deadlines, and request-scoped values.
go-control-flow
cxuu
Go control flow idioms from Effective Go. Covers if with initialization, omitting else for early returns, for loop forms, range, switch without fallthrough, type switch, and blank identifier patterns. Use when writing conditionals, loops, or switch statements in Go.
go-code-review
cxuu
Quick-reference checklist for Go code review based on the Go Wiki CodeReviewComments. Maps to detailed skills for comprehensive guidance. Use when reviewing Go code or checking code against community style standards.
behavioral-testing
caidanw
Behavioral testing methodology — test what users experience, not how code is structured. Use when writing tests, reviewing test quality, planning test strategy for new features, or when existing tests are brittle/verbose/coupled to implementation details. Triggers: writing tests, TDD, test review, "tests keep breaking", "too many mocks", "tests are verbose", test coverage planning, behavior-driven development.
karpathy-guidelines
caidanw
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
business-model-auditor
shipshitdev
Use this skill when users need to stress test their business model, identify scale limitations, find bottlenecks, determine if they're trading time for money, or evaluate unit economics. Activates for "can this scale," "what breaks at 10x," or business model viability questions.
Skill: agent-harness
strikersam
scope-guard — prevent the harness from drifting out of scope
dispatching-parallel-agents
derKlinke
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
code-quality
wutongci
自动检查代码质量问题，提供改进建议
code-reviewer
smestern
Reviews scientific analysis scripts for correctness, reproducibility, error handling, code quality, performance, and scientific best practices — provides severity-rated actionable feedback without modifying code.
writing-typescript
alexei-led
Idiomatic TypeScript development. Use when writing TypeScript code, Node.js services, React apps, or discussing TS patterns. Emphasizes strict typing, composition, and modern tooling (bun/vite).
intent
saadshahd
Turn rough ideas into iron-clad work orders. Use when request is vague like "add a button", "make it better", "fix the thing". Triggers on ambiguous or underspecified requests.
ask-cloudflare-to-claude-fix
OpenSourceAGI
Guide to cloudflare-to-claude-fix (packages/cloudflare-to-claude-fix), the Cloudflare Queue consumer that fires a Claude Code routine when a Workers build fails — creating the queue and DLQ, enabling build Event Subscriptions, the routine /fire API and its beta header, the ROUTINE_FIRE_URL / ROUTINE_FIRE_TOKEN / NOTIFY_WEBHOOK_URL secrets, retries, and local testing. Use when working with this Worker or troubleshooting it — routines that never fire, 400/401/403/404/429 from the fire endpoint, messages piling up in the dead-letter queue, or build events that never reach the consumer.
ask-open-ready
OpenSourceAGI
Guide to open-ready (packages/open-when-ready), the dev-server wrapper that opens the browser when the server is ready and an AI assistant when it errors — wrapping any CLI command, the --ai-base / --noAi / --noOpen / --pollDelay flags, how ready and error signals are detected, and where the log file goes. Use when working with open-ready or troubleshooting it — the browser never opening, opening too early or at the wrong port, an AI tab opening on a harmless log line, or flags being swallowed by the wrapped command.
defense-in-depth
ed3dai
Use when invalid data causes failures deep in execution - validates at every layer data passes through to make bugs structurally impossible rather than temporarily fixed
systematic-debugging
ed3dai
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
test-driven-development
ed3dai
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
requesting-code-review
ed3dai
Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches code-reviewer subagent, handles retries and timeouts, manages review-fix loop until zero issues
transcript
geekatron
Parse, extract, and format transcripts (VTT, SRT, plain text) into structured Markdown packets with action items, decisions, questions, and topics. v2.0 uses hybrid Python+LLM architecture for VTT files. Integrates with ps-critic for quality review.
ux-ai-first-design
geekatron
"AI-first interaction design sub-skill (CONDITIONAL) for the /user-experience parent skill. Provides trust-calibrated AI interaction design guidance using Yang et al.'s trust-risk and error-risk classification framework. Produces interaction pattern recommendations, trust calibration assessments, feedback loop designs, and progressive disclosure strategies for AI-powered features. CONDITIONAL: requires WSM >= 7.80 AND enabler research (FEAT-020) complete; otherwise routes to /ux-heuristic-eval with PAIR protocol. Invoke when teams need to design AI-powered interactions, calibrate user trust in AI outputs, classify AI error risks, design human-AI handoff patterns, or audit existing AI interfaces for trust and safety. Triggers: AI-first design, AI interaction, trust calibration, AI UX, conversational UX, AI interface, LLM interface, agentic UX, human-AI interaction, AI transparency, AI error handling, AI onboarding, progressive AI disclosure, trust-risk, error-risk."
c-lang
htlin222
Write efficient C code with proper memory management and system calls. Use for C optimization, memory issues, or system programming.