调试
定位并修复问题，分析错误
ask
bfly123
Async via ask, end turn immediately; use when user explicitly delegates to any AI provider (gemini/codex/opencode/droid); NOT for questions about the providers themselves.
receiving-code-review
srbhr
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
reviewing-changes
bitwarden
Guides Android code reviews with type-specific checklists and MVVM/Compose pattern validation. Use when reviewing Android PRs, pull requests, diffs, or local changes involving Kotlin, ViewModel, Composable, Repository, or Gradle files. Triggered by "review PR", "review changes", "check this code", "Android review", or code review requests mentioning bitwarden/android. Loads specialized checklists for feature additions, bug fixes, UI refinements, refactoring, dependency updates, and infrastructure changes.
nodejs-backend-patterns
HermeticOrmus
Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices. Use when creating Node.js servers, REST APIs, GraphQL backends, or microservices architectures.
zig-best-practices
aiskillstore
Provides Zig patterns for type-first development with tagged unions, explicit error sets, comptime validation, and memory management. Must use when reading or writing Zig files.
typescript-advanced-types
HermeticOrmus
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.
dyad:deflake-e2e
dyad-sh
Identify and fix flaky E2E tests by running them repeatedly and investigating failures.
m12-lifecycle
actionbook
"Use when designing resource lifecycles. Keywords: RAII, Drop, resource lifecycle, connection pool, lazy initialization, connection pool design, resource cleanup patterns, cleanup, scope, OnceCell, Lazy, once_cell, OnceLock, transaction, session management, when is Drop called, cleanup on error, guard pattern, scope guard, 资源生命周期, 连接池, 惰性初始化, 资源清理, RAII 模式"
domain-fintech
actionbook
"Use when building fintech apps. Keywords: fintech, trading, decimal, currency, financial, money, transaction, ledger, payment, exchange rate, precision, rounding, accounting, 金融, 交易系统, 货币, 支付"
Bun HTTP Server
secondsky
Use when building HTTP servers with Bun.serve, handling requests/responses, implementing routing, creating REST APIs, or configuring fetch handlers.
retrospective
blacklanternsecurity
Post-engagement lessons-learned retrospective. Reads the engagement directory, analyzes skill routing decisions, identifies knowledge gaps and missing skills, and produces an actionable improvement report.
ecto-thinking
georgeguimaraes
This skill should be used when the user asks to "add a database table", "create a new context", "query the database", "add a field to a schema", "validate form input", "fix N+1 queries", "preload this association", "separate these concerns", or mentions Repo, changesets, migrations, Ecto.Multi, has_many, belongs_to, transactions, query composition, or how contexts should talk to each other.
report-issue
codemie-ai
This skill should be used when the user wants to report a bug, file an issue, or suggest a feature for the CodeMie Code CLI tool (codemie-ai/codemie-code repository on GitHub). Trigger phrases include: "report a bug", "open an issue", "submit an issue", "file a bug report", "something is broken in CodeMie", "report to GitHub", "create a GitHub issue", "suggest a feature for CodeMie", "request an enhancement", "I have a feature idea", "codemie is not working", or any mention of filing a report for CodeMie. This skill automatically collects diagnostic context (OS, Node.js, CLI version, installed agents, active profile, codemie doctor output, recent debug logs) and creates a structured GitHub issue via gh issue create with a user-confirmed preview step before submission.
use-of-color
AccessLint
Analyzes code for WCAG 1.4.1 Use of Color compliance. Identifies where color is used as the only means of conveying information and recommends additional visual indicators like text, icons, patterns, or ARIA attributes.
Review Response Writer
rshankras
yourapp.com/help
quality-gate-pipeline
bdfinst
Unified quality gate for agent output — self-validation, verification evidence, and review-correction loops. Consolidates accuracy-validation, verification-before-completion, and task-review-correction into a single three-phase pipeline. Use before delivery, at completion, and during rework.
triage
bdfinst
Investigate a bug, find its root cause, and write a portable triage record to .dev-team-reports/triage/<slug>.md with a TDD fix plan. Use when the user reports a bug and wants it triaged, says "triage this", "investigate and write it up", or wants a hands-off bug investigation that produces an actionable record.
domain-iot
actionbook
"Use when building IoT apps. Keywords: IoT, Internet of Things, sensor, MQTT, device, edge computing, telemetry, actuator, smart home, gateway, protocol, 物联网, 传感器, 边缘计算, 智能家居"
ci-debugging
bdfinst
Systematic CI/CD failure diagnosis with hypothesis-first approach, environment delta analysis, and anti-patterns. Use when CI fails, pipelines break, or the user says "CI is failing", "build broke", "pipeline error", or "tests pass locally but fail in CI".
systematic-debugging
bdfinst
Four-phase debugging protocol (reproduce, investigate, root-cause, fix) that prevents guess-and-fix thrashing. Use this skill whenever a test fails, a bug is reported, an error occurs during implementation, or any unexpected behavior is encountered. Prevents the common LLM failure mode of guessing at fixes without understanding the problem.
test-driven-development
bdfinst
Advisory reference for the Classic RED-GREEN-REFACTOR TDD discipline with hard gates — not a build cadence toggle. The plugin's single build cadence is Code-First Small Batches (docs/experiments/RECOMMENDATIONS.md Rec 3); /build does not dispatch into this skill. Use on explicit user request when someone wants test-first discipline for the code being written, or when reviewing code to verify TDD discipline was followed by hand.
adventure
SimHacker
Room-based exploration with narrative evidence collection
create-pr
n8n-io
Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.
knip
knoopx
Finds unused dependencies, files, and exports in JS/TS projects. Use when cleaning up dead code, removing stale packages from package.json, or identifying unreferenced exports.