Debugging
Find and fix bugs, error analysis
commit
by Donngi
コミット規約に沿ったコミットを作成する（変更の分類・分割も自動判断）。ユーザーが「コミットして」「変更をコミット」「/commit」などと言った場合に使用。Conventional Commitsを基本とした規約に従い、適切なtype/scope/subjectを自動生成。複数の論理単位に分割すべき変更は自動判断して複数コミットに分割する。
issue-fixer
by cyberelf
This skill provides a systematic approach for investigating and fixing bugs and issues in the codebase. Use this skill when users report bugs, unexpected behavior, test failures, or request fixes for specific issues. The skill guides through issue registration, root cause analysis, impact assessment, minimal code changes, quality validation, and E2E testing.
semantic-commit
by buildrtech
Create semantic git commits following Conventional Commits specification. Use when committing changes, making commits, or when asked to commit.
debug-session
by manastalukdar
Document debugging sessions with hypothesis tracking and knowledge base
web-auto-form
by DUZ1287
JSON 驱动的浏览器表单自动化工具，为 AI Agent 提供原生 function-calling 集成，支持表单填写、条件分支、数据提取与 PII 脱敏
zod
by thecarlo
A Zod v4 validation specialist.
dispatching-parallel-agents
by buildrtech
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
@tank/tank-package-publisher
by tankpkg
Package lifecycle specialist for Tank directory publishing. Use when users ask to publish a skill to Tank, run tank publish, fix publish failures, validate skills.json, bump versions, or verify releases. Handles dry-run-first workflow, manifest validation, and publish error remediation.
test-driven-development
by buildrtech
Use when implementing any feature or bugfix, before writing implementation code
code-reviewer
by 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.
interhuman-stream
by InterhumanAI
Wrapper for Interhuman API WebSocket /v0/stream/analyze endpoint. Analyzes live video streams in real-time and relays raw JSON messages as received. Use when the user wants to analyze live camera input or continuous video streams (not pre-recorded files). Returns all WebSocket messages exactly as received from the API without modification.
accessibility
by manastalukdar
Accessibility (a11y) compliance checking with WCAG 2.1 validation
decontextualize
by corygabrielsen
Course-correct when artifacts overfit to conversation context. Invoke when examples, names, or language are too specific to current work.
brainstorm
by corygabrielsen
Generate N diverse solutions to a problem. Forced breadth reveals the full landscape — the best option surfaces through comparison, not intuition.
youtube-transcript
by range3
Fetch subtitles/transcripts from YouTube videos and use them as context for summarization, analysis, translation, or Q&A. Use this skill whenever a user shares a YouTube URL and asks to summarize, explain, or discuss the video content, or when they explicitly ask for subtitles or a transcript. Trigger on any youtube.com, youtu.be, or YouTube Shorts link that appears in conversation where understanding the video content is needed.
debug
by pascalamiet
Systematic debugging workflow for any language or environment. Use when: something is broken and you need a structured approach to find and fix it. Covers error reading, isolation, hypothesis testing, and common bug patterns.
behavioral-testing
by 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
by 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.
fix-imports
by manastalukdar
Repair broken imports automatically across the project
flutter-clean-arch
by duckyman-ai
Generate Flutter applications using Clean Architecture with feature-first structure, Riverpod state management, Dio + Retrofit for networking, and fpdart error handling. Use this skill when creating Flutter apps, implementing features with clean architecture patterns, setting up Riverpod providers, handling data with Either type for functional error handling, making HTTP requests with type-safe API clients, or structuring projects with domain/data/presentation layers. Triggers include "Flutter app", "clean architecture", "Riverpod", "feature-first", "state management", "API client", "Retrofit", "Dio", "REST API", or requests to build Flutter features with separation of concerns.
review-skill-parallel
by corygabrielsen
Review a skill document with n parallel reviewers. Synthesizes findings, addresses issues, verifies changes, gets human approvals (plan and confirmation).
run-iflow
by LostAbaddon
向助手发出协助请求，适用中华文化理解、中文古文理解、中国特色作品创作、小红书与抖音的宣发文案编写、编写测试用例、信息检索等任务场景，同时也是其他专家助手的强力替补与协助，可以作为大部分认为的备选候补方案。
fix-eslint
by otrebu
Automatically fix ESLint errors by modifying code to comply with linting rules. For small codebases (≤20 errors), fixes directly. For larger codebases (>20 errors), spawns parallel agents per directory for efficient processing. Never disables rules or adds ignore comments.
moai-alfred-feedback-templates
by AJBcoding
GitHub 이슈 라벨별 구조화된 템플릿. 버그, 기능 요청, 개선 사항, 리팩토링, 문서, 질문 등 각 이슈 타입에 맞는 한국어 템플릿 제공. /alfred:9-feedback에서 사용.