Debugging
Find and fix bugs, error analysis
kotlin-deep-logic-coroutines
by Envy-7z
Deep Kotlin logic workflow for use-cases, repositories, ViewModels, Flow/coroutine orchestration, and compact architecture-safe refactors. Use when implementing non-trivial business rules, fixing coroutine race/cancellation issues, reducing logic complexity, or enforcing clean layered boundaries in Android Kotlin code.
wandb-projects
by vivek100
Resolve and validate Weights & Biases project context before automation. Use when a coding agent needs the correct W&B entity/project values, needs to verify project existence, or needs to avoid logging to the wrong workspace.
unity-debug-quick
by cuozg
Interactively diagnose Unity bugs — parse symptom, investigate, propose 2+ solutions, user picks, fix, loop until resolved. Triggers — 'debug this', 'why is this broken', 'fix this bug', 'something is wrong', 'not working'.
pr-review-handler
by vijaykpatel
Handle PR review feedback by checking for comments, determining necessary changes, responding appropriately to reviewers, implementing fixes, and pushing updates. Use when the user asks to work on an existing open PR, address PR feedback, fix review comments, or handle bot review suggestions (Devin AI, Cursor Bugbot, etc.).
native-data-fetching
by tonyma163
Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, axios, React Query, SWR, error handling, caching strategies, offline support.
shareful-mine
by shareful-ai
Mines past Claude Code conversations for the best shareable coding solutions using claude-code-search (ccs). Uses quality signals -- breakthrough markers, difficulty indicators, and community value scoring -- to surface high-recall content from conversation history. Use when the user wants to "mine conversations for shares", "populate my shares repo", "recall my best work", "find my best solved problems", or "solve the cold start problem".
authentication-patterns
by karchtho
JWT authentication, OAuth 2.0, session management, password hashing, refresh tokens, multi-factor authentication, API keys. Use when implementing user authentication, token management, authorization, password reset flows, or securing APIs.
first-principle-thinking
by campbellmcgregor
Expert methodology for breaking down complex problems into fundamental truths and rebuilding solutions from the ground up. Use when users need breakthrough innovation (not incremental improvement), question industry assumptions, face seemingly impossible problems, want to understand root causes, ask "why does this have to be this way", "rethink from scratch", "reimagine this", request analysis "from first principles", want to challenge conventional wisdom, question everything, or need to deconstruct problems to their core elements. Ideal for strategic decisions, innovation challenges, cost optimization, and escaping local optima.
web3-dapp
by kaos35
Web3 DApp development with Next.js, RainbowKit, wagmi, viem for multi-chain Ethereum applications with NFT, DeFi, and smart contract integration
repo-grounding
by janjaszczak
Ground answers in the repository by reading relevant files, configs, and code paths. Use when the user asks to modify/debug code, configuration, CI/CD, or wants repo-specific reasoning.
recur-portal
by recur-tw
Implement Customer Portal for subscription self-service. Use when building account pages, letting customers manage subscriptions, update payment methods, view billing history, or when user mentions "customer portal", "帳戶管理", "訂閱管理", "更新付款方式", "self-service".
cynic-wisdom
by zeyxx
"Philosophical grounding for technical decisions across 19 traditions. Cross-domain synthesis mapped to 5 axioms (FIDELITY/PHI/VERIFY/CULTURE/BURN). φ-bounded at 61.8%. Use when facing dilemmas, questioning assumptions, or seeking wisdom."
quality-workflow
by metyatech
Use when writing tests, designing test coverage, handling defect fixes, or performing root-cause analysis. Also use when creating test matrices or choosing between unit/integration/E2E tests. Do not use for general development, linting setup, or CI configuration.
async
by yusenthebot
Higher-order functions and common patterns for asynchronous code. Use when: common data transformations; reducing boilerplate code; functional programming helpers. NOT for: complex domain-specific business logic; replacing well-supported native APIs.
reality-verification
by DUTSTECH
Detect fix vs add goals, diagnose failures before work, verify fixes after. Ensures "fix X" specs actually fix X.
reviewing-code
by gajakannan
"Reviews code quality, architecture compliance, test adequacy, and acceptance criteria mapping. Activates when reviewing code, checking PRs, reviewing changes, assessing code cleanliness, or verifying acceptance criteria coverage. Does not handle security vulnerability scanning (security), writing production code (backend-developer or frontend-developer), or writing tests (quality-engineer)."
prompt-improver
by dotneet
A skill for improving prompts by applying general LLM/agent best practices. When the user provides a prompt, this skill outputs an improved version, identifies missing information, and provides specific improvement points. Use when the user asks to "improve this prompt", "review this prompt", or "make this prompt better".
health-data-collect
by maxoreric
æ¥æ°: 0 - 20000ï¼å»ºè®®ï¼â¥ 5000ï¼
git-create-branch
by pc-style
Create a new Git branch with proper naming conventions. Use when the user asks to create a branch, start a new feature branch, or switch to a new branch. Handles branch creation from current HEAD or from a specific base branch, with conventional naming (feature/, fix/, hotfix/, etc.).
6502-assembly
by hwatkins
Write, read, debug, and optimize 6502 assembly language code. Use this skill whenever the user asks about 6502 assembly, MOS 6502, 6510, 65C02, or 65C816 programming, or is working on projects for the NES, SNES, Commodore 64, Apple II, Atari 2600/8-bit, VIC-20, BBC Micro, or any other 6502-based platform. Also trigger when the user mentions opcodes, addressing modes, zero page, stack operations, or assembly language concepts in the context of 8-bit/retro computing. Covers instruction set, addressing modes, common algorithms (16-bit math, multiplication, division), memory layout, optimization, and platform-specific patterns. Even if the user just says "assembly" in a retro computing context, use this skill.
audit
by Nomik94
Use when: 프로젝트 규칙 검증, 커스텀 린트, 커밋 전 검사, audit, 규칙 위반 체크, 프로젝트 컨벤션 확인, 배포 전 검증. NOT for: 일반 린트 (ruff/mypy가 처리), 보안 감사 (security-audit 참조).
vague
by october-academy
This skill should be used when the user's request or requirement is ambiguous and needs iterative questioning to become actionable. Trigger on "clarify requirements", "refine requirements", "요구사항 명확히", "요구사항 정리", "make this clearer", "spec this out", "scope this", "/clarify". Turns vague inputs into concrete specs. For strategy blind spots use unknown; for content-vs-form reframing use metamedium.
create-subagent
by janjaszczak
Create custom subagents for specialized AI tasks. Use when the user wants to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.
securing-server-actions
by djankies
Teach server action authentication and security patterns in Next.js 16. Use when implementing server actions, form handlers, or mutations that need authentication.