Debugging
Find and fix bugs, error analysis
defense-in-depth
by timequity
Use when invalid data causes failures deep in execution - validates at every layer data passes through to make bugs structurally impossible
iterative-code-evolution
by aaronjmars
Systematically improve code through structured analysis-mutation-evaluation loops. Adapted from ALMA (Automated meta-Learning of Memory designs for Agentic systems). Use when iterating on code quality, optimizing implementations, debugging persistent issues, or evolving a design through multiple improvement cycles. Replaces ad-hoc "try and fix" with disciplined reflection, variant tracking, and principled selection of what to change next.
systematic-debugging
by timequity
Use when encountering any bug, test failure, or unexpected behavior - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
roast-yc-application
by DominikScholz
Brutally honest YC application reviewer. Rates your Y Combinator application (0-100%) against proven best practices, highlights strengths, and identifies exactly what needs improvement to maximize your interview chances.
coding-guidelines-verify
by Nymbo
"Verify changes follow nearest-scoped AGENTS.md rules: group changed files by nested scope, auto-fix formatting, run lint/tests, and report violations."
Write Test Plan
by yebot
Create comprehensive test plans for features and changes
interviewing-plans
by galihcitta
Use when a plan, PRD, or spec has vague requirements, undefined terms, or missing details - conducts structured interview using AskUserQuestion to surface hidden assumptions, challenge ambiguities, and produce implementation-ready specs. Also use proactively when encountering plans that say things like "make it faster" or "improve UX" without concrete definitions.
backend-rust
by timequity
Modern Rust backend with Axum, SQLx, tokio + CI/CD automation. Use when: building Rust APIs, high-performance services, or needing build/test/lint/audit automation. Triggers: "axum", "rust backend", "rust api", "sqlx", "tokio", "cargo build", "cargo test", "clippy", "rustfmt", "cargo-audit", "cross-compile", "rust ci", "release build", "rust security", "shuttle", "actix".
dev.lint
by kevinslin
lint project
lua-basics
by germanfndez
Effective Lua programming for FiveM - functions, tables, variables, conditionals, error handling. Use when writing or reviewing Lua code for FiveM resources.
module-discovery
by taptap
排查问题、修复 BUG、定位代码、查找模块、功能开发前，必须先读取此 SKILL 并使用模块索引定位目标，不可跳过
mcp-developer
by trotsky1997
Comprehensive guide for developing Model Context Protocol (MCP) servers. Use when (1) Creating new MCP servers, (2) Implementing MCP tools and handlers, (3) Testing MCP servers, (4) Debugging MCP communication issues, (5) Setting up stdio-based MCP servers, (6) Setting up SSE (Server-Sent Events) based MCP servers, (7) Handling MCP errors and exceptions, (8) Structuring MCP server code, or any MCP development tasks.
jane-street-functional-trading
by copyleftdev
Build trading systems in the style of Jane Street, the elite market maker known for functional programming and intellectual rigor. Emphasizes OCaml, correctness by construction, real-time systems, and principled risk management. Use when building market making systems, pricing engines, or mission-critical financial software.
troubleshooting-kubernetes
by galihcitta
Diagnoses and fixes Kubernetes issues with interactive remediation. Use when pods crash (CrashLoopBackOff, OOMKilled), services unreachable (502/503, empty endpoints), deployments stuck (ImagePullBackOff, pending). Also use when tempted to run kubectl fix commands directly without presenting options, or when user says "just fix it" for K8s issues.
dev.code
by kevinslin
This skill should be used when performing any coding task including implementing features, fixing bugs, refactoring code, or making any modifications to source code. Provides best practices, security considerations, testing guidelines, and a structured workflow for development tasks.
effective-tasks
by yebot
Best practices for writing SIMBL tasks that Claude can execute with zero context. Use when creating or refining tasks for maximum clarity.
toss-patterns
by Tempuss
Use when planning market strategy, learning from Toss's 7 success patterns (Pain Point, Trojan Horse, Friction Removal, Viral Loop, Data-Driven, Ecosystem, Regulation).
code-review-assistant
by iceleaf916
代码审核辅助工具，支持本地 Git 库和 Gerrit Review。支持审核当前最新 commit、暂存的修改、未暂存的修改等，也支持 Golang、Qt/C++、Ansible 等多语言的 Gerrit Code Review。提供"必须修复/建议修复/可选改进"三级分级审核，生成 Markdown 报告。
GitHub Issue Templates
by yebot
Templates for creating well-structured GitHub issues for bugs, features, and tasks
ukrainianizer
by vitalii4reva
Видалення ознак AI-генерованого тексту з української мови. Використовуй для редагування або перевірки тексту, щоб він звучав природно по-українськи. Виявляє та виправляє: русизми, англіцизми, канцеляризми, плеоназми, AI-лексику, надмірне підкреслення значущості, промоційну мову, приховані Unicode watermarks, статистичні AI-патерни (низька perplexity, низька burstiness). Triggers: humanize Ukrainian text, зробити текст українським, прибрати AI, виправити суржик, редагувати українською, nature Ukrainian, remove AI patterns from Ukrainian, fix Russian calques, виправити русизми, канцелярит.
mcp-server-reviewing
by meriley
Audits MCP servers for security vulnerabilities, missing validation, error handling issues, and production readiness. Use when reviewing MCP PRs or auditing server quality.
user-story-writing
by spjoshis
Master writing effective user stories with INVEST principles, acceptance criteria, story slicing, and agile best practices for clear, testable requirements.
commit-message
by lucianghinda
Generate high-quality git commit messages following Conventional Commits and Chris Beams' Seven Rules. Infers WHY from context and provides clear guidance on structure, scope, and body content.
wfc-prompt-fixer
by sam-fakhreddine
Analyzes and rewrites existing Claude-specific prompts (system prompts, user-turn templates, or WFC Agent Skills) to fix structural issues and antipatterns. Pipeline: Analyzer grades A-F against 14 dimensions and 17 antipatterns → Fixer rewrites C-F prompts (preserving intent, output format, and constraints) → Reporter validates and summarizes. A/B prompts skip Fixer and receive diagnostic report only. Modes: Single file, --batch (up to 4 parallel, auto-scales for token budget), --auto-pr (requires gh CLI + write access), --wfc (explicit WFC mode). Trigger: /wfc-prompt-fixer, "fix this prompt", "rewrite this prompt", "debug prompt errors", "grade this prompt", "analyze prompt quality", "optimize for Claude 4" (applies only to Claude prompts).