Use when explaining code, concepts, or system behavior to a specific audience level - provides a structured explanation workflow with depth control and validation steps.
Turn Slack #code-fixes, CodeRabbit, Codex Review, CI, and check-status noise into a repo-and-PR action queue.
Trace code execution path before implementing fixes. Forces understanding of fn(args, deps) flows, Result types, and workflow composition.
Trace code execution paths and data flow. Use when user asks "how does X work", "what happens when X", "trace the flow of X", "where does data come from", or needs to understand…
Format code on the current branch using Biome. Use when asked to format, lint, or clean up code before committing or creating a PR.
Manage a code freeze with a scoped declaration, risk-classed changes, a fast exception process, and a planned thaw.
Context-efficient codebase navigation and documentation using structured frontmatter headers. Use this when exploring an unfamiliar codebase, answering "where is X / how does Y…
Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.
Context-aware routing to code generation workflows including SwiftGen, Sourcery, Feature Flags, and Protobuf.
针对 PR diff 输出结构化合规治理报告. 检查 license / PII / 合规元数据 / 审计 trail. 专为 EU AI Act / 中国网信办算法备案 / 金融医疗合规驱动客户设计.
Use when user wants to vendor a slice of a library into their project as inline source — copy only the code actually used, trim the rest, keep the ability to re-sync from upstream…
AST-based code graph for fast symbol lookup, dependency analysis, and blast radius via codebase-memory-mcp MCP server
Systematischer Code-Wächter für Scope-Verständnis, Deduplizierung, Architektur-Passung und Clean Code mit Unterstützung durch Knip, Ast-Grep und JSCPD
Detect hardcoded values, magic numbers, and leaked secrets. TRIGGERS - hardcode audit, magic numbers, PLR2004, secret scanning.
Harden code by improving type safety, runtime validation, logging, and error handling. Use when the user asks to harden, productionize, add validation, tighten types, or improve…
Assists with code quality tasks. Use when reviewing code, checking for issues, or improving code quality. NOT for: writing new features from scratch.
Final-pass code hygiene on Rust files in this repo. Applies vprogs's comment and small-scale code conventions (contract-first docs, semantic-block inline notes, no em-dashes, no…
Find where specific code lives in a large or unfamiliar codebase. Use whenever someone asks "where is X implemented?", "which file handles Y?", "find the code that does Z", "where…
Read an existing repository's structure into the project cwd as a normalised snapshot the agent can analyse without re-walking the tree on every turn.
Always-active code review skill. Whenever the user shares code — pasted, referenced by file path, or implied by a task — scan it for readability, performance, and best-practice…
Educational code development skill that teaches programming concepts while building applications. Use when the user wants to learn how code works, understand programming concepts,…
Check whether global code intelligence tools are installed and configured consistently.
Dual-perspective code investigation. Claude explores independently, then Codex explores independently (no feeding), finally integrate both conclusions.
Efficient codebase investigation for rapid-go. Use when understanding existing code before modifications, tracing request flows from API to database, finding where functi — from…
Efficient codebase investigation for rapid-go. Use when understanding existing code before modifications, tracing request flows from API to database, finding where functi — from…
Analyzes failed sessions with code-level root causes and files scoped GitHub issues.
Codebase'i knowledge graph olarak analiz et. Dependency, call graph, hotspot analizi.
Where things go inside a function body: define each binding next to its first use, and inline single-use values unless naming one earns its keep.
Evaluate code layout quality based on accuracy, consistency, readability, and maintainability rather than aesthetics.
既存のプロジェクトやコードベースを解析して、学習用のMarkdownドキュメントを自動生成する。 以下のトリガーで自動発動: - 「このコードを教えて」「コードを解説して」「勉強したい」 - 「プロジェクトを理解したい」「アーキテクチャを学びたい」 - 「学習用のドキュメントを作って」「コードの説明ドキュメント」 - /code-learner コマンド
Given a behavior description, locate candidate code paths and line ranges in the active codebase that probably implement it.
소스코드의 기능별 엔트리포인트와 호출 흐름을 .ai/60_codebase/에 색인하고, 도메인·계약·ADR 문서와 교차 참조를 연결합니다. 코드맵, code map, 코드 지도, 코드베이스 색인 시 사용합니다.
Provides templates and analysis guidance for mapping codebases into specialized documentation. Used by the sdd:code-mapper agent to generate 8 focused codebase documents.
Write minimum necessary code following YAGNI principle to prevent bloat and over-engineering. Use when implementing features to keep the codebase lean and avoid premature…
Code mode operational spec for the team lead. Returns lead identity, facilitator identity, mode-specific rules, suggest-members guidance, and phase arc for code-mode teams.
Filme de motion design escrito como PROGRAMA: o modelo escreve `seek(t)` (pinta o quadro exato de qualquer instante), um Chromium headless chama quadro a quadro e o ffmpeg costura…
Use when you need to understand the codebase structure, find definitions, or trace references without reading entire files.
Systematic framework for resurrecting and modernizing legacy codebases through archaeology, resurrection, and rejuvenation phases.
Systematic framework for resurrecting and modernizing legacy codebases through archaeology, resurrection, and rejuvenation phases.
Drafts a Code of Business Conduct and Ethics satisfying SEC, SOX §406, and exchange listing requirements.
Drafts a U.S. corporate Code of Business Conduct and Ethics with governance controls, enforcement mechanics, and implementation artifacts.
Apply a code of conduct consistently, with a reporting path, proportionate responses, and records, so it protects people rather than decorating the repository.
Verhaltenskodizes nach Art. 56 KI-VO und harmonisierte Normen nach Art. 40 KI-VO: Entwicklung Beteiligung Vermutungswirkung gemeinsame Spezifikationen Art. 41.
Otimizador automático de código usando análise evolutiva GEPA para melhorar qualidade, performance e manutenibilidade — from PAGIA Team
Otimizador automático de código usando análise evolutiva GEPA para melhorar qualidade, performance e manutenibilidade — from majiayu000/claude-skill-registry
Enforce code organization principles - "Directory X contains ONLY class type X", DDD naming patterns, PHP best practices, type safety, and SOLID principles.
Identify who owns, maintains, or has expertise in a specific code area — use when asked who to talk to about a system, who to request a code review from, or who has been actively…
Scan your codebase for distinctive patterns — get structured scoring and evidence for patent consultation. NOT legal advice.
Use when mapping code paths, entrypoints, and likely hot files before profiling. — from general/general-misc
Internal logic and data flow philosophy (The 5 Laws of Elegant Defense). Understand deeply to ensure code guides data naturally and prevents errors.
Use when future codebase work needs a plan before implementation: split requirements into scoped executable tasks with owners, dependencies, validation gates, reject criteria, and…
代码搬运师技能：优先搬运优秀开源项目，禁止重复造轮子。 Use when: 需要实现新功能、选择技术方案、评估是否自己实现。 Triggers: "实现", "开发", "创建", "构建", "写一个", "做一个"
Use AFTER verifying-spec passes and BEFORE generating-html during the initial-creation iteration loop of -implementation-plan.md ONLY.
Guide design decisions using the State > Coupling > Complexity > Code priority framework. Use when evaluating tradeoffs, reviewing design choices, deciding between…
Analyze Claude Code session logs to improve prompt quality, optimize tool usage, and become a better AI-native engineer.
Analyze your Claude Code session logs to improve prompt quality, optimize tool usage, and become a better AI-native engineer.
Manage GitHub pull requests or GitLab merge requests: create, read/leave/respond to comments, and merge.
Assess code maintainability through 5 foundational qualities (cohesion, coupling, encapsulation, testability, non-redundancy) with quantifiable scoring rubrics.
Code quality inspection and linting commands for web audio apps. Includes detection of dead code, magic numbers, type safety issues, and naming inconsistencies.
Expert on code quality audit — cyclomatic complexity, SOLID principles, DRY, method/class size, nesting depth, magic numbers, dead code, naming quality, performance smells, and…