context-recovery
>
linear
Manages Linear issues, teams, and projects via CLI. Lists issues, creates tasks, views details, links issues, and runs GraphQL queries. Must use for "my Linear issues", "create Linear task", "link issues in Linear", "Linear API query", or any Linear project management request.
agent-sop-creator
Guide for creating Agent SOPs (Standard Operating Procedures). Use this skill when the user wants to create a new SOP workflow for AI agents, write an agent procedure, or needs help with SOP format and best practices. Triggers on requests like "create an SOP", "new agent workflow", "help me write an SOP", "create a procedure for agents", or "SOP template".
data-gouv
Skill professionnel pour Claude Code permettant d'accéder, télécharger et analyser les données ouvertes françaises via data.gouv.fr. Inclut une librairie Python complète, des exemples de code, et une documentation détaillée des datasets les plus utilisés.
backend-dev
后端开发专家，负责 Express.js + Knex.js + MySQL 8 + Redis 后端服务开发。遵循 OpenAPI 先行、TDD 推动、RBAC 安全、可观测性工程基线。处理 Provider 动态加载、缓存系统、数据库设计、内容管理 API 开发。适用于收到 Backend 部门任务卡（如 CMS-B-001）或修复类任务卡时使用。
billing-guard
计费审计专家,在规划/开发/运行阶段持续审计与优化成本。评估任务卡预算、模拟调用成本、监控高成本路径,在超出预算或异常时阻断执行并提出替代方案。遵循数据驱动、三板斧优化(缓存/批量/降级)、预警阻断的工程基线。适用于规划预审、PR成本审查、运行时监控时使用。
qa-acceptance
质量验收专家,从用户视角验证交付物可用性/正确性/性能/回归。遵循阻断不合格交付、脚本化验证、数据隔离、覆盖验收标准的工程基线。使用 Playwright(E2E)、Jest+Supertest(API)、k6(性能)等工具。适用于收到 QA 部门任务卡(如 CMS-Q-001)或需要验收交付物时使用。
frontend-dev
前端开发专家,负责 Next.js 14 App Router + React 18 + TypeScript + Ant Design + Zustand 前端应用开发。遵循契约驱动、统一UI规范、访问控制、可测试性工程基线。处理登录鉴权、动态表单、内容管理UI、E2E测试。适用于收到 Frontend 部门任务卡(如 CMS-F-001)或修复类任务卡时使用。
codebuddy-deploy
部署与运维专家,负责把通过 Reviewer 与 QA 门禁的构建安全、可回滚、可观测地部署到服务器(PM2 三进程 + Nginx 反代 + 宝塔)。遵循零停机部署、健康检查、回滚≤3分钟、发布后冒烟的工程基线。处理部署编排、配置管理、流量管理、监控告警。适用于收到 Deploy 部门任务卡或需要发布上线时使用。
reviewer
代码审查员,守护质量闸口。对所有部门(Backend/Frontend/SCF/Deploy)的 PR 进行安全、性能、正确性、可维护性、可观测性的系统性审查。遵循证据先行、问题分级、签发修复卡、独立克制的工程基线。适用于收到任一部门提交 PR 或需要质量把关时使用。
scf-worker
云函数工程师,负责腾讯云 SCF 无服务器函数开发。遵循最小权限、幂等、重试+死信、可观测性工程基线。处理 COS 直传签名、回调处理、媒体转码、Webhook 转发、批处理任务。适用于收到 SCF 部门任务卡(如 CMS-S-001)或修复类任务卡时使用。
product-planner
AI产品经理,整套"0基础 AI 协同开发系统"的源头角色与项目总导演。将自然语言需求转换为可执行的产品规划与标准化任务卡,协调 Backend/Frontend/SCF/QA/Reviewer/Deploy/Billing Guard 多部门有序并行交付。遵循易用性优先、契约优先、门禁治理、MVP-first 的工程基线。适用于收到自然语言需求时使用。
context_editing_guide
Managing context window, token optimization, summarization strategies for long conversations.
fintech-patterns
Common fintech customer patterns, objections, and success stories. Compliance handling, long conversation management, and case studies.
interview-records
Archive of past customer interviews. Contains full transcripts, summaries, pain points, outcomes, and skills used. Use for referencing previous conversations with the same company or finding similar case patterns.
pricing-guidance
Claude API pricing, tier recommendations, token cost optimization, and ROI calculations for CDP features.
memory-playbook
Cross-session persistence for user preferences, implementation guide for Memory feature.
cdp-skills
Claude Developer Platform Skills feature. Custom knowledge packages for agents, curated playbooks, and versioned expertise domains.
atl-cli
>
linear-skills
Lightweight Linear skill for fetching issue details. Returns only essential data (title, description, state, assignee) to optimize context usage compared to full Linear MCP.
go-db-query
Skills for querying Gene Ontology annotation databases in DuckDB format. Use this for queries about GO annotations, genes, terms, evidence codes, or taxonomic relationships in GO-DB databases (db/*.ddb files). Particularly useful for hierarchical queries using closure tables to find genes annotated to terms and their descendants.
rosetta-helix-substrate
Consciousness simulation framework with Kuramoto oscillators, APL operators, and K-formation dynamics. Use for physics simulations, phase transitions, coherence analysis, and cloud training via GitHub Actions. Requires numpy and requests packages.
unified-consciousness-framework
|
uv
Python package manager and project tooling using uv. Use when working with Python projects, managing dependencies, creating virtual environments, running Python scripts, configuring workspaces/monorepos, or troubleshooting uv issues. Triggers on pyproject.toml projects, uv commands, pip replacement workflows, Python version management, workspace configuration, or CI/CD Python setup.
aboutme-index
Index-based file discovery using ABOUTME headers. Use INSTEAD of grep or Explore agent when searching for files by purpose or feature. Faster and more accurate than scanning code. Invoke this skill when user asks "which files handle X", "where is Y implemented", or when you need to find files related to a feature or task.
workspace-blazor-mvvm
Guide for implementing LionFire workspace documents with Blazor MVVM patterns, including ObservableDataView component usage, workspace-scoped service injection, and reactive persistence. Use this skill when creating Blazor pages for workspace documents, fixing workspace service scoping issues, or implementing list/detail views with ObservableReader/Writer.
email-extractor
Expert in email content extraction and analysis. **Use whenever the user mentions .eml files, email messages, says "Extract email information", "Using the email information", or requests to extract, parse, analyze, or process email files.** Handles email thread parsing, attachment extraction, and converting emails to structured markdown format for AI processing. (project, gitignored)
Obsidian Add Content
Obsidian vault에 새로운 Frontend 지식 또는 Team Sparta 프로젝트를 템플릿 기반으로 추가합니다. 폴더 존재 여부를 확인하고 필요시 생성합니다.
Obsidian Refine Content
Obsidian vault의 기존 파일 내용을 분석하고, 사용자 확인 후 템플릿에 맞춰 정리/보완합니다. 틀린 부분은 수정하되 최종 문서에는 언급하지 않고 깔끔하게 완성합니다.
flask-docker-deployment
Set up Docker deployment for Flask applications with Gunicorn, automated versioning, and container registry publishing. Use when dockerizing a Flask app, containerizing for production, or setting up CI/CD with Docker.
aegis-nextjs-frontend
This skill should be used when the user asks to "create a new website", "spin up a frontend", "set up a Next.js site with aegis auth", "scaffold a new web app with authentication", "create a site with login and i18n", or needs a production-ready Next.js frontend integrated with ByteForge Aegis authentication. Provides complete project scaffolding with auth pages, internationalization, Docker deployment, and a design system.
python-project-scaffold
Scaffold a multi-repo Python workspace with models library, core library, Flask backend, and optional sub-projects. Creates directory structure and root CLAUDE.md describing each sub-project and which skills to use next. Use when starting a new Python project, setting up a multi-repo workspace, or scaffolding a project skeleton.
python-lib-setup
Set up Python project for PyPI publishing or private GitHub distribution with pyproject.toml, src layout, and optional build scripts. Use when creating a new Python package, setting up for PyPI distribution, initializing a Python library project, or setting up a private library distributed via GitHub.
postgres-setup
Set up PostgreSQL database with standardized schema.sql pattern. Use when starting a new project that needs PostgreSQL, setting up database schema, or creating setup scripts for postgres.
mcp-docker-deployment
Set up Docker deployment for Python MCP servers (FastMCP or low-level mcp.server.Server SDK) with SSE/streamable-http transport, automated versioning, and container registry publishing. Use when dockerizing an MCP server, containerizing for remote access, deploying an MCP server behind nginx, or setting up a production MCP server with Docker. Covers Dockerfile, build scripts, docker-compose, and nginx reverse proxy for SSE streaming.
flask-smorest-api
Set up Flask REST API with flask-smorest, OpenAPI docs, blueprint architecture, and dataclass models. Use when creating a new Flask API server, building REST endpoints, or setting up a production API.
byteforge-loki-logging
Configure Grafana Loki logging using byteforge-loki-logging library for Python/Flask applications. Use when setting up Loki logging, configuring centralized logging, or adding structured JSON logging to any Python project.
kurrentdb
Provides KurrentDB (EventStoreDB) client code for event sourcing and CQRS. Generates correct package names, connection strings, and API patterns for Python, Node.js, .NET, F#, Go, Java, Rust. Triggers on "kurrentdb", "eventstore", "event sourcing", "append events", "read stream", "subscription", "aggregate", "CQRS".
cc-track-tools
Provides paths to cc-track utility scripts for validation, task completion, and git operations. Use when a cc-track command needs to run a script.
repo-clipboard
Snapshot the current directory into pseudo-XML for LLM context. Use when you need to share a repo (or a sub-tree) with Codex/LLMs, especially for code review/debugging, generating an agent-friendly “repo snapshot”, or piping context into tools like `llm` (see skill $llm-cli). Supports `.gitignore`-aware file discovery, common ignore patterns, extension filtering, regex include/exclude, optional file-list printing, line-range snippets, and writes `/tmp/repo_clipboard.{stdout,stderr}` for reuse.
deep-reason
Esta skill debe usarse cuando el usuario pide \"pensemos esto a fondo\", \"analicemos paso a paso\", \"evaluemos opciones\", \"razonemos sobre esto\", \"pensemos detenidamente\", \"meditemos\", \"qué me sugieres\", \"qué me recomiendas\", \"esto es complejo\", \"esto es complicado\", \"problema grande\", o ante problemas que requieren análisis profundo, afectan múltiples componentes del sistema, tienen implicaciones arquitectónicas importantes, o representan decisiones de diseño con impacto significativo. IMPORTANTE: Invocar esta skill en lugar de usar seq-think MCP directamente - la skill proporciona workflow estructurado con generación de documentos de análisis.
check-third-party-docs
Esta skill debe usarse cuando el usuario pide \"investiga documentación de\", \"consulta documentación de\", \"quiero integrar X en\", \"cómo integrar\", \"implementar X en proyecto\", \"qué librería para\", \"instalar\", \"configurar\", \"error con\", o menciona agregar funcionalidad que requiere dependencias especializadas (validación con zod, procesamiento imágenes con sharp, colas con bull, caché con ioredis, formularios con react-hook-form). IMPORTANTE: Invocar esta skill en lugar de usar Context7 MCP directamente - la skill proporciona framework de decisión sobre cuándo usar Context7 vs dependency-docs-collector agent según complejidad. No usar para paquetes ampliamente conocidos como express, react, vue, lodash, axios, jest; Claude tiene datos de entrenamiento suficientes para estos. Usar solo para paquetes especializados, plugins de framework, o librerías poco conocidas.
create-pr
Esta skill debe usarse cuando el usuario pide "crea el PR", "prepara el PR", "escribe el PR", "genera el PR", "draft del PR", "documenta el PR", "crea la descripción del PR", o menciona crear pull request manualmente. Proporciona formato estructurado adaptado al tamaño de los cambios.
document
Esta skill debe usarse cuando el usuario pide "documentar un patrón", "documentar un problema", "documentar una decisión", "documentar guías", "documentar la sesión", "documentar el conocimiento de la sesión", "document session knowledge", "capturar lo aprendido en la sesión", "crear documentación de", o quiere capturar conocimiento técnico de la sesión usando plantillas estructuradas.
dropletify
Esta skill debe usarse cuando el usuario pide "desplegar en DigitalOcean", "configurar droplet", "deploy a droplet", "CI/CD para DigitalOcean", "GitHub Actions para droplet", o quiere preparar un proyecto para despliegue con Docker en DigitalOcean.
typescript-advanced-types
Esta skill debe usarse cuando el usuario pide "planear biblioteca TypeScript", "crear módulo reutilizable", "refactorizar tipados", "refactorizar tipos de un módulo", o cuando estés en modo plan y el diseño requiera tipados fuertes de TypeScript, sistemas extensibles, o arquitecturas type-safe. Especialmente útil para planear sistemas de notificaciones, background jobs, cores de aplicación, o módulos pluggables que requieran tipos complejos. Proporciona guía completa para diseñar y construir módulos y bibliotecas type-safe con el sistema de tipos avanzado de TypeScript.
plan-feature
Esta skill debe usarse cuando el usuario pide "planear una feature", "plan a feature", "crear un plan de acción", "disenar una implementacion", "design an implementation", "crear un plan de desarrollo", "create a development plan", "quiero planear", "quiero hacer un plan", "quiero disenar", o cuando solicite un feature cuya complejidad lo requiera. Ejecuta workflow de 5 fases: discovery, exploracion del codebase, clarificacion, arquitectura, y escritura del plan. Al aprobar el plan, invoca smart-delegation automaticamente para ejecutar la implementacion.
post-implementation
Esta skill debe usarse cuando el usuario pide "haz review de los cambios", "review the changes", "aplica el post-implementacion", "apply post-implementation", "run post-implementation", o cuando el plan aprobado instruye "invoke /smart-plan:post-implementation". Ejecuta workflow post-implementacion despues de que el codigo este completo con quality review (3 reviewers paralelos), auto-fix de issues (confianza >= 80%), documentacion del feature, y commit opcional. Puede usarse despues de cualquier implementacion, no solo smart-plan.
smart-delegation
Esta skill debe usarse cuando Claude detecta que una implementacion es lo suficientemente grande como para dividirla en sub-agentes (5+ archivos, dependencias entre cambios, nuevas abstracciones que otros archivos consumen), cuando el usuario pide "delega la implementacion", "orquesta los implementadores", "usa sub-agentes", "delegate to sub-agents", "orchestrate implementers", o cuando plan-feature invoca la delegacion tras aprobar un plan.
smart-interview
Esta skill debe usarse cuando el usuario pregunta "¿Preguntas?", "¿Tienes dudas?", "¿Tienes preguntas?", "¿Quieres aclarar algo?", "¿Necesitas aclarar algo?", "aclara lo que necesites", o cuando quiere aterrizar requerimientos antes de planear. Tambien la invoca plan-feature en Phase 3. Ejecuta entrevista estructurada para obtener requerimientos cuantificables, reglas de negocio traducibles a codigo, y flujos del sistema; luego anota los resultados en el plan.
Page 1330 of 1484 · 74167 results
