Carregando o README do repositório…
Mostrando 40 de 186 skills coletadas.
Creates an isolated git worktree outside the repository, in the agent's worktree home, off the right base branch. Use for parallel or isolated workspaces and multi-agent runs.
Idioma do texto original: inglês
Reconciles a project board with current work and delivery evidence, reporting gaps; applies only approved field changes. Use for board drift or blocked-work review.
Idioma do texto original: inglês
Regenerate catalog counts, layout claims, and README summaries from canonical sources. Run after adding, removing, or renaming skills, commands, or bundles.
Idioma do texto original: inglês
Audit the skills library for duplicates, stale content, spec violations, and structural issues. Run periodically or before releases.
Idioma do texto original: inglês
Validate SKILL.md files against the Agent Skills spec and Claude Code extensions. Run on new or modified skills before committing.
Idioma do texto original: inglês
Router behind /agent. Parses audit, config, init, or route and delegates to the matching agent-setup engine without adding logic of its own.
Idioma do texto original: inglês
Generates raster images (icons, illustrations, textures) via the logged-in Codex CLI image tool. Use when an agent needs a real image but has no native image generation.
Idioma do texto original: inglês
Granular feedback on drafts without rewriting. Generates highlighted HTML with click-to-reveal inline comments. Use when user says "comment on this", "leave comments on", "give feedback on", or asks for feedback on a draft. Supports multiple lenses—editor…
Idioma do texto original: inglês
Improves context efficiency and diagnoses context degradation: budgets, masking, KV-cache, partitioning, lost-in-middle, poisoning. Use when token cost or context quality constrains a task.
Idioma do texto original: inglês
Builds evaluation frameworks for agent systems, including LLM-as-judge design. Use when testing agent performance, comparing model outputs, or debugging inconsistent evals.
Idioma do texto original: inglês
Creates MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Activates on: "build an MCP server", "create MCP tools", "integrate API via MCP", "write a FastMCP server", "add an MCP server to an…
Idioma do texto original: inglês
Designs memory architectures for agents that persist state across sessions and keep entities consistent. Use when choosing among Mem0, Zep/Graphiti, Letta, LangMem, or Cognee.
Idioma do texto original: inglês
Designs multi-agent architectures that split work across agents to isolate context. Use when one agent's context limit is exceeded or subtasks decompose in parallel.
Idioma do texto original: inglês
Applies prompt engineering patterns — few-shot, chain-of-thought, templates, optimization. Use when improving prompts, debugging agent behavior, or designing generation prompts.
Idioma do texto original: inglês
Guides creating or updating a skill with specialized knowledge, workflows or tool integrations. Use when authoring a new SKILL.md or editing an existing skill.
Idioma do texto original: inglês
Designs agent-facing tools: descriptions, schemas, responses, errors, naming, and consolidating overlapping tool sets. Use when creating tools or when agents pick the wrong one.
Idioma do texto original: inglês
Designs RESTful APIs for NestJS: endpoints, OpenAPI/Swagger docs, versioning, error responses, DTOs, and pagination. Use when designing or documenting API endpoints.
Idioma do texto original: inglês
Designs error handling, exception filters, error responses, logging, and recovery for React, Next.js, and NestJS. Use when implementing or reviewing error flows.
Idioma do texto original: inglês
Designs and reviews GraphQL schemas, resolvers, mutations, pagination, and data loading. Use when building or refactoring GraphQL APIs or fixing N+1 and resolver design.
Idioma do texto original: inglês
Builds resilient data ingestion pipelines from paginated APIs using two watermarks so progress is never lost. Not for one-shot calls, websockets, or file downloads.
Idioma do texto original: inglês
Guides NestJS 12 APIs with Prisma and Postgres — modules, DI, guards, interceptors, pipes, DTOs, auth, errors. Use when building NestJS APIs or debugging Nest-specific issues.
Idioma do texto original: inglês
Writes NestJS Vitest tests — testing modules, provider mocks, service/controller specs, Supertest e2e. Use for any test touching a NestJS service, controller, guard, or endpoint.
Idioma do texto original: inglês
Guides Turborepo monorepos: turbo.json tasks, dependsOn, caching and remote cache, --filter/--affected, internal packages. Use when configuring tasks or debugging cache.
Idioma do texto original: inglês
Solves TypeScript/JS problems and refactors TS for type safety: narrowing, branded types, deep-instantiation errors, strict tsconfig, module resolution, JS-to-TS migration.
Idioma do texto original: inglês
Ask which Dev Loop skill or flow fits the current situation. A router over the flagship idea-to-ship path.
Idioma do texto original: inglês
Builds and sharpens a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
Idioma do texto original: inglês
Executes a prepared GitHub issue without inventing decisions, escalates plan gaps, and tracks review, CI, merge, and deploy evidence. Use for an approved plan or issue queue.
Idioma do texto original: inglês
Turns a rough request into one execution-ready issue via the shared requirements, planning, and issue-publishing engines. Use for /prd prepare or feature intake.
Idioma do texto original: inglês
Grills the user relentlessly about a plan, decision, or idea until every branch of the design tree is resolved. Use when stress-testing thinking or when told grill me.
Idioma do texto original: inglês
Writes a handoff document so a fresh agent session can continue the current work. User-invoked.
Idioma do texto original: inglês
Repo-grounded discovery interview that produces a handoff brief for PRD writing, feature intake, or planning.
Idioma do texto original: inglês
Validates draft requirements and blocks execution until the issue holds a complete, current implementation contract. Use when checking a PRD or plan for execution readiness.
Idioma do texto original: inglês
Publishes prepared requirements and plans as one GitHub feature issue, with child issues only when justified. Use when filing a PRD or bug as issues or sub-issues.
Idioma do texto original: inglês
Writes repository-grounded requirements with full scope and observable EARS acceptance criteria. Use when drafting a PRD or scoping a feature. Plans: writing-plans.
Idioma do texto original: inglês
Audits a project board's fields, columns, and scope, and applies requested setup, copy, or normalization on GitHub or Jira boards. Use when inspecting or configuring a board.
Idioma do texto original: inglês
Runs a multi-phase verification pass on finished AI agent work to catch bugs, missed requirements, and bad assumptions. Use after long multi-step tasks or on check your work.
Idioma do texto original: inglês
Investigates a question against primary sources and writes one Markdown note citing each claim. Use for docs, API, version or limit facts, or reading legwork to delegate.
Idioma do texto original: inglês
Writes an Agent skills routing block in CLAUDE.md/AGENTS.md plus docs/agents/ recording issue tracker, kanban labels and domain docs. Use once per repo before the dev-loop skills.
Idioma do texto original: inglês
Re-pitch the last message in plain English using the project's glossary vocabulary.
Idioma do texto original: inglês
Charts a foggy effort too big for one session as a map issue of decision tickets, then resolves one ticket per session until the way is clear. Plans only.
Idioma do texto original: inglês
Copie este prompt para o assistente de IA que você usa.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/shipshitdev/skills.Arquivo de origem do README: README.md
Ler o README original