AGENT SKILLS · EQUIPAMENTO DE MISSÃO
Agent Skills úteis classificados pelo uso real
Compare Skills verificados por finalidade, conteúdo do pacote, instalações e evidências da fonte antes de adicioná-los.
- ESCOPO DO CATÁLOGO
- VERIFICADO
- Skills
- 22.403
- repositórios
- 3432
- última sincronização
- 27 de out. de 2026
mariusflorescuthermos
Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.
- Instalações / 1h
- 1
- GitHub Stars
- 0
- Atualizado
- 10 de out.
mateuszkruk1303raven-auto-implement
Carry out the user's instruction, optionally with a given GitHub issue, plan or external ticket link (Jira, Linear and similar) read as the specification, verify the change at a quick, standard or thorough level matched to risk, and summarize the result only in the final chat message.
- Instalações / 1h
- 1
- GitHub Stars
- 0
- Atualizado
- 20 de out.
mateuszkruk1303raven-md
Create, update or review AGENTS.md and CLAUDE.md (or another AI instructions file) from the project's real files, commands and conventions. AGENTS.md holds the shared content, CLAUDE.md imports it. Review gives a scorecard without rewriting rules. Does not initialize context folders or the stack.
- Instalações / 1h
- 1
- GitHub Stars
- 0
- Atualizado
- 20 de out.
mateuszkruk1303raven-merge
Merge the given PR after green CI and the user's consent, then confirm its GitHub issue, if any, is closed. Deploy is separate.
- Instalações / 1h
- 1
- GitHub Stars
- 0
- Atualizado
- 20 de out.
mateuszkruk1303raven-pr
Push the branch and create or update the PR of the given change, linked to its issue or external ticket. Only on explicit request; no merge.
- Instalações / 1h
- 1
- GitHub Stars
- 0
- Atualizado
- 20 de out.
mateuszkruk1303raven-shape
Refine an idea for a new product or a significant change to an existing system in a structured conversation about the problem, users and product scope. Write and resume shape-notes.md for Raven skills before the PRD. Use for shaping the vision, MVP scope, requirements and business rules; not for implementing a single bug.
- Instalações / 1h
- 1
- GitHub Stars
- 0
- Atualizado
- 20 de out.
mousesport9526browser-cdp
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP, agent-browser, 浏览器操作, 操作浏览器, Chrome CDP, 复用登录态, extract token from browser.
- Instalações / 1h
- 1
- GitHub Stars
- 0
- Atualizado
- 16 de out.
mousesport9526story-short-scan
短篇网文扫榜。分析知乎盐言、七猫、黑岩、点众等平台热门短篇数据，捕捉风口题材。触发方式：/story-short-scan、/短篇扫榜、「短篇什么火」「知乎故事排行」。
- Instalações / 1h
- 1
- GitHub Stars
- 0
- Atualizado
- 16 de out.
pawpairpaw-mail-usage
How to use the Paw Mail CLI (paw-mail). Use this skill when: (1) you need to run a CLI command (auth, accounts, emails, sync, threads, config), (2) someone asks how to use or invoke the mail CLI, (3) you need to check CLI flags or subcommands.
- Instalações / 1h
- 1
- GitHub Stars
- 0
- Atualizado
- 10 de abr.
technobureaucode-quality
Improve maintainability and secure engineering quality by removing verified dead code and applying modular, documented, testable practices, API compatibility rules, dependency hygiene, and observability standards. Use for explicit cleanup, refactoring, code review, or code-standard tasks; not as a side effect of documentation.
- Instalações / 1h
- 1
- GitHub Stars
- 0
- Atualizado
- 20 de out.
technobureautests
Add, improve, review, or document repository tests using the project's existing frameworks and verified commands, with enterprise coverage of functional, security, accessibility, performance, and resilience risks. Use only when test work, test strategy, test evidence, or docs/tests.md is requested; testing documentation is not part of ai-init's default output.
- Instalações / 1h
- 1
- GitHub Stars
- 0
- Atualizado
- 20 de out.
tinyanalyticstinyanalytics-events
Use when the user wants to measure specific actions in tinyanalytics beyond pageviews — "track signups", "instrument checkout", "add revenue tracking", "identify logged-in users", "track accounts/companies". Covers custom events (browser + server-side), revenue on events, user identity + traits, and B2B account (group) tracking, then verifies the data arrived and labels it in the catalog. TRIGGER when: tinyanalytics tracking already works and the user wants product events, conversions, revenue,
- Instalações / 1h
- 1
- GitHub Stars
- 0
- Atualizado
- 30 de jul.
githubcode-exemplars-blueprint-generator
Technology-agnostic prompt generator that creates customizable AI prompts for scanning codebases and identifying high-quality code exemplars. Supports multiple programming languages (.NET, Java, JavaScript, TypeScript, React, Angular, Python) with configurable analysis depth, categorization methods, and documentation formats to establish coding standards and maintain consistency across development teams.
- Instalações / 1h
- 1
- GitHub Stars
- 40,2 mil
- Atualizado
- 20 de out.
githubdoc-and-modernize
Two related workflows for a locally-cloned codebase, in one skill. Documentation mode produces a single, comprehensive, verifiable architecture document primarily by reading files on disk (local-first) — use it whenever the user wants to understand, map, document, research, or onboard onto a codebase ("research this repo", "write up the architecture", "do an architecture deep dive", "document how this codebase works", "map the system design", "create an onboarding doc"). Modernization mode gener
- Instalações / 1h
- 1
- GitHub Stars
- 40,2 mil
- Atualizado
- 20 de out.
githubreadme-blueprint-generator
Intelligent README.md generation prompt that analyzes project documentation structure and creates comprehensive repository documentation. Scans .github/copilot directory files and copilot-instructions.md to extract project information, technology stack, architecture, development workflow, coding standards, and testing approaches while generating well-structured markdown documentation with proper formatting, cross-references, and developer-focused content.
- Instalações / 1h
- 1
- GitHub Stars
- 40,2 mil
- Atualizado
- 20 de out.
githubrefactor-plan
Create a concrete plan before starting a multi-file refactor. Use when the user asks to plan, sequence, scope, or safely execute a refactor across multiple files; always investigate first, output the plan, and wait for confirmation before making code changes.
- Instalações / 1h
- 1
- GitHub Stars
- 40,2 mil
- Atualizado
- 20 de out.
mem0aimem0
Mem0 Platform SDK for adding persistent memory to AI applications. TRIGGER when: user mentions "mem0", "MemoryClient", "memory layer", "remember user preferences", "persistent context", "personalization", or needs to add long-term memory to chatbots, agents, or AI apps. Covers Python SDK (mem0ai), TypeScript SDK (mem0ai), and framework integrations (LangChain, CrewAI, OpenAI Agents SDK, Pipecat, LlamaIndex, AutoGen, LangGraph). Also covers the open-source self-hosted Memory class. This is the DE
- Instalações / 1h
- 1
- GitHub Stars
- 67,5 mil
- Atualizado
- 20 de out.
sickn33api-testing-observability-api-mock
You are an API mocking expert specializing in realistic mock services for development, testing, and demos. Design mocks that simulate real API behavior and enable parallel development.
- Instalações / 1h
- 1
- GitHub Stars
- 48,1 mil
- Atualizado
- 20 de out.
sickn33conversation-memory
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory
- Instalações / 1h
- 1
- GitHub Stars
- 48,1 mil
- Atualizado
- 20 de out.
garrytanfact-check
Systematic claim-by-claim verification for any content before it ships. Modeled on professional fact-checking desks (The New Yorker, ProPublica, IFCN standards): extract every verifiable claim, check each against live citable sources (never training data), assign a 6-level confidence status, apply corrections, and produce a scored pass/fail report. Includes a data-derived-claims gate for outputs produced FROM the brain or a database: PRODUCER ≠ VERIFIER (re-derive each claim via a different quer
- Instalações / 1h
- 1
- GitHub Stars
- 31 mil
- Atualizado
- 20 de out.
garrytanskillpack-harvest
Lift a proven skill from a host repo (e.g. your OpenClaw fork) back into gbrain's bundle so other clients can scaffold it. Editorial workflow: the CLI does the file copy + privacy lint; this skill drives the judgment-heavy genericization (scrub real names, generalize triggers, lift fork-specific conventions to references).
- Instalações / 1h
- 1
- GitHub Stars
- 31 mil
- Atualizado
- 20 de out.
alirezarezvaniazure-cloud-architect
Design Azure architectures for startups and enterprises. Use when asked to design Azure infrastructure, create Bicep/ARM templates, optimize Azure costs, set up Azure DevOps pipelines, or migrate to Azure. Covers AKS, App Service, Azure Functions, Cosmos DB, and cost optimization.
- Instalações / 1h
- 1
- GitHub Stars
- 28,4 mil
- Atualizado
- 30 de ago.
alirezarezvanichaos-engineering
Use when planning, running, or learning from chaos engineering experiments. Triggers on "chaos experiment", "fault injection", "gameday", "resilience test", "blast radius", "steady state", "abort criteria", "Chaos Toolkit", "Chaos Mesh", "Litmus", "Gremlin", "AWS FIS", or any deliberate failure-injection question. Ships experiment designer, blast-radius calculator, and postmortem generator (all stdlib Python), 4 references on chaos principles + experiment design + attack taxonomy + tooling lands
- Instalações / 1h
- 1
- GitHub Stars
- 28,4 mil
- Atualizado
- 30 de ago.
alirezarezvanicloud-security
Use when assessing cloud infrastructure for security misconfigurations, IAM privilege escalation paths, S3 public exposure, open security group rules, or IaC security gaps. Covers AWS, Azure, and GCP posture assessment with MITRE ATT&CK mapping.
- Instalações / 1h
- 1
- GitHub Stars
- 28,4 mil
- Atualizado
- 30 de ago.