MCP App StoreMCP App Store
de agents-in-a-box9
Modèles SRE pour l'exploitation et la protection d'agents autonomes : plafonds de coûts, coupe-circuits, détection de blocage, observabilité et runbooks pour la récupération après incidents.
Fournit des modèles SRE prêts pour la production et adaptés aux agents IA. Comprend des vérifications concrètes et de petits utilitaires pour appliquer des plafonds de coûts, arrêter les boucles infinies, détecter les comportements bloqués et afficher des indicateurs de santé afin que les opérateurs puissent observer et agir.
Utilisez cette compétence lors de l'exécution de sessions d'agents autonomes ou de longue durée, pour coordonner des flux de travail multi-agents, ou lorsque vous avez besoin de garde-fous pour éviter les spirales de coûts ou de comportement (API défaillantes, boucles infinies, tentatives excessives). Également utile lors du débogage et de la réponse aux incidents.
Fonctionne avec les environnements d'exécution d'agents pouvant exécuter des fragments Python/bash et intégrer des variables d'environnement et des fichiers locaux (Claude/Claude-Code, Cursor, exécuteurs d'agents locaux).
Agent Ops provides SRE patterns (cost caps, circuit breakers, stall detection, observability, runbooks) for autonomous AI agent workflows. No bundled scripts — all code is inline in SKILL.md as examples. Well-written reference material with practical patterns, though the inline bash script uses template placeholders like {{TOOL_DIR}} that won't resolve outside the agents-in-a-box ecosystem. Security is solid with no risky patterns; one minor concern is the bash health script embedding $METRICS path directly in a python -c string, which could be injection-prone if the path were user-controlled (though here it's derived from $HOME).
Well-structured SRE reference skill. Code examples are idiomatic Python/bash. The skill is documentation-first rather than tool-first, which limits direct usability but makes it a good instructional resource. Would benefit from having actual runnable scripts in a scripts/ directory rather than just inline code blocks.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.