MCP App StoreMCP App Store
de deepagents-autoglm119
Guide et modèles pour l'authoring de Agent Skills modulaires (SKILL.md), incluant les meilleures pratiques, la disposition des fichiers et des scripts d'initialisation pour échafauder des skills.
Fournit un guide concis et tranché ainsi que des outils pour créer des Agent Skills. Il explique l'anatomie du fichier SKILL.md, la divulgation progressive, les modèles de ressources groupées (scripts, références, assets) et propose des scripts d'initialisation et des modèles pour créer de nouveaux skills.
À utiliser lors de la création ou de la mise à jour d'un Agent Skill : initialisation des dossiers de skill, rédaction du frontmatter de SKILL.md, décision de ce qui appartient aux scripts vs références, et validation du format du skill avant publication. Idéal lors du développement de capacités d'agent ou lors de l'encapsulation de workflows répétables.
Conçu pour les flux de travail CLI DeepAgents et les environnements d'exécution d'agents génériques qui chargent des fichiers SKILL.md ; applicable aux intégrations d'agents de style Claude/Codex et aux outils de skill pilotés par CLI.
A well-documented skill-creator guide for the DeepAgents CLI ecosystem, providing templates and scripts to scaffold new Agent Skills. The SKILL.md is comprehensive with progressive disclosure patterns, frontmatter specs, and step-by-step authoring workflow. Both scripts (init_skill.py, quick_validate.py) require CLI arguments and exited with usage messages when run without them — expected behavior for scaffolding/validation tools, not bugs.
pyyaml (quick_validate.py imports yaml)Clean skill with no security concerns. SKILL.md is thorough and well-structured — serves as both a reference and a template. The init_skill.py script properly validates skill names per the Agent Skills spec (Unicode lowercase alphanumeric + hyphens, max 64 chars). quick_validate.py uses yaml.safe_load (safe). No network calls, no credentials, no destructive operations.
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.