Skill Creator

Trust Score 84/100

Guide and templates for authoring modular Agent Skills (SKILL.md), including best practices, file layout, and initialization scripts to scaffold skills.

triggers:create a skillinit_skill.pyskill templateskill authoringSKILL.md

GitHub SKILL.md

What it does

Provides a concise, opinionated guide and tooling for creating Agent Skills. It explains SKILL.md anatomy, progressive disclosure, bundled resource patterns (scripts, references, assets), and offers init scripts and templates to scaffold new skills.

When to use it

Use when creating or updating an Agent Skill: initializing skill folders, writing SKILL.md frontmatter, deciding what belongs in scripts vs references, and validating skill format before publishing. Ideal during development of agent capabilities or when packaging repeatable workflows.

What's included

Scripts: example init/validation scripts (has_scripts=true)
References: guidance embedded in SKILL.md (has_references=false)
Instructions: step-by-step rules for frontmatter, body size, resource organization, and validation commands

Compatible agents

Designed for DeepAgents CLI workflows and generic agent runtimes that load SKILL.md files; applicable to Claude/Codex-style agent integrations and CLI-driven skill tooling.

Audit Summary

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.

Watch Out

Requires pyyaml dependency for quick_validate.py
Scripts are CLI tools requiring arguments — cannot be run bare
Specific to DeepAgents CLI skill directory conventions

Missing Dependencies

pyyaml (quick_validate.py imports yaml)

Notes

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.

Information

Repository: deepagents-autoglm
Stars: 119

Trust Score

Overall84

Security88

Code Quality78

Architecture82

Usefulness70

Related Skills

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.

Back to Skills