# FrancyJGLisboa/agent-skill-creator

Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.

Repository: https://github.com/FrancyJGLisboa/agent-skill-creator
Canonical: https://ross.abutalabs.com/products/agent-skill-creator
Homepage: https://francyjglisboa.github.io/agent-skill-creator/
Language: Python
License: MIT
License Family: permissive
Topics: agent-skills, ai-agents, claude-code, codex, cursor, developer-tools, evals, github-copilot, governance, skill-marketplace
Last push: 2026-08-26T18:42:11+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 22
- inputs: {"age_days": 319, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2335, forks 256 (observed 2026-08-28T04:06:37.991142+00:00)

## What it is
Agent Skill Creator is a Python tool that turns human expertise (sentences, documents, scripts) into tested, installable agent skills for AI coding agents. It also provides a governed marketplace lifecycle for those skills, covering evidence, discovery, updates, rollback, quarantine, and distribution across 17 platforms.

## Use cases
- create tested agent skills from expert workflows
- govern a team marketplace of agent skills
- evaluate and dry-run agent skills before deployment
- roll back or quarantine broken agent skills
- distribute agent skills across multiple AI coding tools
- capture organizational knowledge as reusable skill packages

## When to choose
- you build and maintain agent skills for Claude Code, Codex, Cursor, or GitHub Copilot
- your team needs lifecycle governance (approve, publish, rollback, quarantine) for skills
- you want evals and security checks before deploying skills
- you need to distribute skills across many agent platforms

## When to avoid
- you need a RAG system, MCP server, or agent runtime - skills organize these but are not them
- you just want simple prompt templates without testing or governance
- you need a fully managed SaaS marketplace rather than a self-run one

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, testing, workflow-automation, developer-tools, prompt-engineering
- domain: developer-tools, large-language-models
- platform: python, cli, cross-platform
- tags: agent-skills, skill-marketplace, governance, claude-code, codex, cursor, github-copilot, evals, skill-lifecycle, rollback, quarantine, ai-agents, automation

## Member repositories
- FrancyJGLisboa/agent-skill-creator (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:37.991142+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:37:36.187817+00:00, confidence not recorded.
  - readme: https://github.com/FrancyJGLisboa/agent-skill-creator (fetched 2026-08-28T04:06:37.991142+00:00, sha 142807e959ea)
  - homepage: https://francyjglisboa.github.io/agent-skill-creator/ (fetched 2026-08-29T10:18:17.596407+00:00, sha 85da948f8a79)
- Data as of 2026-08-30T08:39:29.467469+00:00.