skill-lifecycle-manager

skill-lifecycle-manager215 wordsMITv1.0.0Repo-owned

skill-lifecycle-manager

Report skill lifecycle stage from frontmatter, eval coverage, and validators. Use when promoting, deprecating, or auditing repo skills. NOT for live installs.

Quick Start

Install:

npx skills add github:wyattowalsh/agents --skill skill-lifecycle-manager -y -g --agent antigravity --agent claude-code --agent codex --agent crush --agent cursor --agent gemini-cli --agent github-copilot --agent grok --agent opencode

Use: /skill-lifecycle-manager <skill-name|repo> [--format json]

Works with Claude Code, Gemini CLI, OpenCode, and other agentskills.io-compatible agents.

Source & provenance

This page is generated from the repository file skills/skill-lifecycle-manager/SKILL.md by wagents docs generate.

What It Does

Classify repository skills by lifecycle stage and readiness gates.

Modes

$ARGUMENTS	Action
<name>	Lifecycle report for one skill
repo / --all	Summary for every skills/*/ directory
--format json	Machine-readable report
Empty	Show stage definitions and example commands

Critical Rules

1. Never auto-promote a skill based on lifecycle heuristics alone.
2. Treat missing evals as a draft signal, not a hard block for internal skills.
3. Do not mutate metadata.internal or catalog authoring rows from this skill.
4. Run the repo validation command before declaring a skill active-ready.
5. Route executable fixes to skill-creator or the maintainer lead.

Public Metadata

Field	Value
Source Type	repo-owned
Display Source	github:wyattowalsh/agents
Source Kind	repo
Installability	portable command
Review State	reviewed
Target Agents	antigravity, claude-code, codex, crush, cursor, gemini-cli, github-copilot, grok, opencode

General

Field	Value
Name	skill-lifecycle-manager
License	MIT
Version	1.0.0
Author	wyattowalsh

Claude Code

Field	Value
Argument Hint	`[skill-name

View Full SKILL.md

---
name: skill-lifecycle-manager
description: >-
  Report skill lifecycle stage from frontmatter, eval coverage, and validators.
  Use when promoting, deprecating, or auditing repo skills. NOT for live installs.
user-invocable: true
argument-hint: "<skill-name|repo> [--format json]"
license: MIT
metadata:
  author: wyattowalsh
  version: "1.0.0"
---

# Skill Lifecycle Manager

Classify repository skills by lifecycle stage and readiness gates.

**Scope:** Read-only lifecycle reporting. Does not edit skills, run installs, or mutate catalog indexes.

## Dispatch

| $ARGUMENTS | Action |
|------------|--------|
| `<name>` | Lifecycle report for one skill |
| `repo` / `--all` | Summary for every `skills/*/` directory |
| `--format json` | Machine-readable report |
| Empty | Show stage definitions and example commands |

## Lifecycle Stages

| Stage | Signals |
|-------|---------|
| `draft` | TODO description, missing evals, or failing `scripts/check.py` contract |
| `internal` | `metadata.internal: true` |
| `active` | Valid frontmatter, eval manifest, and portable validator present |
| `deprecated` | Body or metadata marks deprecation (maintainer-authored) |

## Workflow

```bash
uv run python skills/skill-lifecycle-manager/scripts/lifecycle_report.py <name>
uv run python skills/skill-lifecycle-manager/scripts/lifecycle_report.py --all --format json
```

Pair lifecycle output with `/skill-creator audit` before promotion.

## Validation Contract

```bash
uv run python skills/skill-lifecycle-manager/scripts/check.py
```

## Critical Rules

1. Never auto-promote a skill based on lifecycle heuristics alone.
2. Treat missing evals as a draft signal, not a hard block for internal skills.
3. Do not mutate `metadata.internal` or catalog authoring rows from this skill.
4. Run the repo validation command before declaring a skill active-ready.
5. Route executable fixes to skill-creator or the maintainer lead.

Download from GitHub

Resources

Skill CatalogBrowse custom and external skills.

CLI ReferenceInstall and manage skills.

agentskills.ioThe open ecosystem for cross-agent skills.

---

View source on GitHub