skill-governance
Audits and manages the skill library to ensure all skills are relevant, non-redundant, and rule-compliant.
Install
mkdir -p .claude/skills/skill-governance && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14570" && unzip -o skill.zip -d .claude/skills/skill-governance && rm skill.zipInstalls to .claude/skills/skill-governance
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Curate the Inspire Courts skill library — decide when a workflow earns a skill, refine/dedupe, retire stale skills, and audit skills against current architecture rules. Keeps the toolkit lean and reviewed. Use periodically, after big architecture changes, or when adding/removing a skill.Key capabilities
- →Decide when a workflow earns a skill based on defined criteria
- →Refine and deduplicate existing skills to avoid redundancy
- →Retire stale skills that are no longer relevant or accurate
- →Audit skills against current architectural rules and conventions
- →Enforce SKILL.md conventions for frontmatter and body content
- →Update the skill library map with current skills
How it works
This skill evaluates workflows against a 4-point bar to determine if they qualify as a skill, then refines, deduplicates, and audits existing skills against architectural rules and conventions. It also manages the retirement of stale skills and updates the library map.
Inputs & outputs
When to use skill-governance
- →Auditing the skill library
- →Retiring stale skills
- →Reviewing new skill creation
About skill-governance
Evaluates workflows against criteria to decide if they earn a skill, deduplicates redundant efforts, and ensures all SKILL.md files align with current architectural standards.
Curate the Inspire Courts skill library — decide when a workflow earns a skill, refine/dedupe, retire stale skills, and audit skills against current architecture rules. Keeps the toolkit lean and reviewed. Use periodically, after big architecture changes, or when adding/removing a skill.
When not to use it
- →When a workflow is a one-off task
- →When a workflow involves pure judgment with no repeatable steps
- →When a skill's instructions contradict current architecture and cannot be salvaged
Limitations
- →Requires adherence to specific SKILL.md conventions
- →Relies on defined criteria for skill creation and retirement
- →Auditing is based on explicit architectural rules like CLAUDE.md and AGENTS.md
How it compares
This workflow provides a structured, rule-based approach to skill library management, ensuring consistency and relevance, unlike ad-hoc methods that can lead to redundancy or outdated information.
Compared to similar skills
skill-governance side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| skill-governance (this skill) | 0 | 1mo | Review | Intermediate |
| session-handoff | 13 | 2mo | Review | Beginner |
| spec-to-backlog | 8 | 4mo | No flags | Intermediate |
| create-handoff | 3 | 6mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
session-handoff
davila7
Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.
spec-to-backlog
atlassian
Automatically convert Confluence specification documents into structured Jira backlogs with Epics and implementation tickets. When Claude needs to: (1) Create Jira tickets from a Confluence page, (2) Generate a backlog from a specification, (3) Break down a spec into implementation tasks, or (4) Convert requirements into Jira issues. Handles reading Confluence pages, analyzing specifications, creating Epics with proper structure, and generating detailed implementation tickets linked to the Epic.
create-handoff
parcadei
Create handoff document for transferring work to another session
moai-workflow-project
modu-ai
Integrated project management system with documentation, language initialization, and template optimization modules. Use when setting up projects, generating documentation, configuring multilingual support, or optimizing templates.
granola-core-workflow-b
jeremylongshore
Post-meeting note processing and sharing workflow with Granola. Use when reviewing meeting notes, sharing with team members, or processing action items after meetings. Trigger with phrases like "granola post meeting", "share granola notes", "granola follow up", "process meeting notes", "granola action items".
reporting
comeredon
Final pipeline execution report format. Defines the structure, agent registry, Mermaid gantt chart, and change summary. Used by AnalystAgent in Phase 6.