Help us improve
Share bugs, ideas, or general feedback.
From meta-skillpack-maintenance
Maintains Claude Code plugins through domain analysis, structure review, behavioral testing, and quality fixes for skills, commands, agents, hooks, and reference sheets. Use when enhancing existing packs.
npx claudepluginhub tachyon-beep/skillpacks --plugin meta-skillpack-maintenanceHow this skill is triggered — by the user, by Claude, or both
Slash command
/meta-skillpack-maintenance:using-skillpack-maintenanceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Systematic maintenance of Claude Code plugins including skills, commands, agents, hooks, and reference sheets.
Upgrades Claude Code plugins by aligning skills, hooks, and patterns with latest capabilities and best practices. Use after updates, for modernization, or on user request.
Guides creation of Claude Code plugins including skills, commands, agents, hooks, MCP servers, and configuration. Use for 'create plugin', 'make skill', scaffolding structures.
Quick-reference for editing Claude Code skills, agents, slash commands, hooks, plugins, and configs. Triggers on YAML frontmatter, .claude/ files, Task tools, hook debugging.
Share bugs, ideas, or general feedback.
Systematic maintenance of Claude Code plugins including skills, commands, agents, hooks, and reference sheets.
Maintenance = behavioral validation, not syntactic checking. Test if components guide Claude correctly, not if they parse correctly.
| Component | Location | Frontmatter |
|---|---|---|
| Skills | skills/*/SKILL.md | name, description, allowed-tools |
| Reference sheets | skills/using-*/*.md | (none - content files) |
| Commands | commands/*.md | description, allowed-tools, argument-hint |
| Agents | agents/*.md | description, model, tools |
| Hooks | hooks/hooks.json | JSON with event matchers |
Use for:
Do NOT use for:
superpowers:writing-skills)All reference sheets are in this skill's directory:
analyzing-pack-domain.md - Domain investigationreviewing-pack-structure.md - Structure review, scorecardtesting-skill-quality.md - Behavioral testing methodologyimplementing-fixes.md - Execution and versioningWhen reading analyzing-pack-domain.md, find it at:
skills/using-skillpack-maintenance/analyzing-pack-domain.md
Load: analyzing-pack-domain.md
Output: Coverage map, component inventory, gaps identified
Load: reviewing-pack-structure.md
Generate fitness scorecard:
Decision gate: Present scorecard → User decides: Proceed / Rebuild / Cancel
Load: testing-skill-quality.md
Test each component with challenging scenarios:
Output: Per-component test results (Pass / Fix needed)
Present findings by category:
Gaps requiring new components:
superpowers:writing-skills (each = separate RED-GREEN-REFACTOR)Existing components needing fixes:
Get user approval before execution.
Load: implementing-fixes.md
CRITICAL CHECKPOINT:
If gaps were identified → Use superpowers:writing-skills for EACH new skill first.
Do NOT create new skills inline. They require behavioral testing.
Execute approved changes:
---
name: skill-name
description: When to use this skill and what it does
allowed-tools: [Read, Grep, Glob] # optional
---
Key questions:
---
description: What this command does
allowed-tools: [Read, Bash, Glob, Grep]
argument-hint: "[optional_arg]"
---
Key questions:
---
description: What this agent specializes in
model: sonnet # or opus, haiku
tools: [Read, Grep, Glob, Bash, Write]
---
Key questions:
{
"hooks": {
"PostToolUse": [{
"matcher": "Write|Edit",
"hooks": [{"type": "command", "command": "script.sh"}]
}]
}
}
Events: PreToolUse, PostToolUse, UserPromptSubmit, Notification, Stop, SubagentStop, SessionStart, SessionEnd, PreCompact
Key questions:
| Impact | Bump | Examples |
|---|---|---|
| Low | Patch (x.y.Z) | Typos, formatting, minor clarifications |
| Medium | Minor (x.Y.0) | Enhanced guidance, new components, better examples |
| High | Major (X.0.0) | Components removed, structural changes, philosophy shifts |
Default for maintenance: Minor bump
| Thought | Reality |
|---|---|
| "I'll write new skills during execution" | NO. Use superpowers:writing-skills for each gap |
| "Syntax looks correct, no need to test" | Parsing ≠ effectiveness. Test behavior. |
| "This is a quick fix, skip the process" | Quick untested = broken later |
| "The command/agent is simple enough" | Simple things fail in edge cases. Test anyway. |
Investigation → Scorecard → Testing → Discussion → Execution
↓ ↓ ↓ ↓ ↓
Domain map Fitness Behavioral Present Apply
+ inventory rating validation + approve changes
Load briefings at each stage. Test with scenarios. Get approval. Execute.