From superpowers-plus
Generates new skill.md files from natural language descriptions, observed patterns, or codebase analysis. Enables self-extending skill ecosystem.
npx claudepluginhub bordenet/superpowers-plus --plugin superpowers-plusThis skill uses the workspace's default tool permissions.
> **Wrong skill?** Skill structure/format → `writing-skills`. Checking skill health → `skill-health-check`. Diagnosing skill issues → `superpowers-doctor`.
Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.
Share bugs, ideas, or general feedback.
Wrong skill? Skill structure/format →
writing-skills. Checking skill health →skill-health-check. Diagnosing skill issues →superpowers-doctor.Purpose: Generate skill.md files from descriptions, patterns, or analysis Last Updated: 2026-03-16
Announce at start: "I'm using the skill-authoring skill to help create a new skill."
This skill enables superpowers-plus to extend itself. Three modes:
| Mode | Input | Output |
|---|---|---|
| From Description | Natural language | Draft skill.md |
| From Patterns | learning-state.json observations | Skill candidates |
| From Codebase | Repository analysis | Skill recommendations |
Triggers: "create a skill for...", "I need a skill that...", "make a skill to..."
User: "I need a skill that checks for TypeScript strict mode violations before commit"
Response:
I'll help create a TypeScript strict mode skill.
**Proposed skill:**
- Name: `domain-specific-conventions` (overlay)
- Domain: `engineering`
- Triggers: ["strict mode violations", "typescript strict", "check strict mode", "ts strict"]
**What it would do:**
1. Check tsconfig.json for strict mode settings
2. Run tsc --noEmit to find violations
3. Categorize violations by severity
4. Suggest fixes or auto-fix where possible
**Integration:**
- Could run as part of pre-commit-gate
- Composition: consumes code-changes, produces strict-validated
Want me to generate the full skill.md?
Before presenting the draft:
Triggers: "turn this pattern into a skill", "synthesize skill from patterns"
When you notice a recurring pattern worth codifying, tell the AI:
"Turn this pattern into a skill: [pattern description]"
The pattern description contains the "what" — extract trigger conditions, actions, and outcomes, then expand into the full skill structure.
Triggers: "what skills should this repo have", "skill gap analysis"
| Target | What to Look For |
|---|---|
.github/workflows/ | CI patterns that could be skills |
scripts/ | Manual scripts to codify |
package.json scripts | Build/test patterns |
| Commit history | Recurring commit types |
| TODOs/FIXMEs | Pain points to address |
For each recommended skill:
See references/output-location.md for directory structure and domain selection guide.
name: <skill-name>
source: superpowers-plus
triggers: ["trigger 1", "trigger 2"]
description: <one-line description>
Required sections: ## When to Use, ## Process, ## Examples, ## Companion Skills, ## Failure Modes.
superpowers-doctor)harsh-review.sh · user approvalskills/{domain}/ · update README · ./install.shSkip when: domain design (domain-design) · structural lint (skill-health-check) · runtime issues (superpowers-doctor)
| Failure | Fix |
|---|---|
| Oversized skill (>250L) | Extract reference material to references/ |
| Missing frontmatter | Add --- delimiters, description:, triggers: |
| Trigger collision | Run superpowers-doctor before committing |