agentleFS
bordenetbordenet/superpowers-plus/skills/productivity/skill-authoring/skill.md

skill-authoring

Skill8 starsChanged 3 days agoMITView on GitHub

The genesis capability — create new skills from natural language descriptions, observed patterns, or codebase analysis. Makes superpowers-plus self-extending.

87 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use cloud-api-recipe-authoring, codebuddy-ide-mcp-upgrade and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • TencentCloudBaseSkill

    cloud-api-recipe-authoring

    Author or revise a cloud-api-operations recipe (config/source/skills/cloud-api-operations/references/recipes/). Encodes why the long tail of control-plane capabilities is deliberately NOT wrapped as MCP/CLI tools, the API-first admission test for whether a capability deserves a recipe, the negative and positive lists, the fixed recipe structure, the writing rules distilled from writing-for-agents, the user-facing copy red lines, and the product regeneration/verification pipeline. Also routes contributors (and their agents) to the contribution flow and the pre-PR self-test protocol in references/contributing.md. Use when adding a recipe, judging whether a scenario belongs in the recipe set, updating the recipes index, re-checking existing recipes against the admission test, or onboarding someone who wants to submit one.

    Also in 3 projects that use this

  • TencentCloudBaseSkill

    codebuddy-ide-mcp-upgrade

    升级 CodeBuddy IDE(genie 扩展)内置的 CloudBase MCP,以及 MCP 发版时同步 IDE 侧白名单。当用户提到「更新 IDE 里的 MCP」「内置 MCP 版本太老」「IDE 集成的 CloudBase 功能不足」「改工具白名单 toolWhiteList」「把新 bundle 打进 CodeBuddy」「白名单漂移」「MCP 发版要同步什么」时使用。覆盖:解包定位内置 bundle 与内嵌配置、重新构建 mcp bundle、生成新的工具白名单与系统提示词、安全注入 IDE 并备份、用 MCP 协议验证工具清单、人工端到端验收、一键回滚。

    Also in 3 projects that use this

  • DIL8654Skill

    api-contract-review

    Review ASP.NET Core Web API contracts for HTTP semantics, versioning, backward compatibility, and response consistency. Use when the user asks to review an API, check endpoints, validate REST behavior, or before releasing contract changes.

    Also in 5 projects that use this

  • zaxbysauceSkill

    pr-review-fix

    Codex adapter for addressing pull request review feedback in opencode-swarm. Use when the user asks to fix PR review comments, requested changes, reviewer findings, CI-review notes, or a pasted review summary with low false-positive tolerance.

    Also in 3 projects that use this

  • albertdobmeyerSkill

    git-workflows

    Advanced git operations beyond add/commit/push. Use when rebasing, bisecting bugs, using worktrees for parallel development, recovering with reflog, managing subtrees/submodules, resolving merge conflicts, cherry-picking across branches, or working with monorepos.

    Also in 3 projects that use this

  • rogue-dev-studioSkill

    frontend-engineering

    Expert frontend application engineering: accessible UI structure, state and data-fetching discipline, form/validation UX, responsive layouts, performance budgets, and integration with API contracts. Use when building or refining SPA/web screens, design-system consumption, client-side routing, or fixing UI reliability (loading, empty, and error states).

    Also in 3 projects that use this

  • +6 more from TencentCloudBase

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 78 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before presenting the draft:

    line 90
  2. Distinctive:

    When you notice a recurring pattern worth codifying, tell the AI:

    line 112
  3. Very specific:

    Check trigger uniqueness — no overlap with existing skills (superpowers-doctor)

    line 164
  4. Very specific:

    Verify domain fit · run harsh-review.sh · user approval

    line 165

“Common” is measured: kept by at least 6 in 10 of the 78 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
skill.md

Skill Authoring

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."

When to Use

  • User asks to create, generate, or scaffold a new skill
  • A repeating pattern is identified that should become a reusable skill
  • Skill gap analysis reveals missing capabilities in the skill catalog

Authoring Modes

This skill enables superpowers-plus to extend itself. Three modes:

ModeInputOutput
From DescriptionNatural languageDraft skill.md
From Patternslearning-state.json observationsSkill candidates
From CodebaseRepository analysisSkill recommendations

Mode 1: From Natural Language

Triggers: "create a skill for...", "I need a skill that...", "make a skill to..."

Process

  1. Capture intent — What should this skill do?
  2. Identify domain — engineering, wiki, writing, productivity, etc.
  3. Generate triggers — What phrases should invoke this skill?
  4. Define workflow — What steps does the skill guide?
  5. Draft skill.md — Using the template structure
  6. Review with user — Iterate until approved

Example

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?

Validation Checklist

Before presenting the draft:

  • Name is kebab-case, unique, descriptive
  • Triggers don't overlap with existing skills
  • Description starts with "Use when..."
  • Process has actionable steps
  • At least one concrete example
  • Domain is appropriate

Mode 2: From Observed Patterns

Triggers: "turn this pattern into a skill", "synthesize skill from patterns"

Process

  1. Identify pattern — User describes a recurring workflow or behavior they want codified
  2. Review scope — Determine if the pattern is distinct enough to warrant its own skill
  3. Generate draft — Create skill.md from pattern description
  4. Validate — Run through the quality checklist (see below)

Example

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.

Mode 3: From Codebase Analysis

Triggers: "what skills should this repo have", "skill gap analysis"

Process

  1. Scan repository — Analyze structure, scripts, patterns
  2. Identify workflows — Recurring tasks, manual processes
  3. Propose skills — Ranked by potential value
  4. Generate drafts — User selects which to create

Analysis Targets

TargetWhat to Look For
.github/workflows/CI patterns that could be skills
scripts/Manual scripts to codify
package.json scriptsBuild/test patterns
Commit historyRecurring commit types
TODOs/FIXMEsPain points to address

Output Format

For each recommended skill:

  1. Name — Suggested skill name
  2. Evidence — What in the codebase suggests this
  3. Value — Why this skill would help
  4. Complexity — Low/Medium/High
  5. Priority — P1/P2/P3

Skill Template

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.

Quality Gates

  1. Validate YAML frontmatter (name, triggers, description)
  2. Check trigger uniqueness — no overlap with existing skills (superpowers-doctor)
  3. Verify domain fit · run harsh-review.sh · user approval
  4. Save to skills/{domain}/ · update README · ./install.sh

Skip when: domain design (domain-design) · structural lint (skill-health-check) · runtime issues (superpowers-doctor)

Companion Skills

  • writing-skills: Skill file format reference
  • skill-health-check: Structural lint for skill files
  • superpowers-doctor: Runtime diagnostics after publishing
  • domain-design: Domain-level skill design
  • golden-agents: Similar scaffolding UX pattern
  • evolution-loop: Pattern-driven skill creation

Failure Modes

FailureFix
Oversized skill (>250L)Extract reference material to references/
Missing frontmatterAdd --- delimiters, description:, triggers:
Trigger collisionRun superpowers-doctor before committing

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.