skill-creator

A guide for creating, restructuring, or improving coding-agent skills. It defines the expected documentation structure and the research and review steps required before publishing one.

In plain words
What is it for?
Use it when creating a new skill, adapting an existing one to another technology, reorganising its files, or filling gaps in its documentation.
Why use it?
It helps keep skills consistent and prevents their documentation from being written without checking the codebase and relevant technical sources.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/fusengine/agents/skill-creator
Any agent
npx skills add fusengine/agents --skill skill-creator
Clone the repo
git clone --depth 1 https://github.com/fusengine/agents

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,184 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.01184
Opus 5 $0.00010 $0.00592
Sonnet 5 $0.00004 $0.00237
Haiku 4.5 $0.00002 $0.00118

Measured 2d ago against content hash 759330adecca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/ai-pilot/skills/skill-creator/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

It generates the skill's structural and documentation content only, not the skill's substantive technical guidance -- that must come from research-expert + explore-codebase findings gathered before writing.

Skill Creator

Agent Workflow (MANDATORY)

Before ANY skill creation, use TeamCreate to spawn 3 agents:

  1. fuse-ai-pilot:explore-codebase - Check existing skills, analyze structure
  2. fuse-ai-pilot:research-expert - Fetch latest official documentation online
  3. mcp__context7__query-docs - Get code examples from official sources

After creation, run fuse-ai-pilot:sniper for validation.


Overview

Action When to Use
New Skill Library/framework not yet documented
Restructure Existing skill doesn't follow pattern
Improve Missing references or outdated content
Adapt Copy from similar skill (Next.js → React)

Critical Rules

  1. ALL content in English - Never French or other languages
  2. SKILL.md is descriptive - Guides agent to references/templates
  3. References are conceptual - WHY + WHEN, max 150 lines
  4. Templates are complete - Copy-paste ready code
  5. Register in agent + marketplace.json - Or skill won't load
  6. Run sniper after creation - Validate all files

Architecture

skills/<skill-name>/
├── SKILL.md                    # Entry point (guides agent)
└── references/                 # All documentation
    ├── installation.md         # Setup, configuration (conceptual)
    ├── patterns.md             # Core patterns (conceptual)
    ├── ...                     # Other references
    └── templates/              # Complete code examples
        ├── basic-setup.md      # Full project setup
        └── feature-example.md  # Feature implementation

Read the full file on GitHub · 162 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 162 lines · 19 tokens per session scan A 759330adecca

Subscribe to this mod's changes

skill-creator is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed 29d ago), licensed MIT. It adds 19 tokens to every session and 1,184 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.