creating-skills

creating-skills is a skill for Claude Code, Codex from TechyMT/claude-code-superpowers. It costs 83 tokens per session (1,387 once invoked), scanned A, original, MIT.

A guide to turning a repeated engineering pattern into a reusable skill for an AI assistant. It explains how to combine general instructions with examples from the real codebase.

In plain words
What is it for?
Use it when packaging a recurring code pattern as a SKILL.md file, reviewing an existing skill, or deciding what examples and application steps it needs.
Why use it?
It prevents a skill from becoming either vague advice or code-specific documentation that cannot be applied elsewhere. The result tells the assistant both what to do and when not to do it.

Skill for Claude CodeCodex

Part of the claude-code-superpowers plugin — 16 skills shipped together

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/techymt/claude-code-superpowers/creating-skills
Any agent
npx skills add TechyMT/claude-code-superpowers --skill creating-skills
Clone the repo
git clone --depth 1 https://github.com/TechyMT/claude-code-superpowers

Made for: Claude Code, Codex.

Or install claude-code-superpowers, the plugin that ships this one along with the rest of its 16 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for creating-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/techymt/claude-code-superpowers/creating-skills.svg)](https://agentmods.dev/skills/techymt/claude-code-superpowers/creating-skills)
Your own site
<a href="https://agentmods.dev/skills/techymt/claude-code-superpowers/creating-skills"><img src="https://agentmods.dev/badge/skills/techymt/claude-code-superpowers/creating-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,387 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 $0.00083 $0.01387
Opus 5 $0.00042 $0.00694
Sonnet 5 $0.00017 $0.00277
Haiku 4.5 $0.00008 $0.00139

Measured 4d ago against content hash 04a6ae10aabb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

creating-skills 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 4d 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.

skills/creating-skills/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creating Skills

Overview

A skill is a unit of transferable understanding, not a documentation page. It teaches an AI assistant a pattern well enough that it applies the pattern correctly without being reminded — including knowing when not to apply it.

Every skill has two layers. The generic layer stands alone: someone who has never seen your codebase reads it and understands the pattern. The source layer grounds it: real code from a real file proves the pattern is battle-tested, not invented.

If a skill only has the source layer, it's internal documentation. If it only has the generic layer, it's a blog post. Both layers together make it a skill.


Structure

Every skill follows this order:

---
name: skill-name
description: Use when [specific triggering conditions — NOT a summary of what the skill does]
---

# Skill Name

## The pattern          ← generic, no codebase knowledge required
## Why this matters  ← domain connection: what breaks for users without this
## How to apply it      ← concrete steps
## In the source  ← real source code with // Source: file/path.ext
## Apply it to your code  ← before/after with // WHY: comments on every change
## Signals that you need this pattern
## Signals that you're over-applying it
## Works with           ← related skills

The real-code requirement

The pattern section must contain code extracted from the actual source — not code written to illustrate the concept.

How to tell the difference:

  • Invented code looks clean, minimal, and perfectly illustrative
  • Real code has imports, handles edge cases, and sometimes does things that seem unrelated to the pattern

Real code earns trust. Invented code loses it the moment a reader opens the actual file and finds something different.

Every code block in section 4 must have a // Source: path/to/actual/file.ext comment. If you can't point to a file, the code doesn't belong in the pattern section.


The two-layer rule

The generic section ("The pattern") must pass the stranger test: someone who has never heard of the source codebase reads it and can apply the pattern to their own project.

Read the full file on GitHub · 137 lines

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. 4d ago First seen · 137 lines · 83 tokens per session scan A 04a6ae10aabb

Subscribe to this mod's changes

creating-skills is a skill published in the GitHub repository TechyMT/claude-code-superpowers (5 stars, last pushed 5mo ago), licensed MIT. It adds 83 tokens to every session and 1,387 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens