create-skill

A command for creating new Claude Code skills through a guided design and testing process. TDD, or test-driven development, means writing checks before building the thing they test.

In plain words
What is it for?
Use it to brainstorm, scaffold, test, and validate a new skill, optionally placing it inside a specific plugin.
Why use it?
It helps turn a rough idea into a consistent skill and exposes missing files or registration errors before the skill is finished.

Command

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 commands/athola/claude-night-market/create-skill
Clone the repo
git clone --depth 1 https://github.com/athola/claude-night-market
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,003 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 $0.00025 $0.03003
Opus 5 $0.00013 $0.01502
Sonnet 5 $0.00005 $0.00601
Haiku 4.5 $0.00003 $0.00300

Measured yesterday against content hash d1b0e0c53c1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-skill 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 yesterday.

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/abstract/commands/create-skill.md · 494 lines

How it starts

The opening of the file, as written. The whole thing — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Skill Command

Creates new skills through a structured workflow: iron-law → brainstorm → scaffold → validate. Uses Socratic questioning to refine rough ideas into well-designed skills before generating any files.

Usage

# Start with brainstorming (recommended)
/create-skill "a skill for analyzing test coverage gaps"

# Skip brainstorming if you already have a clear design
/create-skill analyzing-coverage --skip-brainstorm

# Create in specific plugin
/create-skill "debugging async race conditions" --plugin parseltongue

Workflow

Phase -1: Iron Law Interlock (Blocking)

This phase is required and cannot be skipped.

Quick Reference
  1. Create test file FIRST: tests/test_${skill_name}_skill.py
  2. Write structural tests: File exists, frontmatter valid, registered in plugin.json
  3. Run tests - capture RED state:
    pytest tests/test_${skill_name}_skill.py -v
    # Expected: FAILED (skill does not exist)
    
  4. Capture evidence:
    [E1] Command: pytest tests/test_${skill_name}_skill.py -v
    Output: FAILED - FileNotFoundError
    Status: RED - Interlock satisfied
    

Only after completing Phase -1 may you proceed.


Phase 0: Methodology Curation (Optional but Recommended)

Before brainstorming, consider surfacing expert frameworks for your domain.

Invoke the methodology-curator skill:

Use abstract:methodology-curator to surface proven methodologies before brainstorming.

This is especially valuable when:

  • Creating skills that teach techniques (debugging, testing, reviewing)
  • Building knowledge management features
  • Designing decision frameworks
  • The domain has recognized experts (most do!)

Phase 0.5: Brainstorming (Default)

After methodology curation (or if skipping it), refine the skill idea through collaborative dialogue.

Invoke the brainstorming skill:

Use superpowers:brainstorming to refine this skill idea before scaffolding.

Read the full file on GitHub · 494 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. yesterday First seen · 494 lines · 25 tokens per session scan A d1b0e0c53c1e

Subscribe to this mod's changes

create-skill is a command published in the GitHub repository athola/claude-night-market (332 stars, last pushed 5d ago), licensed MIT. It adds 25 tokens to every session and 3,003 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.