Skip to content
Agentmart
Submit a tool

skill-authoring

Use when creating, editing, auditing, or validating Agent Skills.

Skill by ntk148v

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying skill-authoring?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ntk148v-skill-authoring

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when creating, editing, auditing, or validating Agent Skills. Covers TDD-based creation and specification compliance auditing.

Use cases: testing, security, writing, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/skill-authoring

What's inside

Skill name
skill-authoring
Description
Use when creating, editing, auditing, or validating Agent Skills. Covers TDD-based creation and specification compliance auditing.
License
MIT
Instructions
74 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Skill Authoring

## Overview

Skill Authoring is the complete lifecycle of creating and maintaining high-quality Agent Skills. It combines Test-Driven Development (TDD) for creation with rigorous auditing for specification compliance and quality.

**Core principle:** If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.

## When to Use

- Creating new Agent Skills
- Editing or refactoring existing skills
- Auditing skills for duplicates or spec violations
- Verifying skills work before deployment

---

## 1. Creation (TDD for Skills)

Writing skills is TDD applied to process documentation.

| TDD Concept  | Skill Creation                                                               |
| :----------- | :--------------------------------------------------------------------------- |
| **RED**      | Run baseline scenario WITHOUT skill. Document exact failure/rationalization. |
| **GREEN**    | Write minimal skill addressing those specific violations. Watch it pass.     |
| **REFACTOR** | Close loopholes and consolidate logic while maintaining compliance.          |

### The Iron Law

**NO SKILL WITHOUT A FAILING TEST FIRST.** Delete any untested skill code.

---

## 2. Auditing & Compliance

Maintain a clean, efficient library by identifying redundant skills and specification violations.

### Specification Requirements

- **YAML Frontmatter**: `name` (kebab-case, max 64 chars) and `description` (max 1024 chars).
- **Description**: Must start with "Use when..." and describe triggers, not workflow.
- **Structure**: Required `## Overview` and `## When to Use` sections.
- **Directory**: Directory name must match the skill name in frontmatter.

### Duplicate Detection

Skills are duplicates if they share the **same name**, **same purpose**, or **overlapping functionality**.

- **Resolution**: Keep the highest quality version, merge unique improvements, and remove inferior versions.

---

## 3. Implementation Checklist

- [ ] **RED**: Baseline failure documented?
- [ ] **Frontmatter**: Valid `name` and `description`?
- [ ] **Triggers**: Description uses "Use when..."?
- [ ] **Discovery**: Keywords included for search?
- [ ] **Efficiency**: Under 500 words (200 for frequent skills)?
- [ ] **Verification**: Pass scenario WITH skill?
- [ ] **Audit**: No duplicates or spec violations?

## Quick Reference: Validating a Skill

```bash
# Check name matches directory
name=$(grep "^name:" SKILL.md | cut -d' ' -f2)
[ "$name" == "$(basename $PWD)" ] || echo "Error: Name mismatch"

# Check for required sections
grep -q "^## Overview" SKILL.md && grep -q "^## When to Use" SKILL.md || echo "Error: Missing sections"
```

From ntk148v/skills, MIT.

More from ntk148v/skills

Signals

Stars
1
Forks
1
Open issues
0
Last commit (this folder)
May 19, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ntk148v

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get skill-authoring running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying skill-authoring?

CallGet help
Cite this page

skill-authoring. Agent Mart. https://agentmart.dev/skills/ntk148v-skill-authoring (last updated 2026-10-24)