write-a-skill

write-a-skill is a skill for Claude Code from skilletmd/skillet. It costs 53 tokens per session (2,345 once invoked), scanned A, original, Apache-2.0.

A guide for creating or improving a SKILL.md file, the instruction file that tells an AI agent what a skill does and when to use it.

In plain words
What is it for?
Use it to define skill metadata, write trigger descriptions, limit tool access, and avoid common authoring mistakes.
Why use it?
It helps keep a skill focused and gives it a specific trigger, reducing vague descriptions and unwanted activation.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to define skill metadata, write trigger descriptions, limit tool access, and avoid common authoring mistakes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skilletmd/skillet/write-a-skill
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.

Any agent
npx skills add skilletmd/skillet --skill write-a-skill
Clone the repo
git clone --depth 1 https://github.com/skilletmd/skillet

Made for: Claude Code.

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 write-a-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/skilletmd/skillet/write-a-skill.svg)](https://agentmods.dev/skills/skilletmd/skillet/write-a-skill)
Your own site
<a href="https://agentmods.dev/skills/skilletmd/skillet/write-a-skill"><img src="https://agentmods.dev/badge/skills/skilletmd/skillet/write-a-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,345 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00053 $0.02345
Opus 5 $0.00026 $0.01172
Sonnet 5 $0.00011 $0.00469
Haiku 4.5 $0.00005 $0.00234

Measured 7d ago against content hash 31b32e64601e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

write-a-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 7d 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/write-a-skill/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

write-a-skill

A good SKILL.md does one thing well, triggers on the right moment, and stays scoped to what it actually knows. Most skill problems come from: vague trigger descriptions, scope creep, and missing the why.

The minimum viable skill

---
name: my-skill
description: "One sentence. What does this skill do and WHEN should the AI invoke it? Be specific."
---

# my-skill

Instructions for the AI go here.

That's it. Name, description, body. The description is the most important field — it's how the runtime decides whether to load this skill at all.

Frontmatter reference

---
name: my-skill                    # Required. Slug-format (lowercase, hyphens).

description: "..."                # Required. One sentence, specific trigger condition.
                                  # Bad:  "Helps with code."
                                  # Good: "Use when reviewing TypeScript PRs for type safety issues."

user-invocable: true              # Optional. Adds a /my-skill slash command.

allowed-tools: Bash(git *)        # Optional. Restricts which tools the skill can use.
                                  # Omit if the skill only generates text.
---

Writing the description field

The description does two jobs: it tells the runtime when to load the skill, and it tells the user what the skill does.

Bad descriptions (too vague — the runtime loads this for everything):

  • "Helps with tasks."
  • "Useful for developers."
  • "Context about my project."

Good descriptions (specific trigger condition + what it provides):

  • "Use when writing or reviewing commit messages to enforce conventional commit format."
  • "Contains my company's refund policy. Trigger when a user asks about returns, refunds, or billing disputes."
  • "Teaches the Skillet sync model. Trigger when someone asks how Skillet works, how to sync skills, or how to add a skill."

The pattern: "Use when [specific situation]. [What the skill provides or does.]"

Read the full file on GitHub · 229 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. 7d ago First seen · 229 lines · 53 tokens per session scan A 31b32e64601e

Subscribe to this mod's changes

write-a-skill is a skill published in the GitHub repository skilletmd/skillet (3 stars, last pushed 8d ago), licensed Apache-2.0. It adds 53 tokens to every session and 2,345 once invoked, about $0.0003 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.