agentleFS
viknesh20-20viknesh20-20/claude-code-tool-kit/.claude/skills/write-skill/SKILL.md

write-skill

Skill7 starsChanged 6 months agoMITView on GitHub

Meta-skill that creates new Claude Code skills. Describe what you want the skill to do and this generates a complete SKILL.md with proper frontmatter, shell injection, structured instructions, and output format.

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use grill, write-docs and 6 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • renatorozasSkill

    grill

    Adversarial code review. Don't let me ship until the changes pass your scrutiny.

    Also in 5 projects that use this

  • SentrySkill

    write-docs

    Create or update documentation pages for the Abacus docs site. Use when adding new documentation, updating existing pages, or ensuring docs stay in sync with code changes. Ensures pages follow Starlight patterns and build correctly.

    Also in 3 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 4 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 4 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 5 projects that use this

  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Trigger: When should someone use it?

    line 22
  2. Distinctive:

    Create the file following this template:

    line 29
  3. Very specific:

    Check the generated SKILL.md against these requirements:

    line 66
  4. Distinctive:

    Follow existing skill patterns in this project

    line 95
  5. Very specific:

    Keep SKILL.md under 200 lines

    line 96
  6. Distinctive:

    Use shell injection for context detection, not hardcoded assumptions

    line 97

“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill Creator

Existing Skills (for pattern reference)

!ls .claude/skills/ 2>/dev/null


Process

Step 1: Gather Requirements

From the user's description, determine:

  1. Name: lowercase-with-hyphens, becomes the /slash-command
  2. Purpose: What does this skill do?
  3. Trigger: When should someone use it?
  4. Input: What arguments does it need?
  5. Output: What should it produce?
  6. Tools needed: Which Claude Code tools does it require?

Step 2: Generate SKILL.md

Create the file following this template:

---
name: skill-name
description: "One sentence: what it does + when to use it. Be specific enough for auto-invocation."
argument-hint: "[argument description]"
allowed-tools: Read, Grep, Glob
---

# Skill Title

## Context Detection
!`relevant shell command for auto-detecting project context`

---

## Instructions

### Step 1: [First action]
Detailed instructions for what Claude should do.

### Step 2: [Second action]
...

### Step N: [Final action]
...

## Output Format
Describe the expected structure of the output.

## Rules
- Rule 1
- Rule 2

Step 3: Validate the Skill

Check the generated SKILL.md against these requirements:

  • Frontmatter has name and description (required)
  • Description is under 150 characters and specific
  • allowed-tools lists only what's needed (principle of least privilege)
  • Shell injection uses !command`` syntax correctly
  • Instructions are numbered steps, not vague paragraphs
  • Output format is defined
  • Rules section exists with boundaries

Step 4: Save and Test

  1. Create directory: .claude/skills/<skill-name>/
  2. Save SKILL.md to that directory
  3. Instruct user to test: open Claude Code, type /<skill-name>

Frontmatter Reference

FieldRequiredDescription
nameYesSlash command name (lowercase, hyphens)
descriptionYesWhen to use (specific, <150 chars)
argument-hintNoAutocomplete hint, e.g. [filename]
allowed-toolsNoTools allowed without asking
disable-model-invocationNotrue = manual only
user-invocableNofalse = hidden from menu
modelNoOverride model
effortNolow, medium, high, max
contextNofork for subagent isolation

Rules

  • Follow existing skill patterns in this project
  • Keep SKILL.md under 200 lines
  • Use shell injection for context detection, not hardcoded assumptions
  • Description must be specific enough for Claude to auto-invoke correctly

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.