Use when creating a new skill from scratch, modifying an existing skill, or optimizing a skill's triggering description. Guides intent capture, structure, writing patterns, and progressive-disclosure organization so skills reliably trigger and stay maintainable. Trigger on phrases like "turn this into a skill", "write a skill for X", "improve this skill", "my skill isn't triggering".
SkillScore100Maintained
Automatic
◆AI Engineer pack
Last verified 8/15/2026
What it changes
Passed 21 of 21 test cases with the skill, and 10 of 21 without it.
Without skill45%
With skill100%
Checks it passed that the model alone missed
Sets the model frontmatter key to opus
Sets the model frontmatter key to haiku
Sets the model frontmatter key to sonnet
and 12 more in the full report
12 fixed10 passed either way0 still failing0 broke
Pass-rate lift
+55 pp
Tokens
+43%
Agent turns
0%
Response time
-33%
Model gemini-3.6-flashMeasured 8/15/2026v122 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 11
Prompt
We are creating a session-start skill that runs directly within the main coordinator agent's context and disables separate model invocation. What model setting belongs in its frontmatter?
What was checked, without and with the skill
Checked
Without skill
With skill
Sets the model frontmatter key to inherit
Missed
Passed
case-06 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md162 linessingle file
Skill Creator
A process skill for writing skills well.
Adapted from anthropics/skills/skill-creator — we keep the authoring workflow and progressive-disclosure guidance but drop the Python eval-viewer harness (not part of our stack).
The loop
Capture intent — what should the skill do? When should it trigger?
Draft SKILL.md with frontmatter + body
Test — 2–3 realistic prompts, see if Claude triggers + executes right
Improve based on failures (wrong trigger, wrong output, over-verbose, etc.)
Optimize description if triggering is unreliable
1. Capture Intent
If the user said "turn X into a skill", extract from conversation history: the tools used, the sequence of steps, corrections the user made, input/output formats observed. Confirm gaps before proceeding.
Ask explicitly:
What should this skill enable Claude to do?
When should it trigger? (user phrases / contexts)
What's the expected output format?
Does this skill have objectively verifiable outputs? (if yes, test cases help; if subjective like writing style / art, skip them)
2. Write the SKILL.md
Frontmatter
---
name: kebab-case-name
description: One or two sentences covering what it does AND when to trigger. Mention multiple trigger phrases/contexts (Claude tends to UNDER-trigger — err on "pushy").
---
Description anti-patterns:
❌ "How to build a dashboard." (no triggers)
✅ "Use when building a dashboard, visualizing data, or displaying metrics — trigger even if the user doesn't say 'dashboard' but mentions charts, KPIs, or metric displays."
Guide for creating effective skills, with structured workflows for capturing intent, drafting, testing, and iteratively improving skills. Use when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.