Skip to content
Skills Library
AI & agents · Building & coding

skill-creator

/skill-creator

Interactive guide for creating new Skills 2.0-compliant skills. Use when user asks to "create a new skill", "build a skill for X", "add a skill to the workflow", or "teach Claude how to do Y consistently". Walks through use case definition, frontmatter generation, instruction writing, evals creation, and validation against Skills 2.0 standard.

Repository
Synapse ↗
Licence
AGPL-3.0
Last repository change
15.09.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
4
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 15.09.2026, without references to retired models or APIs.

Licence

AGPL-3.0, copyleft: przeróbki udostępniane innym muszą mieć tę samą licencję.

What it does and when to use it

Interactive guide for creating new Skills 2.0-compliant skills. Use when user asks to "create a new skill", "build a skill for X", "add a skill to the workflow", or "teach Claude how to do Y consistently". Walks through use case definition, frontmatter generation, instruction writing, evals creation, and validation against Skills 2.0 standard.

Triggers from the description

create a new skillbuild a skill for Xadd a skill to the workflowteach Claude how to do Y consistently

Arguments

/skill-creator descrivi il workflow che vuoi insegnare a Claude
Original author description

Interactive guide for creating new Skills 2.0-compliant skills. Use when user asks to "create a new skill", "build a skill for X", "add a skill to the workflow", or "teach Claude how to do Y consistently". Walks through use case definition, frontmatter generation, instruction writing, evals creation, and validation against Skills 2.0 standard.

How it works

  1. Overview
  2. Process
  3. Examples
  4. Troubleshooting
Original SKILL.md headings · 189 lines, 684 words
SKILL.md preview
---
name: skill-creator
description: >
  Interactive guide for creating new Skills 2.0-compliant skills.
  Use when user asks to "create a new skill", "build a skill for X",
  "add a skill to the workflow", or "teach Claude how to do Y consistently".
  Walks through use case definition, frontmatter generation, instruction writing,
  evals creation, and validation against Skills 2.0 standard.
version: 1.0.0
user-invocable: true
argument-hint: "descrivi il workflow che vuoi insegnare a Claude"
allowed-tools: ["read", "write", "bash", "glob"]
---

# Skill Creator 2.0

Guide interattiva per creare skill conformi allo standard Skills 2.0.

## Overview

Crea skill che si attivano al momento giusto, insegnano workflow specifici, e si testano automaticamente con evals.

**Core principle:** Una buona skill è specifica, testabile, e segue progressive disclosure.

## Process

### Step 1: Define Use Cases

Prima di scrivere qualsiasi codice, identifica 2-3 casi d'uso concreti:

```
Use Case: [nome]
Trigger: Quando l'utente dice "[frase]" o "[frase alternativa]"
Steps:
1. [step 1]
2. [step 2]
Result: [output atteso]
```

Chiedi all'utente:
- Qual è il workflow ripetitivo che vuoi automatizzare?
- Quali frasi usano tipicamente per chiederlo?
- Qual è il risultato atteso?

### Step 2: Generate Frontmatter

Genera il frontmatter YAML con tutti i campi 2.0 appropriati:

```yaml
---
name: [kebab-case-name]
description: >
  [Cosa fa la skill — 1 frase].
  Use when [trigger condition 1].
  Use when user asks to "[phrase 1]", "[phrase 2]".
version: 1.0.0
[user-invocable: true]  # se ha senso come slash command
[argument-hint: "..."]  # se user-invocable
[allowed-tools: [...]]  # se vuoi restringere i tool
[context: "bash scripts/load_context.sh"]  # se serve context injection
---
```

**Regole nome:**
- kebab-case: `my-skill-name`
- No spazi, no maiuscole, no underscore
- No "claude" o "anthropic" nel nome

**Description ottimale:**
- Include COSA fa + QUANDO usarla (trigger phrases)
- Max 1024 chars
- No XML tags, no `<` `>`

### Step 3: Write Instructions

Struttura raccomandata per il body:

```markdown
# Nome Skill

## Overview
Descrizione breve. Core principle in 1-2 frasi.

## When to Use
- Caso d'uso principale
- Caso d'uso secondario
- Non usare quando: [condizioni]

## Instructions

### Step 1: [Primo step]
Istruzione chiara e specifica.

### Step 2: [Secondo step]
...

## Examples

### Example 1: [Scenario tipico]
User: "..."
Azione: [cosa fa la skill]
Output: [risultato]

## Troubleshooting

### La skill non si attiva
Causa: Trigger phrases troppo generiche
Soluzione: Aggiungere frasi più specifiche nella description
```

**Best practices Skills 2.0:**
- Framing positivo (no NEVER/ALWAYS/DO NOT eccessivi)
- No XML tags nel body
- Progressive disclosure: frontmatter → body → references/

### Step 4: Create Directory Structure

```bash
mkdir -p skill-name/scripts
mkdir -p skill-name/references
mkdir -p skill-name/evals
```

### Step 5: Create Evals

Per ogni skill, creare:

**evals/trigger_evals.json:**
```json
{
  "skill": "skill-name",
  "should_trigger": ["query 1", "query 2", "query 3"],
  "should_not_trigger": ["irrelevant query 1", "irrelevant query 2"]
}
```

**evals/evals.json:**
```json
{
  "skill": "skill-name",
  "version": "1.0.0",
  "test_cases": [
    {
      "id": "basic",
      "input": "typical user request",
      "expected_output_contains": ["keyword1"],
      "expected_output_excludes": ["anti-pattern"]
    }
  ]
}
```

### Step 6: Validate

Checklist finale:

- [ ] `name` in kebab-case
- [ ] `description` include trigger phrases
- [ ] `version` presente
- [ ] Nessun XML tag nel body
- [ ] Sezione `## Examples` presente
- [ ] Sezione `## Troubleshooting` presente
- [ ] `evals/trigger_evals.json` con 5+ test
- [ ] `evals/evals.json` con 3+ test
- [ ] Se slash command: `user-invocable: true` + `argument-hint`

## Examples

### Example 1: Creare una skill per code review

User: "Crea una skill per fare code review del nostro stile"

Skill creator:
1. Chiede: quali pattern volete verificare? (naming, patterns, no-any, ecc.)
2. Genera frontmatter con trigger phrases come "review my code", "check this PR"
3. Scrive istruzioni con checklist specifica per il vostro stile
4. Crea evals con query tipo "Can you review this component?"

### Example 2: Skill per workflow n8n

User: "Voglio una skill che mi aiuti a creare workflow n8n"

Skill creator:
1. Chiede: quali tipi di workflow? (webhook, cron, data sync)
2. Genera trigger phrases: "create an n8n workflow", "automate this with n8n"
3. Scrive istruzioni che seguono best practice n8n
4. Crea evals con scenari concreti

## Troubleshooting

### La skill è troppo generica e si attiva sempre
Causa: Description troppo vaga
Soluzione: Aggiungere trigger phrases specifiche e negative examples negli evals

### La skill non si attiva mai
Causa: Trigger phrases troppo tecniche o rare
Soluzione: Usare il linguaggio naturale dell'utente nella description

### YAML syntax error al caricamento
Causa: Caratteri speciali (< > :) nella description senza quotes
Soluzione: Wrappare description in `>` block scalar o quotes
Files in this package (4)
  • SKILL.md 5 KB
  • learnings.md 1 KB
  • evals/evals.json 1 KB
  • evals/trigger_evals.json 1 KB

Versions

RepositoryScoreLicence
This page · PIXARTSeu/Synapse100AGPL-3.0
opencue/cuecards100MIT
zzusp/night-bot100MIT
gonzalezpazmonica/savia100MIT
iuliandita/skills100MIT
langfuse/langfuse100MIT
seaworld008/commonly-used-high-value-skills100MIT
dfinity/icskills100Apache-2.0
LumenJSN/Aris100Apache-2.0

Database snapshot: 13.11.2026 · package version a37b1888b527 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100skill-writer
    Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
  • 100skill-writer
    Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
  • 100skill-creation-guide
    Step-by-step guide for creating Claude Skills in SKILL.md format. ALWAYS use this skill when user wants to create a new skill, write a SKILL.md file, package a .skill file, add instructions as a skill, or asks how to structure skill instructions. Also triggers for: створити…
  • 95writing-skills
    Use when creating new skills, editing existing skills, or verifying skills work before deployment
  • 100sciagent-skill-creator
    Scaffold a new SciAgent-Skills entry. Picks pipeline/toolkit/database/guide template, creates skills/{category}/{name}/SKILL.md with valid frontmatter, appends the registry.yaml entry, runs validation. Enforces name uniqueness, kebab-case, description keyword rules, schema rules…
  • 95skill-creator-ms
    Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.