What makes Skill Creator Flagos notable?

1K downloads. Trust evidence available

How should Skill Creator Flagos be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Skill Creator Flagos

Create new skills, modify existing skills, and validate skill quality for the FlagOS skills repository. Use this skill whenever someone wants to create a ski... Skill: Skill Creator Flagos Owner: wbavon Summary: Create new skills, modify existing skills, and validate skill quality for the FlagOS skills repository. Use this skill whenever someone wants to create a ski... Tags: latest:1.1.0 Version history: v1.1.0 | 2026-05-19T07:04:37.931Z | user Sync from flagos-ai/skills latest v1.0.0 | 2026-03-23T04:33:27.581Z | auto skill-creator-flagos v1.0.0 - Initial release providing

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.1.0release · observed May 19, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s179mcxns07mhashdtzg4tbf6584wt8v:skill-creator-flagos

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-wbavon-skill-creator-flagos/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

112,334 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: skill-creator-flagos
description: >
Create new skills, modify existing skills, and validate skill quality for the FlagOS skills
repository. Use this skill whenever someone wants to create a skill from scratch, improve or
edit an existing skill, scaffold a new skill directory, validate skill structure, or run test
cases against a skill. Trigger when the user says things like "create a skill", "make a new
skill for X", "scaffold a skill", "improve this skill", "validate my skill", or simply
"/skill-creator-flagos". Also trigger when users mention turning a workflow into a reusable skill,
or want to package a repeated process as a skill.
argument-hint: "[skill-name] [--init | --validate | --eval]"
user-invokable: true
compatibility: "Python 3.8+, works with any AI coding assistant that supports the Agent Skills standard"
metadata:
version: "1.0.0"
author: flagos-ai
category: workflow-automation
tags: [skill-creation, scaffolding, validation, meta-skill, developer-tooling]
allowed-tools: "Bash(python3:*) Bash(python:*) Bash(chmod:*) Bash(mkdir:*) Bash(cp:*) Bash(ls:*) Bash(cat:*) Read Edit Write Glob Grep AskUserQuestion TaskCreate TaskUpdate TaskList TaskGet Agent"
---

# Skill Creator

A meta-skill for creating, improving, and validating skills in the FlagOS skills repository.

## Overview

This skill guides you through the full lifecycle of skill development:
1. **Create** — scaffold a new skill from template, interview the user, write SKILL.md
2. **Improve** — analyze an existing skill, identify weaknesses, iterate with test cases
3. **Validate** — check structure, frontmatter, references, and conventions compliance

## Usage

```
/skill-creator-flagos # Interactive — asks what you want to do
/skill-creator-flagosmy-new-skill --init # Scaffold a new skill
/skill-creator-flagosmy-skill --validate # Validate an existing skill
/skill-creator-flagosmy-skill --eval # Run test prompts against a skill
```

## Execution

### Step 0: Parse arguments and determine mode

Extract from user input:
- `{{skill_name}}` — optional skill name (hyphen-case)
- `{{mode}}` — one of: `create`, `improve`, `validate`, `eval`, or `interactive` (default)

If no mode is specified, ask the user:

> What would you like to do?
> 1. Create a new skill from scratch
> 2. Improve an existing skill
> 3. Validate a skill's structure and conventions
> 4. Run test cases against a skill

**-> Tell user**: Confirm the mode and skill name.

---

## Mode 1: Create a New Skill

### Step 1: Capture intent

Start by understanding what the user wants to build. If the current conversation already contains a workflow the user wants to capture (e.g., "turn this into a skill"), extract answers from the conversation history first.

Key questions to clarify:
1. What should this skill enable the agent to do?
2. When should this skill trigger? (user phrases, contexts, file types)
3. What's the expected output or end state?
4. Does the

README.md

# skill-creator-flagos: Skill Development Toolkit

[中文版](README_zh.md)

## Overview

`skill-creator-flagos` is a meta-skill for creating, improving, and validating skills in the FlagOS skills repository.

### Problem Statement

Writing a high-quality skill involves many details: YAML frontmatter conventions, trigger-optimized descriptions, progressive disclosure structure, proper file organization, bilingual documentation, and more. Manually checking all these requirements is tedious and error-prone, and new contributors often miss conventions that only become apparent after review.

This skill automates the entire skill development lifecycle: **scaffold from template -> write with guided patterns -> validate conventions -> iterate with test cases**, spanning 4 operational modes with built-in tooling for each stage.

### Usage

```bash
# Interactive — asks what you want to do
/skill-creator-flagos

# Scaffold a new skill
/skill-creator-flagos preflight-check --init

# Scaffold with specific resource directories
/skill-creator-flagos preflight-check --init --resources scripts,references

# Validate a single skill
/skill-creator-flagos model-migrate-flagos --validate

# Validate all skills
/skill-creator-flagos --validate

# Improve an existing skill
/skill-creator-flagos model-migrate-flagos

# Run test cases against a skill
/skill-creator-flagos model-migrate-flagos --eval
```

| Argument | Required | Default | Description |
|---|---|---|---|
| `skill-name` | No | — | Skill name in hyphen-case (e.g. `preflight-check`) |
| `--init` | No | — | Scaffold a new skill directory |
| `--validate` | No | — | Validate skill structure and conventions |
| `--eval` | No | — | Run test cases against the skill |
| `--resources` | No | — | Comma-separated resource dirs: `scripts,references,assets` |

When no flag is provided, the skill enters interactive mode and asks what you'd like to do.

---

## Four Operational Modes

### Mode 1: Create — Build a New Skill from Scratch

```
Intent capture → Interview → Scaffold → Write SKILL.md → Add resources → Validate → Write README
```

**What happens:**

1. **Intent capture** — The agent interviews you about what the skill should do, when it should trigger, what tools it needs, and what outputs it produces. If the current conversation already contains a workflow you want to capture, the agent extracts answers from context first.

2. **Scaffold** — Runs `init_skill.py` to generate the directory structure:
   ```
   my-skill/
   ├── SKILL.md        # Template with [TODO] placeholders
   ├── LICENSE.txt      # Apache 2.0
   ├── scripts/         # (if requested)
   ├── references/      # (if requested)
   └── assets/          # (if requested)
   ```

3. **Write SKILL.md** — Fills in the frontmatter and body following the patterns in `references/writing-guide.md`. The agent ensures:
   - Description is trigger-optimized (specific phrases, slightly "pushy")
   - Body includes all required sections (Overview, Steps, Examples,

_meta.json

{
  "ownerId": "kn7c1yzknmhkmxasrtdbxa3fhd81z80k",
  "slug": "skill-creator-flagos",
  "version": "1.1.0",
  "publishedAt": 1779174277931
}

references/schemas.md

# JSON Schemas

Defines the JSON schemas used by skill-creator for evaluation and testing.

---

## evals.json

Defines test cases for a skill. Located at `evals/evals.json` within the skill directory.

```json
{
  "skill_name": "example-skill",
  "evals": [
    {
      "id": 1,
      "prompt": "User's example prompt",
      "expected_output": "Description of expected result",
      "files": ["evals/files/sample1.txt"],
      "assertions": [
        "The output includes X",
        "Step Y was executed correctly",
        "No errors were reported"
      ]
    }
  ]
}
```

### Fields

| Field | Required | Description |
|-------|----------|-------------|
| `skill_name` | Yes | Must match the skill's frontmatter `name` |
| `evals[].id` | Yes | Unique integer identifier |
| `evals[].prompt` | Yes | The user prompt to test with |
| `evals[].expected_output` | Yes | Human-readable description of success |
| `evals[].files` | No | Input file paths relative to skill root |
| `evals[].assertions` | No | List of verifiable statements to check |

### Writing Good Test Prompts

- Use realistic language a real user would actually say
- Include both direct invocations (`/skill-name arg`) and natural language triggers
- Cover happy paths, edge cases, and error scenarios
- At least 2-3 test prompts per skill

### Writing Good Assertions

- Make assertions objectively verifiable (not subjective)
- Use descriptive text that reads clearly in reports
- Check both positive outcomes ("file was created") and negative ("no error messages")
- Don't assert on implementation details — focus on user-visible outcomes

---

## eval_result.json

Output from running evaluations. Located at `evals/results/eval_result.json`.

```json
{
  "skill_name": "example-skill",
  "timestamp": "2026-03-15T10:30:00Z",
  "results": [
    {
      "id": 1,
      "prompt": "User's example prompt",
      "assertions": [
        {
          "text": "The output includes X",
          "passed": true,
          "evidence": "Found X in the generated output at line 15"
        },
        {
          "text": "Step Y was executed correctly",
          "passed": false,
          "evidence": "Step Y was skipped due to missing dependency"
        }
      ],
      "summary": {
        "passed": 1,
        "failed": 1,
        "total": 2,
        "pass_rate": 0.5
      }
    }
  ],
  "overall": {
    "total_evals": 1,
    "total_assertions": 2,
    "total_passed": 1,
    "overall_pass_rate": 0.5
  }
}
```

---

## validation_result.json

Output from the validation script. Located at `evals/results/validation_result.json`.

```json
{
  "skill_name": "example-skill",
  "skill_path": "/path/to/skills/example-skill",
  "timestamp": "2026-03-15T10:30:00Z",
  "valid": true,
  "errors": [],
  "warnings": [
    "No README.md found (recommended)",
    "Script scripts/helper.py lacks execute permission"
  ],
  "checks": {
    "frontmatter": "pass",
    "name_convention": "pass",
    "description_quality": "pass",
    "

references/writing-guide.md

# Skill Writing Guide

Detailed patterns and best practices for writing effective skills in the FlagOS skills repository.

## Table of Contents

- [Anatomy of a Skill](#anatomy-of-a-skill)
- [Progressive Disclosure](#progressive-disclosure)
- [Writing the Description](#writing-the-description)
- [Structuring the Body](#structuring-the-body)
- [Writing Style](#writing-style)
- [Scripts and References](#scripts-and-references)
- [FlagOS-Specific Conventions](#flagos-specific-conventions)

---

## Anatomy of a Skill

```
skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter (name, description required)
│   └── Markdown instructions
├── LICENSE.txt (recommended, Apache 2.0)
├── README.md (recommended, English)
├── README_zh.md (optional, Chinese)
└── Bundled Resources (optional)
    ├── scripts/    - Executable code for deterministic/repetitive tasks
    ├── references/ - Docs loaded into context as needed
    └── assets/     - Files used in output (templates, icons, fonts)
```

### Required Fields

| Field | Constraints | Description |
|-------|-------------|-------------|
| `name` | ≤64 chars, lowercase + hyphens, matches directory | Unique identifier |
| `description` | ≤1024 chars | What the skill does AND when to trigger |

### FlagOS Extension Fields

| Field | Description | Example |
|-------|-------------|---------|
| `argument-hint` | CLI argument hint | `"model_name [options]"` |
| `user-invokable` | Can be invoked via `/skill-name` | `true` |
| `allowed-tools` | Fine-grained tool access control | `"Bash(python3:*) Read Edit ..."` |
| `compatibility` | Environment requirements | `"Python 3.8+, CUDA required"` |
| `metadata.version` | Skill version (semver) | `"1.0.0"` |
| `metadata.author` | Author | `"flagos-ai"` |
| `metadata.category` | Category | `"workflow-automation"` |
| `metadata.tags` | Tag list | `[model-migration, vllm]` |

---

## Progressive Disclosure

Skills use a three-level loading system to manage context efficiently:

1. **Metadata** (name + description) — Always in context (~100 words)
2. **SKILL.md body** — Loaded when skill triggers (<500 lines ideal)
3. **Bundled resources** — Loaded as needed (unlimited; scripts can execute without loading)

### Key Principles

- **Keep SKILL.md under 500 lines.** If approaching this limit, split content into `references/` files with clear pointers about when to read them.
- **Reference files must be documented in SKILL.md** with guidance on when to read them.
- **For reference files >300 lines**, include a table of contents at the top.
- **Avoid deeply nested references** — keep one level deep from SKILL.md.

### Patterns

**Pattern 1: Domain-specific organization**

When a skill supports multiple domains/frameworks, organize by variant:

```
cloud-deploy/
├── SKILL.md (workflow + selection)
└── references/
    ├── aws.md
    ├── gcp.md
    └── azure.md
```

The agent reads only the relevant reference file.

**Pattern 2: Workflow with reference catalog**

```
model-migrate-fl

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.