← 返回 Skills 市场

ClawHub Publish Workflow

Name: ClawHub Publish Workflow
Author: kofna3369

作者 Kofna3369 · GitHub ↗ · v1.3.0 · MIT-0

cross-platform ⚠ suspicious

总下载

当前安装

版本数

在 OpenClaw 中安装

/install clawhub-publish-workflow

功能描述

Complete workflow for publishing skills to ClawHub. Use when: (1) creating a new skill to publish, (2) evaluating and improving a skill with dual evaluation...

使用说明 (SKILL.md)

CLAWHUB PUBLISH WORKFLOW 📦

Complete workflow for publishing skills to ClawHub

Info	Value
Version	1.3.0 — 2026-05-07
Status	OPERATIONAL

1. PURPOSE AND SCOPE

Objective

Provide a complete workflow for any OpenClaw agent to publish skills to ClawHub using dual evaluation systems.

Universal Design

Works for ANY OpenClaw agent, regardless of cluster or environment.

When to Use

Trigger	Action
Creating a new skill to publish	Follow this workflow
Need to evaluate and improve	Use bundled dual evaluator
Publishing to ClawHub	Follow all steps
Fixing a failed evaluation	Run evaluation + fix

2. BUNDLED TOOLS

File	System	Purpose
`evaluator.py`	5-Dimension	Colorful 5-dimension evaluation
`eval-skill.py`	ISO 25010	Automated structural checks (13 tests)
`references/tools.md`	—	Complete tools reference

Dual Evaluation System

┌─────────────────────────────────────────────┐
│         CLAWHUB PUBLISH WORKFLOW            │
├─────────────────────────────────────────────┤
│  1. eval-skill.py (ISO 25010)              │
│     → Automated checks (13 tests)          │
│     → Target: 90%+ structural score         │
│                                             │
│  2. evaluator.py (5-Dimension)              │
│     → 5 dimensions × 20% = 100              │
│     → Target: 70+ score                     │
│                                             │
│  3. Manual (25 criteria)                   │
│     → ISO 25010 rubric (8 categories)       │
│     → Target: 80+ score                     │
└─────────────────────────────────────────────┘

3. COMPLETE WORKFLOW

Step 1: Create SKILL.md

TASKS:
1. Create SKILL.md in English (impersonal, universal)
2. Include frontmatter with name + description
3. Follow standard skill structure
4. Make it addressable to ANY agent

Frontmatter Template:

---
name: skill-name
description: "Skill description. Use when: (1) trigger1, (2) trigger2, (3) trigger3. Provides X, Y, Z."
---

Step 2: Automated ISO 25010 Checks

# Run automated structural checks
python3 eval-skill.py \x3Cskill-path> --verbose

# Target: 90%+ (12+/13 checks passed)

Step 3: 5-Dimension Evaluation

# Run full 5-dimension evaluation
python3 evaluator.py \x3Cskill-path> --verbose --improve

# Target: 70+ score

Step 4: Manual 25-Criteria Assessment

Score using the rubric:

Category	Max	Score
Functional Suitability	/12
Reliability	/12
Performance	/8
Usability (AI)	/12
Usability (Human)	/8
Security	/12
Maintainability	/12
Agent-Specific	/24
TOTAL	/100

Step 5: Fix Issues

Low Score Area	Fix
Structure \x3C15	Add missing sections, formatting
Clarity \x3C15	Add examples, commands, constraints
Completeness \x3C15	Add tools, prerequisites, errors
Consistency \x3C15	Add style markers, naming consistency
Functionality \x3C15	Fix command syntax

Step 6: Re-evaluate

# Continue until targets met
python3 eval-skill.py \x3Cpath> --verbose  # Target: 90%+
python3 evaluator.py \x3Cpath> --verbose    # Target: 70+

Step 7: Publish

# Login
clawhub login --token \x3Ctoken> --no-browser

# Check slug availability
clawhub inspect \x3Cslug> 2>&1

# Publish
clawhub publish \x3Cpath> \
  --slug \x3Cslug> \
  --name "\x3CName>" \
  --version 1.0.0 \
  --changelog "\x3Cchanges>"

Step 8: Verify

clawhub inspect \x3Cslug>

4. EVALUATION TARGETS

System	Metric	Target	Command
ISO 25010	Structural	90%+	`eval-skill.py --verbose`
5-Dimension	Score	70+	`evaluator.py --verbose`
Manual	25-Criteria	80+	Rubric scoring

5. COMMON ISSUES

"Slug already taken"

→ Use alternative: yourname-\x3Cskill-name>

"API token invalid"

→ Get new at https://clawhub.com/settings/tokens

"Name mismatch"

→ Rename directory to match frontmatter name:

Score \x3C 70 after fixes

→ Focus on lowest scoring dimensions first

6. EDGE CASES

Case	Solution
No frontmatter	Add `---` at start with name + description
Missing tools section	Document all required tools
No examples	Add at least 2 concrete examples
Very long SKILL.md	Split into references/ if needed
Empty scripts dir	Remove empty directories

7. SKILL STRUCTURE TEMPLATE

---
name: skill-name
description: "Skill description. Use when: (1) trigger1, (2) trigger2."
---

# SKILL NAME

## 1. PURPOSE AND SCOPE

## 2. BUNDLED TOOLS

## 3. PREREQUISITES

## 4. USAGE
```bash
# Commands here

5. EXAMPLES

6. CONSTRAINTS

7. ERROR HANDLING

8. EDGE CASES


---

_In Altum Per Partage._
📦 ClawHub Publish Workflow v1.3

安全使用建议

Install only if you are comfortable using it with a ClawHub publishing token. Do not store the token in memory/credentials.md unless you have confirmed that file is private and excluded from future agent context; prefer a secret manager, environment variable, or official CLI credential storage. Before publishing, verify the package contents, slug, account, and version, and review the full bundled Python scripts and npm package source/version before running them.

功能分析

Type: OpenClaw Skill Name: clawhub-publish-workflow Version: 1.3.0 The bundle provides a legitimate workflow and static analysis tools (evaluator.py and eval-skill.py) designed to validate OpenClaw skills against structural and quality standards. The Python scripts perform heuristic checks using regex and AST parsing to identify missing documentation, syntax errors, and hardcoded secrets (as a security audit feature). No evidence of malicious execution, data exfiltration, or harmful prompt injection was found; the tools are strictly diagnostic and aligned with the stated purpose of skill publication and quality assurance.

能力标签

requires-sensitive-credentials

能力评估

ℹ Purpose & Capability

The stated purpose—evaluate and publish OpenClaw skills to ClawHub—matches the documented evaluator scripts and ClawHub CLI commands, but publishing is account-backed and can create public changes.

ℹ Instruction Scope

The commands are presented as user-directed workflow steps, including login, inspect, and publish. They are purpose-aligned, but the artifacts do not explicitly require a final user confirmation before publishing.

ℹ Install Mechanism

Registry metadata says there is no install spec, while the reference docs instruct installing the ClawHub CLI globally with npm and running bundled Python scripts. This is purpose-aligned but under-declared.

ℹ Credentials

The skill claims universal use, but the bundled evaluator and references include environment-specific Morgana/Ezekiel/Merlin paths, which may confuse users outside that setup.

⚠ Persistence & Privilege

The references recommend persistent storage of a ClawHub API token in memory/credentials.md without clear permissions, retention, or reuse boundaries.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install clawhub-publish-workflow
安装完成后，直接呼叫该 Skill 的名称或使用 /clawhub-publish-workflow 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.3.0

v1.3: Fully impersonal. Dual evaluation (5-dim + ISO 25010). 100% structural score. Added edge cases, backup/restore commands.

v1.2.0

v1.2: Dual evaluation system integrated (Axioma 5-dim + ISO 25010). 100% structural score. Added complete workflow diagram, 25-criteria template, edge cases section.

v1.1.0

Added eval-skill.py automated checks. Merged with Axioma Skill Evaluator v2.0. 100% structural score. Now includes 25-criteria rubric.

v1.0.1

Bundled SKILL_EVALUATOR.py included + tools reference. Now any agent can evaluate skills offline.

v1.0.0

Complete workflow for publishing skills to ClawHub. For any OpenClaw agent who wants to share their skills with the community.

元数据

Slug clawhub-publish-workflow

版本 1.3.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 5

常见问题