skill-reviewer-proPerforms thorough format validation, content quality assessment, and functional verification of OpenClaw skills for compliance and completeness.
Install via ClawdBot CLI:
clawdbot install YKaiXu/skill-reviewer-proComprehensive skill review and validation for OpenClaw skills with scoring rubric, defect checklists, functional verification, optimization recommendations, and workflow validation.
IMPORTANT: Always respond in the same language as the user's request.
Auto-adapt to the user's language to ensure clear communication and better user experience.
package_skill.py validation passedStructure: โ Good (6/6)
Description: โ Strong (8/8)
Example Density: โ ๏ธ Low (1/3)
Organization: โ Good (6/6)
Actionability: โ Good (10/10)
Problem: Generated AGENTS.md template does not match OpenClaw specifications
Missing from templates.md AGENTS.md:
Impact: Skills created with agent-builder-plus will be missing critical OpenClaw agent behaviors.
Progressive Disclosure: โ Good (5/5)
Resource Organization: โ Good (5/5)
Triggering Accuracy: โ Good (5/5)
1. Fix AGENTS.md Template Functional Mismatch
Update references/templates.md to include all required sections from actual OpenClaw AGENTS.md.
2. Add More Concrete Examples
Add 3-5 concrete code examples in workflow sections.
3. Add Quick Start Section
Add a "Quick Start" section at the beginning of SKILL.md.
Note: This level applies to workflow tools (skills that guide users through multi-step processes).
WORKFLOW COMPLETENESS CHECK:
[ ] Each phase has clear operational steps
[ ] Correct CLI commands are used
[ ] Error handling is documented
[ ] Backup and recovery mechanisms exist
[ ] Verification steps are included
[ ] Configuration management is documented
[ ] Failure recovery strategies existagent-builder-plus Analysis:
| Check | Status | Issue |
|--------|---------|--------|
| Each phase has clear operational steps | โ ๏ธ Partial | Phase 2 only lists files, not creation commands |
| Correct CLI commands are used | โ Missing | No openclaw agents add command |
| Error handling is documented | โ Missing | No error handling in any phase |
| Backup and recovery mechanisms exist | โ Missing | No backup before config changes |
| Verification steps are included | โ Missing | No verification after agent registration |
| Configuration management is documented | โ Missing | No auth-profiles.json documentation |
| Failure recovery strategies exist | โ Missing | No recovery strategies for any phase |
Issue 1: Missing BOOTSTRAP.md in file list
BOOTSTRAP.md to Phase 2 file listIssue 2: No agent registration logic
openclaw agents add command documentedopenclaw agents add commandIssue 3: No auth-profiles.json documentation
Issue 4: No backup mechanism
Issue 5: No configuration verification
Issue 6: No directory creation robustness
mkdir -p with error checkingIssue 7: No automated testing (Phase 8)
Issue 8: No failure recovery strategies
Issue 9: Unclear Feishu binding method
Issue 10: Optional systemd heartbeat
SKILL REVIEW SCORECARD
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
Skill: agent-builder-plus
Reviewer: ๅคง้ฑผ
Date: 2026-02-27
Category Score Max
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
Level 1: Format 10 10 โ
Level 2: Writing
- Structure 6 6 โ
- Description 8 8 โ
- Example density 1 3 โ ๏ธ
- Organization 6 6 โ
- Actionability 10 10 โ
Level 3: Functional 0 20 โ CRITICAL
Level 4: Best Practices
- Progressive 5 5 โ
- Resources 5 5 โ
- Triggering 5 5 โ
Level 5: Optimization 0 10 (recommendations provided)
)
Level 6: Workflow 0 20 โ CRITICAL
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
TOTAL 56 116
RATING: 56/116 = Fair โ significant gaps to address
VERDICT: REWORK (functional and workflow verification failed)1. Functional Mismatch: AGENTS.md template missing critical OpenClaw specifications.
2. Workflow Incomplete: Missing agent registration, configuration verification, backup mechanisms, error handling, and failure recovery strategies.
openclaw agents add)Run automatic validation using package_skill.py:
python3 /home/yupeng/.npm-global/lib/node_modules/openclaw/skills/skill-creator/scripts/package_skill.py <skill-path>Check structure, description, examples, organization, and actionability.
For OpenClaw skills, compare generated templates with actual specifications.
Verify progressive disclosure, resource organization, and triggering accuracy.
Provide prioritized recommendations (Critical/Major/Minor).
WORKFLOW COMPLETENESS CHECK:
[ ] Each phase has clear operational steps
[ ] Correct CLI commands are used
[ ] Error handling is documented
[ ] Backup and recovery mechanisms exist
[ ] Verification steps are included
[ ] Configuration management is documented
[ ] Failure recovery strategies existFor each phase in the workflow:
PHASE VALIDATION CHECKLIST:
Phase: [phase name]
Operational Steps:
[ ] Clear, step-by-step instructions provided
[ ] Commands are accurate and complete
[ ] Required parameters are specified
Error Handling:
[ ] Common errors are documented
[ ] Recovery steps are provided
[ ] Error messages are explained
Verification:
[ ] Success criteria are defined
[ ] Verification steps are included
[ ] How to confirm completion is explained
Dependencies:
[ ] Prerequisites are listed
[ ] Order dependencies are clear
[ ] Previous phase completion is verifiedFor workflow tools that use OpenClaw CLI commands:
CLI COMMAND VALIDATION:
[ ] Commands are verified with `openclaw <command> --help`
[ ] Command syntax is correct
[ ] Required options are documented
[ ] Default values are explained
[ ] Example commands are runnableFor tools that modify OpenClaw configuration:
CONFIGURATION MANAGEMENT CHECK:
[ ] Files being modified are listed
[ ] Backup mechanism is provided
[ ] Rollback steps are documented
[ ] Configuration validation is included
[ ] Authentication requirements are explainedCRITICAL: Always respond in the same language as the user's request.
Scenario 1: User asks in Chinese
User: ่ฏทๅฎกๆฅไธไธ agent-builder-plus ่ฟไธช skill
AI: (responds in Chinese)
## ๅฎกๆฅ็ปๆ๏ผagent-builder-plus
...Scenario 2: User asks in English
User: Please review the agent-builder-plus skill
AI: (responds in English)
## Review Results: agent-builder-plus
...Scenario 3: User asks in mixed language
User: ่ฏทๅฎกๆฅ agent-builder-plus skill
AI: (responds in Chinese, as the primary language is Chinese)
## ๅฎกๆฅ็ปๆ๏ผagent-builder-plus
...Keep technical terms in English when appropriate:
But translate descriptions, feedback, and explanations to the user's language.
Generated Mar 1, 2026
An agency that builds and deploys custom OpenClaw agents for clients across various industries. They use Skill Reviewer Pro to audit all skill packages before integration to ensure quality and compliance with OpenClaw specifications, reducing development errors and client support issues.
A large corporation's internal team responsible for overseeing AI tool deployment. They utilize Skill Reviewer Pro to validate downloaded or internally developed skills, ensuring they meet functional and security standards before rollout to departments like HR or IT.
A maintainer of an open-source repository for OpenClaw skills. They employ Skill Reviewer Pro to review community contributions, checking format, writing quality, and functional verification to maintain high code quality and prevent integration failures in the project.
An instructor teaching students how to build AI agents using OpenClaw. They use Skill Reviewer Pro during workshops to provide structured feedback on student-created skills, helping learners improve their coding and documentation practices through multi-level reviews.
A consultant who helps small businesses implement AI solutions. They rely on Skill Reviewer Pro to audit existing skill packages for clients, identifying defects and optimization opportunities to enhance agent performance and reliability in operational workflows.
Offer Skill Reviewer Pro as a cloud service with monthly or annual subscriptions. Users pay for access to automated skill audits, detailed reports, and optimization recommendations, targeting developers and teams needing continuous quality assurance.
Provide Skill Reviewer Pro functionality via an API where customers are charged per review request. This model suits occasional users or integrators who want to embed skill validation into their own tools without a full subscription.
Sell annual enterprise licenses to large organizations for unlimited use of Skill Reviewer Pro. Includes premium support, custom integrations, and advanced features like workflow validation for complex agent deployments.
๐ฌ Integration Tip
Integrate Skill Reviewer Pro into CI/CD pipelines to automatically validate skill packages during development, catching issues early and ensuring compliance with OpenClaw standards before deployment.
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack ๐ฆ
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features
Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.
OpenClaw CLI wrapper โ gateway, channels, models, agents, nodes, browser, memory, security, automation.
MoltGuard โ runtime security plugin for OpenClaw agents by OpenGuardrails. Helps users install, register, activate, and check the status of MoltGuard. Use wh...