Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub ยท Developer Tools
Skill Reviewer Pro
Performs thorough format validation, content quality assessment, and functional verification of OpenClaw skills for compliance and completeness.
skill openclawclawhub Free
Performs thorough format validation, content quality assessment, and functional verification of OpenClaw skills for compliance and completeness.
โฌ 0 downloads โ
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, _meta.json
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 2.1.1
Provenance
- Publisher
- YKaiXu
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Skill Reviewer Pro
Comprehensive skill review and validation for OpenClaw skills with scoring rubric, defect checklists, functional verification, optimization recommendations, and workflow validation.
Language Adaptation
IMPORTANT: Always respond in the same language as the user's request. If user asks in Chinese โ respond in Chinese If user asks in English โ respond in English If user asks in other languages โ respond in that language Auto-adapt to the user's language to ensure clear communication and better user experience.
Level 1: Format Validation โ
package_skill.py validation passed YAML frontmatter valid File structure correct
Level 2: Writing Quality Assessment
Structure: โ Good (6/6) Clear frontmatter with name and description Well-organized body with workflow sections Progressive disclosure pattern used Description: โ Strong (8/8) Starts with what skill does: "Build high-performing OpenClaw agents end-to-end." Includes trigger: "Use when you want to design a new agent..." Specific scope: mentions SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md Reasonable length Contains searchable keywords Example Density: โ ๏ธ Low (1/3) SKILL.md has few code blocks Could benefit from more concrete examples Organization: โ Good (6/6) Organized by workflow (Phase 1 โ Phase 2 โ Phase 3 โ Phase 4) Logical flow from interview to generation to validation Sections are self-contained Actionability: โ Good (10/10) Instructions are imperative Steps are ordered logically Guardrails checklist provided Acceptance tests included
Level 3: Functional Verification โ CRITICAL (0/20)
Problem: Generated AGENTS.md template does not match OpenClaw specifications Missing from templates.md AGENTS.md: Session startup requirements (Read SOUL.md, USER.md, memory files) Memory workflow details (daily notes vs long-term) Group chat behavior guidelines (when to speak, when to stay silent) Heartbeat mechanism details (heartbeat vs cron, what to check) Tool usage guidelines (Skills provide tools, Voice storytelling, Platform formatting) Impact: Skills created with agent-builder-plus will be missing critical OpenClaw agent behaviors.
Level 4: Best Practices Check โ Good (15/15)
Progressive Disclosure: โ Good (5/5) SKILL.md is concise Detailed information in references/ References properly linked Resource Organization: โ Good (5/5) Only necessary directories created No extraneous files Triggering Accuracy: โ Good (5/5) Description clearly states when to use No "When to Use This Skill" in body
Level 5: Optimization Recommendations
๐ด Critical (Must Fix) 1. Fix AGENTS.md Template Functional Mismatch Update references/templates.md to include all required sections from actual OpenClaw AGENTS.md. ๐ก Major (Should Fix) 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.
Level 6: Workflow Validation โ CRITICAL (0/20)
Note: This level applies to workflow tools (skills that guide users through multi-step processes). Workflow Completeness Check 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 exist agent-builder-plus Analysis: CheckStatusIssueEach phase has clear operational stepsโ ๏ธ PartialPhase 2 only lists files, not creation commandsCorrect CLI commands are usedโ MissingNo openclaw agents add commandError handling is documentedโ MissingNo error handling in any phaseBackup and recovery mechanisms existโ MissingNo backup before config changesVerification steps are includedโ MissingNo verification after agent registrationConfiguration management is documentedโ MissingNo auth-profiles.json documentationFailure recovery strategies existโ MissingNo recovery strategies for any phase Detailed Issues Issue 1: Missing BOOTSTRAP.md in file list Phase: Phase 2 Problem: BOOTSTRAP.md is mentioned in AGENTS.md specs but not in file list Impact: New agents lack first-run guidance Fix: Add BOOTSTRAP.md to Phase 2 file list Issue 2: No agent registration logic Phase: Missing Problem: No openclaw agents add command documented Impact: Users must manually configure openclaw.json Fix: Add Phase 2.5 with openclaw agents add command Issue 3: No auth-profiles.json documentation Phase: Missing Problem: No authentication configuration documentation Impact: Agents cannot access external services (e.g., Feishu) Fix: Add authentication section after Phase 2.5 Issue 4: No backup mechanism Phase: Missing Problem: No backup before modifying openclaw.json Impact: Config errors can break entire OpenClaw system Fix: Add backup step before Phase 2.5 Issue 5: No configuration verification Phase: Missing Problem: No verification after agent registration Impact: Agent may not start correctly Fix: Add Phase 2.6 with verification steps Issue 6: No directory creation robustness Phase: Phase 2 Problem: No error handling for directory creation Impact: File writes fail silently if directory creation fails Fix: Add mkdir -p with error checking Issue 7: No automated testing (Phase 8) Phase: Missing Problem: Only Phase 4 (acceptance tests), no automated testing Impact: No complete testing workflow Fix: Add Phase 8 with automated test commands Issue 8: No failure recovery strategies Phase: All phases Problem: No recovery strategies for any phase Impact: Users don't know how to recover from failures Fix: Add failure recovery section to each phase Issue 9: Unclear Feishu binding method Phase: Phase 1 Problem: Question 2 asks "Which channels?" but doesn't clarify Feishu binding Impact: Users unclear about channel binding vs /agentname command Fix: Clarify Feishu binding options in Phase 1 Issue 10: Optional systemd heartbeat Phase: Optional Problem: No systemd service configuration option Impact: Cannot run agent as systemd service Fix: Add optional systemd service configuration
Score Summary
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)
Top Defects
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.
Recommendation
Update references/templates.md AGENTS.md template with all required sections Add Phase 2.5 (agent registration with openclaw agents add) Add Phase 2.6 (configuration verification) Add backup mechanism before config changes Add failure recovery strategies to each phase Add directory creation error handling Add Phase 8 (automated testing) Clarify Feishu binding options in Phase 1 Add optional systemd service configuration
Level 1: Format Validation
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>
Level 2: Writing Quality Assessment
Check structure, description, examples, organization, and actionability.
Level 3: Functional Verification
For OpenClaw skills, compare generated templates with actual specifications.
Level 4: Best Practices Check
Verify progressive disclosure, resource organization, and triggering accuracy.
Level 5: Optimization Recommendations
Provide prioritized recommendations (Critical/Major/Minor).
Level 6: Workflow Validation (For Workflow Tools)
Workflow Completeness Check 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 exist Phase-by-Phase Validation For 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 verified CLI Command Validation For 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 runnable Configuration Management For 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 explained
Critical
Invalid frontmatter Broken code examples Misleading description Functional mismatch (OpenClaw skills) Workflow incomplete (missing phases, no CLI commands) No backup before config changes
Major
No "When to Use" information Text walls without examples Examples missing language tags Abstract organization Duplication between SKILL.md and references No error handling No verification steps No failure recovery strategies
Minor
Placeholder values Inconsistent formatting Extraneous files Missing cross-references No quick start guide
Language Adaptation Guidelines
CRITICAL: Always respond in the same language as the user's request.
Detection Rules
Detect user language from the request message Check the language of the user's input message Use the same language for all responses Language mapping Chinese (ไธญๆ/ๆฑ่ฏญ) โ Respond in Chinese English โ Respond in English Japanese (ๆฅๆฌ่ช) โ Respond in Japanese Korean (ํ๊ตญ์ด) โ Respond in Korean Other languages โ Respond in the detected language Consistency Once language is detected, use it for the entire review All section headers, descriptions, and feedback should be in the same language Technical terms (like "Level 1", "Level 2") can remain in English if they are standard terminology
Example Scenarios
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 ...
Implementation Notes
Language detection should be done at the start of the review Use simple language detection (check for Chinese characters, etc.) If language cannot be detected, default to the language of the previous interaction Maintain language consistency throughout the entire review process
Technical Terms
Keep technical terms in English when appropriate: Skill names (e.g., "agent-builder-plus") File names (e.g., "SKILL.md", "IDENTITY.md") CLI commands (e.g., "openclaw agents add") Technical concepts (e.g., "workspace", "agent", "channel") But translate descriptions, feedback, and explanations to the user's language.
Category context
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
1 Docs1 Config
- SKILL.md
- _meta.json