checker
QA and peer review agent. Reviews output from other agents before delivery. Use when: (1) content from Scribe needs review before posting, (2) research from Scout needs validation before acting on it, (3) outreach messages need a quality check before sending, (4) any deliverable needs a second pair of eyes before it reaches Honey B or goes public. NOT for: creating content (use scribe), doing research (use scout), generating images (use pixel), doing maintenance/cleanup (use janitor). Checker REVIEWS, doesn't create. Don't use for internal drafts or brainstorming — only for pre-delivery QA. Outputs: review verdicts saved to artifacts/checker/.
Why use this skill?
Enhance your workflow with Checker, the OpenClaw agent that provides rigorous, automated quality assurance and peer reviews for all AI-generated content.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/honeybee1130/checkerWhat This Skill Does
Checker is the final gatekeeper for the OpenClaw AI agent ecosystem. Its primary function is to conduct rigorous QA and peer reviews on deliverables generated by other agents—such as Scribe, Scout, or Pixel—before they are released to Honey B or published publicly. Checker ensures that everything passing through the system meets strict internal quality standards regarding brand voice, factual accuracy, and technical formatting.
Unlike content generation agents, Checker is strictly evaluative. It does not write, research, or edit; it reviews existing artifacts against a comprehensive checklist and issues a binary verdict: APPROVED or NEEDS REVISION. By enforcing this review layer, Checker prevents poor-quality, off-brand, or factually incorrect content from ever reaching production.
Installation
To add Checker to your OpenClaw agent instance, run the following command in your terminal:
clawhub install openclaw/skills/skills/honeybee1130/checker
Use Cases
Use Checker for high-stakes deliverables, including:
- Content Verification: Checking Scribe-generated posts for brand voice, proper hook structure, and lack of emojis or em dashes.
- Research Validation: Verifying that research from Scout contains valid, current, and unbiased sources before that information is integrated into a larger report.
- Outreach Quality: Auditing personalized DMs and emails to ensure the tone is professional yet authentic, and that the call-to-action is optimized for low-friction responses.
- Visual Consistency: Ensuring that assets created by Pixel feature the correct brand elements and are properly sized for their target platforms.
Example Prompts
- "Checker, please review the latest blog post draft in
artifacts/scribe/and let me know if it meets the hook and voice guidelines for the Honey B brand." - "I need a QA report on the research summary from Scout regarding the latest market trends; check the links and verify that all claims are supported."
- "Run a full peer review on this draft outreach email meant for potential collaborators. Use the outreach checklist and save the verdict to
artifacts/checker/."
Tips & Limitations
- Be Specific: Always point to the artifact and the agent source to help Checker navigate the workspace effectively.
- Respect the Boundaries: Remember that Checker is not a writing assistant. Do not ask it to 'fix' errors; ask it to identify them so you can route the feedback back to the original authoring agent.
- Binary Verdicts: Do not expect Checker to provide 'maybe' feedback. It is designed to hold a high standard. If a deliverable fails, treat the NEEDS REVISION report as a direct set of instructions to improve the asset before the next submission.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-honeybee1130-checker": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write
Related Skills
font-interceptor
Extract fonts (TTF/OTF) from any website using MSCHF Font Interceptor. Use when user drops a URL and wants to identify/extract/download fonts from that website, or asks "what font is this site using" or similar font extraction requests.
janitor
Maintenance and cleanup agent. Keeps the workspace healthy — memory consolidation, doc drift fixes, stale data cleanup, and repo organization. Use when: (1) memory files need consolidation (daily notes → MEMORY.md), (2) research files have stale leads or outdated info, (3) workspace needs organization — orphaned files, messy dirs, (4) docs are out of sync with reality (HEARTBEAT.md, TOOLS.md, agent configs), (5) scheduled maintenance runs (weekly deep clean). NOT for: creating content (use scribe), researching (use scout), reviewing quality (use checker), generating images (use pixel). Janitor MAINTAINS, doesn't create or review. Don't use for urgent tasks — Janitor handles background hygiene. Outputs: maintenance logs saved to artifacts/janitor/.
Seedance
Skill by honeybee1130
Clickbait Engine
Skill by honeybee1130
mml
Build 3D scenes and interactive experiences using MML (Metaverse Markup Language) for the Otherside metaverse and other MML-compatible environments. Use when creating 3D objects, worlds, interactive elements, animations, models, characters, audio/video, labels, collision-based interactions, position tracking, chat integration, or any MML document. Triggers on: MML, metaverse markup, 3D scene building, Otherside world building, m-cube, m-model, m-character, m-group, m-frame, m-attr-anim.