# Send Peer Review to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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 ```text 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. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "peer-review", "name": "Peer Review", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/staybased/peer-review", "canonicalUrl": "https://clawhub.ai/staybased/peer-review", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/peer-review", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=peer-review", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "peer-review", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-07T00:39:26.313Z", "expiresAt": "2026-05-14T00:39:26.313Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=peer-review", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=peer-review", "contentDisposition": "attachment; filename=\"peer-review-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "peer-review" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/peer-review" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/peer-review", "downloadUrl": "https://openagent3.xyz/downloads/peer-review", "agentUrl": "https://openagent3.xyz/skills/peer-review/agent", "manifestUrl": "https://openagent3.xyz/skills/peer-review/agent.json", "briefUrl": "https://openagent3.xyz/skills/peer-review/agent.md" } } ``` ## Documentation ### Peer Review — Local LLM Critique Layer Hypothesis: Local LLMs can catch ≥30% of real errors in cloud output with <50% false positive rate. ### Architecture Cloud Model (Claude) produces analysis │ ▼ ┌────────────────────────┐ │ Peer Review Fan-Out │ ├────────────────────────┤ │ Drift (Mistral 7B) │──► Critique A │ Pip (TinyLlama 1.1B) │──► Critique B │ Lume (Llama 3.1 8B) │──► Critique C └────────────────────────┘ │ ▼ Aggregator (consensus logic) │ ▼ Final: original + flagged issues ### Swarm Bot Roles BotModelRoleStrengthsDrift 🌊Mistral 7BMethodical analystStructured reasoning, catches logical gapsPip 🐣TinyLlama 1.1BFast checkerQuick sanity checks, low latencyLume 💡Llama 3.1 8BDeep thinkerNuanced analysis, catches subtle issues ### Scripts ScriptPurposescripts/peer-review.shSend single input to all models, collect critiquesscripts/peer-review-batch.shRun peer review across a corpus of samplesscripts/seed-test-corpus.shGenerate seeded error corpus for testing ### Usage # Single file review bash scripts/peer-review.sh [output_dir] # Batch review bash scripts/peer-review-batch.sh [results_dir] # Generate test corpus bash scripts/seed-test-corpus.sh [count] [output_dir] Scripts live at workspace/scripts/ — not bundled in skill to avoid duplication. ### Critique Prompt Template You are a skeptical reviewer. Analyze the following text for errors. For each issue found, output JSON: {"category": "factual|logical|missing|overconfidence|hallucinated_source", "quote": "...", "issue": "...", "confidence": 0-100} If no issues found, output: {"issues": []} TEXT: --- {cloud_output} --- ### Error Categories CategoryDescriptionExamplefactualWrong numbers, dates, names"Bitcoin launched in 2010"logicalNon-sequiturs, unsupported conclusions"X is rising, therefore Y will fall"missingImportant context omittedIgnoring a major counterargumentoverconfidenceCertainty without justification"This will definitely happen" on 55% eventhallucinated_sourceCiting nonexistent sources"According to a 2024 Reuters report..." ### Discord Workflow Post analysis to #the-deep (or #swarm-lab) Drift, Pip, and Lume respond with independent critiques Celeste synthesizes: deduplicates flags, weights by model confidence If consensus (≥2 models agree) → flag is high-confidence Final output posted with recommendation: publish | revise | flag_for_human ### Success Criteria OutcomeTPRFPRDecisionStrong pass≥50%<30%Ship as default layerPass≥30%<50%Ship as opt-in layerMarginal20–30%50–70%Iterate on prompts, retestFail<20%>70%Abandon approach ### Scoring Rules Flag = true positive if it identifies a real error (even if explanation is imperfect) Flag = false positive if flagged content is actually correct Duplicate flags across models count once for TPR but inform consensus metrics ### Dependencies Ollama running locally with models pulled: mistral:7b, tinyllama:1.1b, llama3.1:8b jq and curl installed Results stored in experiments/peer-review-results/ ### Integration When peer review passes validation: Package as Reef API endpoint: POST /review Agents call before publishing any analysis Configurable: model selection, consensus threshold, categories Log all reviews to #reef-logs with TPR tracking ## Trust - Source: tencent - Verification: Indexed source record - Publisher: staybased - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-07T00:39:26.313Z - Expires at: 2026-05-14T00:39:26.313Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/peer-review) - [Send to Agent page](https://openagent3.xyz/skills/peer-review/agent) - [JSON manifest](https://openagent3.xyz/skills/peer-review/agent.json) - [Markdown brief](https://openagent3.xyz/skills/peer-review/agent.md) - [Download page](https://openagent3.xyz/downloads/peer-review)