{ "schemaVersion": "1.0", "item": { "slug": "validator-agent", "name": "Validator Agent", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/up2itnow/validator-agent", "canonicalUrl": "https://clawhub.ai/up2itnow/validator-agent", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/validator-agent", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=validator-agent", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "skill.json" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "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." ], "prompts": [ { "label": "New install", "body": "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." }, { "label": "Upgrade existing", "body": "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." } ] }, "sourceHealth": { "source": "tencent", "slug": "validator-agent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-10T13:20:59.956Z", "expiresAt": "2026-05-17T13:20:59.956Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=validator-agent", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=validator-agent", "contentDisposition": "attachment; filename=\"validator-agent-1.1.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "validator-agent" }, "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/validator-agent" }, "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." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/validator-agent", "agentPageUrl": "https://openagent3.xyz/skills/validator-agent/agent", "manifestUrl": "https://openagent3.xyz/skills/validator-agent/agent.json", "briefUrl": "https://openagent3.xyz/skills/validator-agent/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "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." ], "prompts": [ { "label": "New install", "body": "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." }, { "label": "Upgrade existing", "body": "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." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Validator Agent", "body": "Multi-round automated validation pipeline for TypeScript/Solidity projects. Runs 8 rounds of checks before any publish or deploy: compile gate, lint, test suite, security audit, type coverage, docs, changelog, and final review.\n\nThe gold standard — catches what manual review misses. Originally built to validate the agent-wallet-sdk before every npm publish. Now available as a reusable skill for any project." }, { "title": "When to Use", "body": "Before npm publish — run the full 8-round validation\nBefore merging a PR — run as a quality gate\nAfter a dependency update — verify nothing regressed\nOn any TypeScript or Solidity project in the workspace" }, { "title": "Quick Start", "body": "Run the Validator Agent on skills/agent-nexus-2/agent-wallet-sdk\n\nOr trigger specific rounds:\n\nRun Validator Agent round 0 (compile gate) on projects/mastra-plugin" }, { "title": "Round 0 — Compile Gate (BLOCKING)", "body": "cd && npx tsc --noEmit 2>&1\n\nIf this fails, ALL subsequent rounds are BLOCKED. Nothing proceeds until compile is clean. This was added after a Feb 20 incident where broken types were published to npm." }, { "title": "Round 1 — Lint", "body": "cd && npm run lint 2>&1 | tail -20\n\nCheck for lint errors. Warnings are noted but don't block. Errors block." }, { "title": "Round 2 — Test Suite", "body": "cd && npm test 2>&1\n\nCapture: total tests, passing, failing, skipped. Compare against baseline in ops/test-baselines.md if it exists. Any test count drop = regression = BLOCK." }, { "title": "Round 3 — Security Audit", "body": "cd && npm audit 2>&1 | tail -15\n\n0 vulnerabilities → ✅ PASS\nModerate only (transitive) → ⚠️ WARN (note but don't block)\nHIGH or CRITICAL → 🚨 BLOCK" }, { "title": "Round 4 — Type Coverage", "body": "cd && npx type-coverage 2>&1 || echo \"type-coverage not installed — skip\"\n\nIf available, report percentage. Target: >95%. Below 90% = WARN." }, { "title": "Round 5 — Documentation Check", "body": "Does README.md exist and reference current version?\nDoes CHANGELOG.md have an entry for the version being published?\nAre all exported functions documented?" }, { "title": "Round 6 — Changelog Verification", "body": "Read package.json version field\nRead CHANGELOG.md — does it have an entry matching that version?\nIf no changelog entry for current version → BLOCK publish" }, { "title": "Round 7 — Final Review Summary", "body": "Aggregate all rounds into a single verdict:\n\n# Validator Agent Report — [project] — [timestamp]\n\n## Verdict: [✅ PASS / ⚠️ WARN / 🚨 BLOCK]\n\n| Round | Check | Result |\n|-------|-------|--------|\n| 0 | Compile | ✅/❌ |\n| 1 | Lint | ✅/⚠️/❌ |\n| 2 | Tests | ✅ X/X passing / ❌ regression |\n| 3 | Security | ✅/⚠️/🚨 |\n| 4 | Type Coverage | ✅ X% / ⚠️ / skipped |\n| 5 | Docs | ✅/⚠️ |\n| 6 | Changelog | ✅/❌ |\n| 7 | Summary | [verdict] |\n\n## Blocking Issues\n[list or \"None\"]\n\n## Warnings\n[list or \"None\"]\n\n## Recommendation\n[PUBLISH / FIX FIRST / DO NOT PUBLISH]\n\nSave report to: ops/reports/validator-YYYY-MM-DD-HH-[project].md" }, { "title": "Configuration", "body": "The skill auto-detects project type from:\n\npackage.json → TypeScript/Node project\nfoundry.toml → Solidity/Forge project\n\nFor Solidity projects, Round 0 uses forge build instead of tsc, Round 2 uses forge test, and Round 3 uses forge audit (if slither is available)." }, { "title": "Authority", "body": "This skill is read-only — it checks and reports, never modifies code\nIt produces a recommendation, never auto-publishes\nMax or Bill must approve the publish after reviewing the report" } ], "body": "Validator Agent\n\nMulti-round automated validation pipeline for TypeScript/Solidity projects. Runs 8 rounds of checks before any publish or deploy: compile gate, lint, test suite, security audit, type coverage, docs, changelog, and final review.\n\nThe gold standard — catches what manual review misses. Originally built to validate the agent-wallet-sdk before every npm publish. Now available as a reusable skill for any project.\n\nWhen to Use\nBefore npm publish — run the full 8-round validation\nBefore merging a PR — run as a quality gate\nAfter a dependency update — verify nothing regressed\nOn any TypeScript or Solidity project in the workspace\nQuick Start\nRun the Validator Agent on skills/agent-nexus-2/agent-wallet-sdk\n\n\nOr trigger specific rounds:\n\nRun Validator Agent round 0 (compile gate) on projects/mastra-plugin\n\nThe 8 Rounds\nRound 0 — Compile Gate (BLOCKING)\ncd && npx tsc --noEmit 2>&1\n\n\nIf this fails, ALL subsequent rounds are BLOCKED. Nothing proceeds until compile is clean. This was added after a Feb 20 incident where broken types were published to npm.\n\nRound 1 — Lint\ncd && npm run lint 2>&1 | tail -20\n\n\nCheck for lint errors. Warnings are noted but don't block. Errors block.\n\nRound 2 — Test Suite\ncd && npm test 2>&1\n\n\nCapture: total tests, passing, failing, skipped. Compare against baseline in ops/test-baselines.md if it exists. Any test count drop = regression = BLOCK.\n\nRound 3 — Security Audit\ncd && npm audit 2>&1 | tail -15\n\n0 vulnerabilities → ✅ PASS\nModerate only (transitive) → ⚠️ WARN (note but don't block)\nHIGH or CRITICAL → 🚨 BLOCK\nRound 4 — Type Coverage\ncd && npx type-coverage 2>&1 || echo \"type-coverage not installed — skip\"\n\n\nIf available, report percentage. Target: >95%. Below 90% = WARN.\n\nRound 5 — Documentation Check\nDoes README.md exist and reference current version?\nDoes CHANGELOG.md have an entry for the version being published?\nAre all exported functions documented?\nRound 6 — Changelog Verification\nRead package.json version field\nRead CHANGELOG.md — does it have an entry matching that version?\nIf no changelog entry for current version → BLOCK publish\nRound 7 — Final Review Summary\n\nAggregate all rounds into a single verdict:\n\n# Validator Agent Report — [project] — [timestamp]\n\n## Verdict: [✅ PASS / ⚠️ WARN / 🚨 BLOCK]\n\n| Round | Check | Result |\n|-------|-------|--------|\n| 0 | Compile | ✅/❌ |\n| 1 | Lint | ✅/⚠️/❌ |\n| 2 | Tests | ✅ X/X passing / ❌ regression |\n| 3 | Security | ✅/⚠️/🚨 |\n| 4 | Type Coverage | ✅ X% / ⚠️ / skipped |\n| 5 | Docs | ✅/⚠️ |\n| 6 | Changelog | ✅/❌ |\n| 7 | Summary | [verdict] |\n\n## Blocking Issues\n[list or \"None\"]\n\n## Warnings\n[list or \"None\"]\n\n## Recommendation\n[PUBLISH / FIX FIRST / DO NOT PUBLISH]\n\n\nSave report to: ops/reports/validator-YYYY-MM-DD-HH-[project].md\n\nConfiguration\n\nThe skill auto-detects project type from:\n\npackage.json → TypeScript/Node project\nfoundry.toml → Solidity/Forge project\n\nFor Solidity projects, Round 0 uses forge build instead of tsc, Round 2 uses forge test, and Round 3 uses forge audit (if slither is available).\n\nAuthority\nThis skill is read-only — it checks and reports, never modifies code\nIt produces a recommendation, never auto-publishes\nMax or Bill must approve the publish after reviewing the report" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/up2itnow/validator-agent", "publisherUrl": "https://clawhub.ai/up2itnow/validator-agent", "owner": "up2itnow", "version": "1.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/validator-agent", "downloadUrl": "https://openagent3.xyz/downloads/validator-agent", "agentUrl": "https://openagent3.xyz/skills/validator-agent/agent", "manifestUrl": "https://openagent3.xyz/skills/validator-agent/agent.json", "briefUrl": "https://openagent3.xyz/skills/validator-agent/agent.md" } }