{ "schemaVersion": "1.0", "item": { "slug": "execution-verifier", "name": "Execution Verifier", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/RichardSun700/execution-verifier", "canonicalUrl": "https://clawhub.ai/RichardSun700/execution-verifier", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/execution-verifier", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=execution-verifier", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "scripts/verify_execute_verify.py", "scripts/verify_progress.py" ], "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": "execution-verifier", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-01T10:47:12.465Z", "expiresAt": "2026-05-08T10:47:12.465Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=execution-verifier", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=execution-verifier", "contentDisposition": "attachment; filename=\"execution-verifier-1.1.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "execution-verifier" }, "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/execution-verifier" }, "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/execution-verifier", "agentPageUrl": "https://openagent3.xyz/skills/execution-verifier/agent", "manifestUrl": "https://openagent3.xyz/skills/execution-verifier/agent.json", "briefUrl": "https://openagent3.xyz/skills/execution-verifier/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": "Execution Verifier", "body": "Use this skill to prevent fake progress." }, { "title": "Core policy", "body": "Treat \"no artifact change\" as \"no progress\".\nReport only hard evidence: file changes, line deltas, commits, test outputs.\nIf no evidence is detected in the time window, report blocker + immediate next action." }, { "title": "Minimal operating loop (30 min)", "body": "Execute one concrete next action from OPEN_TASKS.\nWrite artifacts (target files must change).\nVerify with scripts/verify_progress.py.\nReport in strict 3-line format." }, { "title": "Strict report format", "body": "已完成：\n进行中：\n下一步+ETA：\n\nIf verification fails, replace line 1 with: 本轮无新增（原因：）." }, { "title": "Verifier command", "body": "python3 skills/execution-verifier/scripts/verify_progress.py \\\n --project-dir projects/ai-human-co-production \\\n --status projects/ai-human-co-production/STATUS.md \\\n --open-tasks projects/ai-human-co-production/OPEN_TASKS.md \\\n --window-min 30" }, { "title": "Closed-loop mode (verify → auto-execute → re-verify)", "body": "Use built-in script:\n\npython3 skills/execution-verifier/scripts/verify_execute_verify.py \\\n --verify-cmd \"python3 skills/execution-verifier/scripts/verify_progress.py --project-dir projects/ai-human-co-production --status projects/ai-human-co-production/STATUS.md --open-tasks projects/ai-human-co-production/OPEN_TASKS.md --window-min 30\" \\\n --execute-cmd \"openclaw cron run fc567f18-83fa-426c-8181-71a10f4568b3 --force\"\n\nBehavior:\n\nStep A: verify current progress\nStep B: if no progress, auto-trigger executor\nStep C: verify again\nOutput JSON includes before, triggered_execute, after" }, { "title": "Cron pattern (recommended)", "body": "Use two jobs:\n\nExecutor job (isolated agentTurn, every 30m): do real work + write files.\nVerifier job (main systemEvent, every 30m offset +5m): run closed-loop script above.\n\nNever run report-only cron without verifier." } ], "body": "Execution Verifier\n\nUse this skill to prevent fake progress.\n\nCore policy\nTreat \"no artifact change\" as \"no progress\".\nReport only hard evidence: file changes, line deltas, commits, test outputs.\nIf no evidence is detected in the time window, report blocker + immediate next action.\nMinimal operating loop (30 min)\nExecute one concrete next action from OPEN_TASKS.\nWrite artifacts (target files must change).\nVerify with scripts/verify_progress.py.\nReport in strict 3-line format.\nStrict report format\n已完成：\n进行中：\n下一步+ETA：\n\nIf verification fails, replace line 1 with: 本轮无新增（原因：）.\n\nVerifier command\npython3 skills/execution-verifier/scripts/verify_progress.py \\\n --project-dir projects/ai-human-co-production \\\n --status projects/ai-human-co-production/STATUS.md \\\n --open-tasks projects/ai-human-co-production/OPEN_TASKS.md \\\n --window-min 30\n\nClosed-loop mode (verify → auto-execute → re-verify)\n\nUse built-in script:\n\npython3 skills/execution-verifier/scripts/verify_execute_verify.py \\\n --verify-cmd \"python3 skills/execution-verifier/scripts/verify_progress.py --project-dir projects/ai-human-co-production --status projects/ai-human-co-production/STATUS.md --open-tasks projects/ai-human-co-production/OPEN_TASKS.md --window-min 30\" \\\n --execute-cmd \"openclaw cron run fc567f18-83fa-426c-8181-71a10f4568b3 --force\"\n\n\nBehavior:\n\nStep A: verify current progress\nStep B: if no progress, auto-trigger executor\nStep C: verify again\nOutput JSON includes before, triggered_execute, after\nCron pattern (recommended)\n\nUse two jobs:\n\nExecutor job (isolated agentTurn, every 30m): do real work + write files.\nVerifier job (main systemEvent, every 30m offset +5m): run closed-loop script above.\n\nNever run report-only cron without verifier." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/RichardSun700/execution-verifier", "publisherUrl": "https://clawhub.ai/RichardSun700/execution-verifier", "owner": "RichardSun700", "version": "1.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/execution-verifier", "downloadUrl": "https://openagent3.xyz/downloads/execution-verifier", "agentUrl": "https://openagent3.xyz/skills/execution-verifier/agent", "manifestUrl": "https://openagent3.xyz/skills/execution-verifier/agent.json", "briefUrl": "https://openagent3.xyz/skills/execution-verifier/agent.md" } }