{ "schemaVersion": "1.0", "item": { "slug": "skill-test", "name": "Skill Test", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/ivangdavila/skill-test", "canonicalUrl": "https://clawhub.ai/ivangdavila/skill-test", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/skill-test", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-test", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "compare.md", "evaluate.md", "sandbox.md" ], "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", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/skill-test" }, "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/skill-test", "agentPageUrl": "https://openagent3.xyz/skills/skill-test/agent", "manifestUrl": "https://openagent3.xyz/skills/skill-test/agent.json", "briefUrl": "https://openagent3.xyz/skills/skill-test/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": "Test Skills Safely", "body": "Two use cases:\n\nTry before commit — Test drive skills before installing\nEvaluate before publish — Verify quality before publishing\n\nKey principle: Test in isolation. Never affect user's environment.\n\nReferences:\n\nRead sandbox.md — Isolated testing environment\nRead compare.md — A/B comparison between skills\nRead evaluate.md — Multi-agent quality evaluation" }, { "title": "Quick Start", "body": "Trial a skill:\n\nsessions_spawn(\n task=\"Test skill X: Load ONLY its SKILL.md, run [sample task], report quality\",\n model=\"anthropic/claude-haiku\"\n)\n\nCompare two skills:\n\nRun same task through each (separate sub-agents)\nPresent outputs side-by-side\nAsk: \"Which works better? Why?\"" }, { "title": "Test Modes", "body": "Trial Mode — Before installing\n\nSpawn sub-agent with ONLY the test skill\nRun 2-3 representative tasks\nEvaluate: Does it help? Clear instructions?\nDecision: keep, pass, or try another\n\nEvaluation Mode — Before publishing\n\nSpawn specialized reviewers (see evaluate.md)\nCheck structure, safety, usefulness\nSynthesize findings\nRecommend improvements" }, { "title": "Sandbox Isolation", "body": "⚠️ Never load test skill into your main context.\n\nSub-agent approach (recommended):\n\nsessions_spawn(\n task=\"You have ONE skill loaded: [skill content]. Test by doing: [task]\",\n model=\"anthropic/claude-haiku\"\n)\n\nComplete isolation — main session unaffected\nNatural cleanup — sub-agent terminates, done\nCheap testing — use Haiku\n\nWhat to check:\n\nDoes it activate correctly?\nAre instructions clear?\nToken cost reasonable?\nOutput quality acceptable?" }, { "title": "Edge Cases", "body": "Skill requires credentials: Ask user for test credentials or skip auth-dependent features.\n\nSkill not found: Verify slug with npx clawhub info before testing.\n\nTest fails mid-way: Sub-agent terminates cleanly. Review logs, adjust test task, retry.\n\nSkill has many auxiliary files: Load SKILL.md first, reference others only if needed during test.\n\nTest thoroughly. Install only after explicit user approval." } ], "body": "Test Skills Safely\n\nTwo use cases:\n\nTry before commit — Test drive skills before installing\nEvaluate before publish — Verify quality before publishing\n\nKey principle: Test in isolation. Never affect user's environment.\n\nReferences:\n\nRead sandbox.md — Isolated testing environment\nRead compare.md — A/B comparison between skills\nRead evaluate.md — Multi-agent quality evaluation\nQuick Start\n\nTrial a skill:\n\nsessions_spawn(\n task=\"Test skill X: Load ONLY its SKILL.md, run [sample task], report quality\",\n model=\"anthropic/claude-haiku\"\n)\n\n\nCompare two skills:\n\nRun same task through each (separate sub-agents)\nPresent outputs side-by-side\nAsk: \"Which works better? Why?\"\nTest Modes\n\nTrial Mode — Before installing\n\nSpawn sub-agent with ONLY the test skill\nRun 2-3 representative tasks\nEvaluate: Does it help? Clear instructions?\nDecision: keep, pass, or try another\n\nEvaluation Mode — Before publishing\n\nSpawn specialized reviewers (see evaluate.md)\nCheck structure, safety, usefulness\nSynthesize findings\nRecommend improvements\nSandbox Isolation\n\n⚠️ Never load test skill into your main context.\n\nSub-agent approach (recommended):\n\nsessions_spawn(\n task=\"You have ONE skill loaded: [skill content]. Test by doing: [task]\",\n model=\"anthropic/claude-haiku\"\n)\n\nComplete isolation — main session unaffected\nNatural cleanup — sub-agent terminates, done\nCheap testing — use Haiku\n\nWhat to check:\n\nDoes it activate correctly?\nAre instructions clear?\nToken cost reasonable?\nOutput quality acceptable?\nEdge Cases\n\nSkill requires credentials: Ask user for test credentials or skip auth-dependent features.\n\nSkill not found: Verify slug with npx clawhub info before testing.\n\nTest fails mid-way: Sub-agent terminates cleanly. Review logs, adjust test task, retry.\n\nSkill has many auxiliary files: Load SKILL.md first, reference others only if needed during test.\n\nTest thoroughly. Install only after explicit user approval." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/skill-test", "publisherUrl": "https://clawhub.ai/ivangdavila/skill-test", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/skill-test", "downloadUrl": "https://openagent3.xyz/downloads/skill-test", "agentUrl": "https://openagent3.xyz/skills/skill-test/agent", "manifestUrl": "https://openagent3.xyz/skills/skill-test/agent.json", "briefUrl": "https://openagent3.xyz/skills/skill-test/agent.md" } }