{ "schemaVersion": "1.0", "item": { "slug": "rtfm-testing", "name": "RTFM Testing", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/zscole/rtfm-testing", "canonicalUrl": "https://clawhub.ai/zscole/rtfm-testing", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/rtfm-testing", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=rtfm-testing", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "GAPS.md", "SKILL.md", "TESTER.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", "slug": "rtfm-testing", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-01T01:08:20.971Z", "expiresAt": "2026-05-08T01:08:20.971Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=rtfm-testing", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=rtfm-testing", "contentDisposition": "attachment; filename=\"rtfm-testing-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "rtfm-testing" }, "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/rtfm-testing" }, "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/rtfm-testing", "agentPageUrl": "https://openagent3.xyz/skills/rtfm-testing/agent", "manifestUrl": "https://openagent3.xyz/skills/rtfm-testing/agent.json", "briefUrl": "https://openagent3.xyz/skills/rtfm-testing/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": "RTFM Testing", "body": "A documentation quality methodology that spawns fresh agents to validate whether docs are actually usable." }, { "title": "The Problem", "body": "Documentation written by the person who built the thing is almost always incomplete. They fill in gaps unconsciously. They assume context. They skip \"obvious\" steps.\n\nRTFM Testing fixes this by spawning a fresh agent with zero context and asking: can you complete this task using only the docs?" }, { "title": "When to Use", "body": "Before publishing docs, READMEs, tutorials, or setup guides\nWhen users report confusion but you can't see why\nAfter major refactors to validate docs still work\nAs part of CI for documentation-heavy projects" }, { "title": "How It Works", "body": "Identify the task — What should someone be able to do after reading the docs?\nBundle the docs — Collect all relevant documentation (and nothing else)\nSpawn a fresh tester — Use the TESTER.md prompt with sessions_spawn\nAnalyze failures — Every confusion point is a doc bug\nFix and repeat — Update docs, respawn, retest until clean" }, { "title": "Usage", "body": "sessions_spawn(\n task: \"Complete the following task using ONLY the provided documentation. [TASK DESCRIPTION]\\n\\n---\\n\\n[PASTE DOCS HERE]\",\n agentId: \"default\",\n label: \"rtfm-test\"\n)\n\nOr use the full TESTER.md prompt for more structured output." }, { "title": "Metrics", "body": "Cold Start Score — Number of spawn cycles until task completion (lower = better docs)\nGap Count — Number of [GAP] reports per run\nGap Categories — Missing steps, unclear language, wrong assumptions, missing prerequisites" }, { "title": "Key Principles", "body": "No hints — Don't help the tester. Let it fail.\nLiteral reading — Tester must not infer or guess\nDocs only — No external knowledge, no \"common sense\"\nFailures are signal — Every stumble is actionable feedback" }, { "title": "Files", "body": "SKILL.md — This file\nTESTER.md — System prompt for the fresh agent\nGAPS.md — Output format specification" } ], "body": "RTFM Testing\n\nA documentation quality methodology that spawns fresh agents to validate whether docs are actually usable.\n\nThe Problem\n\nDocumentation written by the person who built the thing is almost always incomplete. They fill in gaps unconsciously. They assume context. They skip \"obvious\" steps.\n\nRTFM Testing fixes this by spawning a fresh agent with zero context and asking: can you complete this task using only the docs?\n\nWhen to Use\nBefore publishing docs, READMEs, tutorials, or setup guides\nWhen users report confusion but you can't see why\nAfter major refactors to validate docs still work\nAs part of CI for documentation-heavy projects\nHow It Works\nIdentify the task — What should someone be able to do after reading the docs?\nBundle the docs — Collect all relevant documentation (and nothing else)\nSpawn a fresh tester — Use the TESTER.md prompt with sessions_spawn\nAnalyze failures — Every confusion point is a doc bug\nFix and repeat — Update docs, respawn, retest until clean\nUsage\nsessions_spawn(\n task: \"Complete the following task using ONLY the provided documentation. [TASK DESCRIPTION]\\n\\n---\\n\\n[PASTE DOCS HERE]\",\n agentId: \"default\",\n label: \"rtfm-test\"\n)\n\n\nOr use the full TESTER.md prompt for more structured output.\n\nMetrics\nCold Start Score — Number of spawn cycles until task completion (lower = better docs)\nGap Count — Number of [GAP] reports per run\nGap Categories — Missing steps, unclear language, wrong assumptions, missing prerequisites\nKey Principles\nNo hints — Don't help the tester. Let it fail.\nLiteral reading — Tester must not infer or guess\nDocs only — No external knowledge, no \"common sense\"\nFailures are signal — Every stumble is actionable feedback\nFiles\nSKILL.md — This file\nTESTER.md — System prompt for the fresh agent\nGAPS.md — Output format specification" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/zscole/rtfm-testing", "publisherUrl": "https://clawhub.ai/zscole/rtfm-testing", "owner": "zscole", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/rtfm-testing", "downloadUrl": "https://openagent3.xyz/downloads/rtfm-testing", "agentUrl": "https://openagent3.xyz/skills/rtfm-testing/agent", "manifestUrl": "https://openagent3.xyz/skills/rtfm-testing/agent.json", "briefUrl": "https://openagent3.xyz/skills/rtfm-testing/agent.md" } }