{ "schemaVersion": "1.0", "item": { "slug": "guardrails", "name": "Guardrails", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/dgriffin831/guardrails", "canonicalUrl": "https://clawhub.ai/dgriffin831/guardrails", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/guardrails", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=guardrails", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "CHANGELOG.md", "README.md", "SKILL.md", "templates/guardrails-template.md", "scripts/generate_guardrails_md.py", "scripts/classify-risks.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/guardrails" }, "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/guardrails", "agentPageUrl": "https://openagent3.xyz/skills/guardrails/agent", "manifestUrl": "https://openagent3.xyz/skills/guardrails/agent.json", "briefUrl": "https://openagent3.xyz/skills/guardrails/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "guardrails - Interactive Security Guardrails Configuration", "body": "Helps users configure comprehensive security guardrails for their OpenClaw workspace through an interactive interview process." }, { "title": "guardrails setup", "body": "Interactive setup mode - Guides user through creating their GUARDRAILS.md file.\n\nWorkflow:\n\nRun environment discovery: bash scripts/discover.sh\nClassify risks: bash scripts/discover.sh | python3 scripts/classify-risks.py\nGenerate tailored questions: bash scripts/discover.sh | python3 scripts/classify-risks.py | python3 scripts/generate_questions.py\nConduct interactive interview with the user:\n\nAsk questions from the generated question bank (tailored to discovered environment)\nPresent suggestions for each question\nAllow custom answers\nFollow up when appropriate\n\n\nGenerate GUARDRAILS.md: echo '' | python3 scripts/generate_guardrails_md.py /path/to/guardrails-config.json\n\nStdin JSON format: {\"discovery\": {...}, \"classification\": {...}, \"answers\": {...}}\n\n\nPresent the generated GUARDRAILS.md for review\nAsk for confirmation before writing to workspace\nWrite GUARDRAILS.md to workspace root\nSave guardrails-config.json to workspace root\n\nImportant:\n\nBe conversational and friendly during the interview\nExplain why each question matters\nProvide context about discovered risks\nHighlight high-risk skills/integrations\nAllow users to skip or customize any answer\nReview the final output with the user before writing" }, { "title": "guardrails review", "body": "Review mode - Check existing configuration against current environment.\n\nWorkflow:\n\nRun discovery and classification\nLoad existing guardrails-config.json\nCompare discovered skills/integrations against config\nIdentify gaps (new skills not covered, removed skills still in config)\nAsk user about gaps only - don't re-interview everything\nUpdate config and GUARDRAILS.md if changes needed" }, { "title": "guardrails monitor", "body": "Monitor mode - Detect changes and potential violations.\n\nWorkflow:\n\nRun: bash scripts/monitor.sh\nParse the JSON report\nIf status is \"ok\": silent or brief acknowledgment\nIf status is \"needs-attention\": notify user with details\nIf status is \"review-recommended\": suggest running guardrails review\n\nCan be run manually or via cron/heartbeat." }, { "title": "Files Generated", "body": "GUARDRAILS.md - The main guardrails document (workspace root)\nguardrails-config.json - Machine-readable config for monitoring (workspace root)" }, { "title": "Notes", "body": "This skill only helps create guardrails - enforcement is up to the agent\nDiscovery (discover.sh) uses bash + jq; classification (classify-risks.py) uses Python standard library only\nQuestion generation and GUARDRAILS.md generation require an LLM — set OPENAI_API_KEY or ANTHROPIC_API_KEY\nPython scripts require the requests library (pip install requests)\nDiscovery and classification are read-only operations\nOnly setup and review modes write files, and only with user confirmation" } ], "body": "guardrails - Interactive Security Guardrails Configuration\n\nHelps users configure comprehensive security guardrails for their OpenClaw workspace through an interactive interview process.\n\nCommands\nguardrails setup\n\nInteractive setup mode - Guides user through creating their GUARDRAILS.md file.\n\nWorkflow:\n\nRun environment discovery: bash scripts/discover.sh\nClassify risks: bash scripts/discover.sh | python3 scripts/classify-risks.py\nGenerate tailored questions: bash scripts/discover.sh | python3 scripts/classify-risks.py | python3 scripts/generate_questions.py\nConduct interactive interview with the user:\nAsk questions from the generated question bank (tailored to discovered environment)\nPresent suggestions for each question\nAllow custom answers\nFollow up when appropriate\nGenerate GUARDRAILS.md: echo '' | python3 scripts/generate_guardrails_md.py /path/to/guardrails-config.json\nStdin JSON format: {\"discovery\": {...}, \"classification\": {...}, \"answers\": {...}}\nPresent the generated GUARDRAILS.md for review\nAsk for confirmation before writing to workspace\nWrite GUARDRAILS.md to workspace root\nSave guardrails-config.json to workspace root\n\nImportant:\n\nBe conversational and friendly during the interview\nExplain why each question matters\nProvide context about discovered risks\nHighlight high-risk skills/integrations\nAllow users to skip or customize any answer\nReview the final output with the user before writing\nguardrails review\n\nReview mode - Check existing configuration against current environment.\n\nWorkflow:\n\nRun discovery and classification\nLoad existing guardrails-config.json\nCompare discovered skills/integrations against config\nIdentify gaps (new skills not covered, removed skills still in config)\nAsk user about gaps only - don't re-interview everything\nUpdate config and GUARDRAILS.md if changes needed\nguardrails monitor\n\nMonitor mode - Detect changes and potential violations.\n\nWorkflow:\n\nRun: bash scripts/monitor.sh\nParse the JSON report\nIf status is \"ok\": silent or brief acknowledgment\nIf status is \"needs-attention\": notify user with details\nIf status is \"review-recommended\": suggest running guardrails review\n\nCan be run manually or via cron/heartbeat.\n\nFiles Generated\nGUARDRAILS.md - The main guardrails document (workspace root)\nguardrails-config.json - Machine-readable config for monitoring (workspace root)\nNotes\nThis skill only helps create guardrails - enforcement is up to the agent\nDiscovery (discover.sh) uses bash + jq; classification (classify-risks.py) uses Python standard library only\nQuestion generation and GUARDRAILS.md generation require an LLM — set OPENAI_API_KEY or ANTHROPIC_API_KEY\nPython scripts require the requests library (pip install requests)\nDiscovery and classification are read-only operations\nOnly setup and review modes write files, and only with user confirmation" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/dgriffin831/guardrails", "publisherUrl": "https://clawhub.ai/dgriffin831/guardrails", "owner": "dgriffin831", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/guardrails", "downloadUrl": "https://openagent3.xyz/downloads/guardrails", "agentUrl": "https://openagent3.xyz/skills/guardrails/agent", "manifestUrl": "https://openagent3.xyz/skills/guardrails/agent.json", "briefUrl": "https://openagent3.xyz/skills/guardrails/agent.md" } }