[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75GJS12NQ0XF4Z81XGSX6CC":3,"skill-same:01M75GJS12NQ0XF4Z81XGSX6CC":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M75GJS12NQ0XF4Z81XGSX6CC","pyx-scan",null,"Check whether an AI agent skill is safe before installing or using it. Calls the PYX Scanner API to retrieve trust status, risk score, and safety recommendation. Use when agent needs to verify skill safety, or user says \"is this safe\", \"check skill\", \"scan skill\", \"verify tool\", \"pyx scan\".","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Ffysoul17\u002Fpyx-scan\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: pyx-scan\ndescription: >\n  Check whether an AI agent skill is safe before installing or using it.\n  Calls the PYX Scanner API to retrieve trust status, risk score, and safety\n  recommendation. Use when agent needs to verify skill safety, or user says\n  \"is this safe\", \"check skill\", \"scan skill\", \"verify tool\", \"pyx scan\".\nallowed-tools: WebFetch, Bash(curl *)\nargument-hint: \"[owner\u002Fname]\"\n---\n\n# PYX Scan — Agent Skill Safety Check\n\nVerify whether an AI agent skill is safe before installing or using it by querying the PYX Scanner API.\n\n## Workflow\n\n### Step 1: Parse Input\n\nExtract `owner` and `name` from `$ARGUMENTS`.\n\n- Expected format: `owner\u002Fname` (e.g., `anthropic\u002Fweb-search`)\n- If `$ARGUMENTS` is empty or missing the `\u002F` separator, ask the user:\n  *\"Which skill do you want to check? Provide it as `owner\u002Fname` (e.g., `anthropic\u002Fweb-search`).\"*\n- Trim whitespace. Reject if either part is empty after trimming.\n\n### Step 2: Call the PYX Scanner API\n\nFetch the safety data:\n\n```\nWebFetch URL: https:\u002F\u002Fscanner.pyxmate.com\u002Fapi\u002Fv1\u002Fcheck\u002F{owner}\u002F{name}\nPrompt: \"Return the full JSON response body exactly as-is. Do not summarize.\"\n```\n\nIf `WebFetch` fails (tool unavailable, network error), fall back to:\n\n```bash\ncurl -s \"https:\u002F\u002Fscanner.pyxmate.com\u002Fapi\u002Fv1\u002Fcheck\u002F{owner}\u002F{name}\"\n```\n\n### Step 3: Handle Errors\n\n| HTTP Status | Meaning | Action |\n|---|---|---|\n| **200** | Skill found | Proceed to Step 4 |\n| **404** | Skill not in database | Verdict = **UNSCANNED** |\n| **429** | Rate limited | Verdict = **ERROR** — \"Rate limited. Try again shortly.\" |\n| **5xx** | Server error | Verdict = **ERROR** — \"PYX Scanner is temporarily unavailable.\" |\n| Network failure | Cannot reach API | Verdict = **ERROR** — \"Could not connect to PYX Scanner.\" |\n\n### Step 4: Determine Verdict\n\nUse the JSON response fields to determine the verdict:\n\n| Condition | Verdict |\n|---|---|\n| `recommendation == \"safe\"` AND `is_outdated == false` | **SAFE** |\n| `recommendation == \"safe\"` AND `is_outdated == true` | **OUTDATED** |\n| `recommendation == \"caution\"` | **CAUTION** |\n| `recommendation == \"danger\"` | **FAILED** |\n| `recommendation == \"unknown\"` | **UNSCANNED** |\n\n### Step 5: Output Report\n\nFormat the report as structured markdown. Omit any section where the data is null or empty.\n\n**For SAFE verdict:**\n\n```\n## PYX Scan: {owner}\u002F{name}\n\n**Verdict: SAFE** — This skill has been scanned and verified safe.\n\n**Trust Score:** {trust_score}\u002F10 | **Risk Score:** {risk_score}\u002F10 | **Confidence:** {confidence}%\n**Intent:** {intent} | **Status:** {status}\n\n### Summary\n{summary}\n\n### About\n**Purpose:** {about.purpose}\n**Capabilities:** {about.capabilities as bullet list}\n**Permissions Required:** {about.permissions_required as bullet list}\n\n[View full report]({detail_url}) | [Badge]({badge_url})\n```\n\n**For OUTDATED verdict:**\n\n```\n## PYX Scan: {owner}\u002F{name}\n\n**Verdict: OUTDATED** — Last scan was safe, but the skill has been updated since.\n\nThe scanned commit (`{scanned_commit}`) no longer matches the latest (`{latest_commit}`).\nThe new version has NOT been reviewed. Proceed with caution.\n\n**Trust Score:** {trust_score}\u002F10 | **Risk Score:** {risk_score}\u002F10\n**Last Safe Commit:** {last_safe_commit}\n\n### Summary\n{summary}\n\n[View full report]({detail_url})\n```\n\n**For CAUTION verdict:**\n\n```\n## PYX Scan: {owner}\u002F{name}\n\n**Verdict: CAUTION** — This skill has potential risks that need your attention.\n\n**Trust Score:** {trust_score}\u002F10 | **Risk Score:** {risk_score}\u002F10 | **Confidence:** {confidence}%\n**Intent:** {intent} | **Status:** {status}\n\n### Summary\n{summary}\n\n### About\n**Purpose:** {about.purpose}\n**Permissions Required:** {about.permissions_required as bullet list}\n**Security Notes:** {about.security_notes}\n\n**Do you want to proceed despite the caution rating?** Please confirm before installing or using this skill.\n\n[View full report]({detail_url})\n```\n\n**For FAILED verdict:**\n\n```\n## PYX Scan: {owner}\u002F{name}\n\n**Verdict: FAILED** — This skill has been flagged as dangerous. Do NOT install or use it.\n\n**Trust Score:** {trust_score}\u002F10 | **Risk Score:** {risk_score}\u002F10 | **Confidence:** {confidence}%\n**Intent:** {intent} | **Status:** {status}\n\n### Summary\n{summary}\n\n### About\n**Security Notes:** {about.security_notes}\n\n[View full report]({detail_url})\n```\n\n**For UNSCANNED verdict:**\n\n```\n## PYX Scan: {owner}\u002F{name}\n\n**Verdict: UNSCANNED** — This skill has not been scanned by PYX Scanner.\n\nNo safety data is available. You should:\n1. Review the skill's source code manually before use\n2. Check the skill's repository for known issues\n3. Request a scan at https:\u002F\u002Fscanner.pyxmate.com\n```\n\n**For ERROR verdict:**\n\n```\n## PYX Scan: {owner}\u002F{name}\n\n**Verdict: ERROR** — {error_message}\n\nSafety could not be verified. Treat this skill as unverified until you can confirm its safety.\n```\n\n## Behavioral Rules\n\n1. **Always call the API** — never skip the check or return a cached\u002Fassumed result.\n2. **Never soften a FAILED verdict** — if the scan says danger, report danger. Do not add qualifiers like \"but it might be fine.\"\n3. **Always ask user confirmation on CAUTION** — the user must explicitly agree before proceeding.\n4. **Keep reports concise** — omit null\u002Fempty sections rather than showing \"N\u002FA.\"\n5. **No raw JSON** — always format the response as the structured markdown report above.\n\n## Self-Scan Awareness\n\nWhen `$ARGUMENTS` is `pyxmate\u002Fpyx-scan`, `pyxmate\u002Fpyx-scanner`, or refers to this skill itself, still call the API honestly and report whatever comes back. If the result is UNSCANNED, append:\n\n> *\"Yes, even the security scanner's own skill hasn't been scanned yet. We practice what we preach — treat unscanned skills with caution.\"*\n","# PYX Scan — Agent Skill Safety Check\n\nVerify whether an AI agent skill is safe before installing or using it by querying the PYX Scanner API.\n\n## Workflow\n\n### Step 1: Parse Input\n\nExtract `owner` and `name` from `$ARGUMENTS`.\n\n- Expected format: `owner\u002Fname` (e.g., `anthropic\u002Fweb-search`)\n- If `$ARGUMENTS` is empty or missing the `\u002F` separator, ask the user:\n  *\"Which skill do you want to check? Provide it as `owner\u002Fname` (e.g., `anthropic\u002Fweb-search`).\"*\n- Trim whitespace. Reject if either part is empty after trimming.\n\n### Step 2: Call the PYX Scanner API\n\nFetch the safety data:\n\n```\nWebFetch URL: https:\u002F\u002Fscanner.pyxmate.com\u002Fapi\u002Fv1\u002Fcheck\u002F{owner}\u002F{name}\nPrompt: \"Return the full JSON response body exactly as-is. Do not summarize.\"\n```\n\nIf `WebFetch` fails (tool unavailable, network error), fall back to:\n\n```bash\ncurl -s \"https:\u002F\u002Fscanner.pyxmate.com\u002Fapi\u002Fv1\u002Fcheck\u002F{owner}\u002F{name}\"\n```\n\n### Step 3: Handle Errors\n\n| HTTP Status | Meaning | Action |\n|---|---|---|\n| **200** | Skill found | Proceed to Step 4 |\n| **404** | Skill not in database | Verdict = **UNSCANNED** |\n| **429** | Rate limited | Verdict = **ERROR** — \"Rate limited. Try again shortly.\" |\n| **5xx** | Server error | Verdict = **ERROR** — \"PYX Scanner is temporarily unavailable.\" |\n| Network failure | Cannot reach API | Verdict = **ERROR** — \"Could not connect to PYX Scanner.\" |\n\n### Step 4: Determine Verdict\n\nUse the JSON response fields to determine the verdict:\n\n| Condition | Verdict |\n|---|---|\n| `recommendation == \"safe\"` AND `is_outdated == false` | **SAFE** |\n| `recommendation == \"safe\"` AND `is_outdated == true` | **OUTDATED** |\n| `recommendation == \"caution\"` | **CAUTION** |\n| `recommendation == \"danger\"` | **FAILED** |\n| `recommendation == \"unknown\"` | **UNSCANNED** |\n\n### Step 5: Output Report\n\nFormat the report as structured markdown. Omit any section where the data is null or empty.\n\n**For SAFE verdict:**\n\n```\n## PYX Scan: {owner}\u002F{name}\n\n**Verdict: SAFE** — This skill has been scanned and verified safe.\n\n**Trust Score:** {trust_score}\u002F10 | **Risk Score:** {risk_score}\u002F10 | **Confidence:** {confidence}%\n**Intent:** {intent} | **Status:** {status}\n\n### Summary\n{summary}\n\n### About\n**Purpose:** {about.purpose}\n**Capabilities:** {about.capabilities as bullet list}\n**Permissions Required:** {about.permissions_required as bullet list}\n\n[View full report]({detail_url}) | [Badge]({badge_url})\n```\n\n**For OUTDATED verdict:**\n\n```\n## PYX Scan: {owner}\u002F{name}\n\n**Verdict: OUTDATED** — Last scan was safe, but the skill has been updated since.\n\nThe scanned commit (`{scanned_commit}`) no longer matches the latest (`{latest_commit}`).\nThe new version has NOT been reviewed. Proceed with caution.\n\n**Trust Score:** {trust_score}\u002F10 | **Risk Score:** {risk_score}\u002F10\n**Last Safe Commit:** {last_safe_commit}\n\n### Summary\n{summary}\n\n[View full report]({detail_url})\n```\n\n**For CAUTION verdict:**\n\n```\n## PYX Scan: {owner}\u002F{name}\n\n**Verdict: CAUTION** — This skill has potential risks that need your attention.\n\n**Trust Score:** {trust_score}\u002F10 | **Risk Score:** {risk_score}\u002F10 | **Confidence:** {confidence}%\n**Intent:** {intent} | **Status:** {status}\n\n### Summary\n{summary}\n\n### About\n**Purpose:** {about.purpose}\n**Permissions Required:** {about.permissions_required as bullet list}\n**Security Notes:** {about.security_notes}\n\n**Do you want to proceed despite the caution rating?** Please confirm before installing or using this skill.\n\n[View full report]({detail_url})\n```\n\n**For FAILED verdict:**\n\n```\n## PYX Scan: {owner}\u002F{name}\n\n**Verdict: FAILED** — This skill has been flagged as dangerous. Do NOT install or use it.\n\n**Trust Score:** {trust_score}\u002F10 | **Risk Score:** {risk_score}\u002F10 | **Confidence:** {confidence}%\n**Intent:** {intent} | **Status:** {status}\n\n### Summary\n{summary}\n\n### About\n**Security Notes:** {about.security_notes}\n\n[View full report]({detail_url})\n```\n\n**For UNSCANNED verdict:**\n\n```\n## PYX Scan: {owner}\u002F{name}\n\n**Verdict: UNSCANNED** — This skill has not been scanned by PYX Scanner.\n\nNo safety data is available. You should:\n1. Review the skill's source code manually before use\n2. Check the skill's repository for known issues\n3. Request a scan at https:\u002F\u002Fscanner.pyxmate.com\n```\n\n**For ERROR verdict:**\n\n```\n## PYX Scan: {owner}\u002F{name}\n\n**Verdict: ERROR** — {error_message}\n\nSafety could not be verified. Treat this skill as unverified until you can confirm its safety.\n```\n\n## Behavioral Rules\n\n1. **Always call the API** — never skip the check or return a cached\u002Fassumed result.\n2. **Never soften a FAILED verdict** — if the scan says danger, report danger. Do not add qualifiers like \"but it might be fine.\"\n3. **Always ask user confirmation on CAUTION** — the user must explicitly agree before proceeding.\n4. **Keep reports concise** — omit null\u002Fempty sections rather than showing \"N\u002FA.\"\n5. **No raw JSON** — always format the response as the structured markdown report above.\n\n## Self-Scan Awareness\n\nWhen `$ARGUMENTS` is `pyxmate\u002Fpyx-scan`, `pyxmate\u002Fpyx-scanner`, or refers to this skill itself, still call the API honestly and report whatever comes back. If the result is UNSCANNED, append:\n\n> *\"Yes, even the security scanner's own skill hasn't been scanned yet. We practice what we preach — treat unscanned skills with caution.\"*\n",{"name":5,"description":24,"allowed-tools":25,"argument-hint":26},"Check whether an AI agent skill is safe before installing or using it. Calls the PYX Scanner API to retrieve trust status, risk score, and safety recommendation. Use when agent needs to verify skill safety, or user says \"is this safe\", \"check skill\", \"scan skill\", \"verify tool\", \"pyx scan\".\n","WebFetch, Bash(curl *)","[owner\u002Fname]","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Ffysoul17\u002Fpyx-scan",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill pyx-scan",{"tool":42,"command":43},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill pyx-scan",{"tool":45,"command":46},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill pyx-scan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Ffysoul17\u002Fpyx-scan\u002FSKILL.md",true,[],[51,59,66,73,80,87],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":58},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":58},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":58},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":58},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":58},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":58},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]