{ "schemaVersion": "1.0", "item": { "slug": "skillpub", "name": "Skill Publisher", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/theashbhat/skillpub", "canonicalUrl": "https://clawhub.ai/theashbhat/skillpub", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/skillpub", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skillpub", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "scripts/publish.sh", "scripts/scaffold.sh", "scripts/security-scan.sh", "scripts/validate.sh", "templates/starter/SKILL.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": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/skillpub" }, "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/skillpub", "agentPageUrl": "https://openagent3.xyz/skills/skillpub/agent", "manifestUrl": "https://openagent3.xyz/skills/skillpub/agent.json", "briefUrl": "https://openagent3.xyz/skills/skillpub/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": "Skill Publisher", "body": "Build and publish skills to ClawHub in one flow." }, { "title": "1. Scaffold a new skill", "body": "bash {baseDir}/scripts/scaffold.sh [--dir ]\n\nCreates a new skill folder with SKILL.md template and scripts/ directory.\nDefault output: ./skills/" }, { "title": "2. Fill in the skill", "body": "Edit the generated SKILL.md:\n\nSet name and description in frontmatter (description is critical for triggering)\nWrite clear instructions in the body\nAdd scripts/ for executable code, references/ for docs, assets/ for templates" }, { "title": "3. Validate", "body": "bash {baseDir}/scripts/validate.sh \n\nChecks:\n\nRequired files exist (SKILL.md)\nFrontmatter has name and description\nNaming conventions (lowercase, hyphens)\nNo forbidden files (README.md, CHANGELOG.md, etc.)" }, { "title": "4. Security scan", "body": "bash {baseDir}/scripts/security-scan.sh \n\nScans for red flags:\n\nRemote code execution / eval patterns\nData exfiltration (curl to unknown hosts)\nEnvironment variable harvesting\nPrompt injection in markdown files\nSuspicious file permissions" }, { "title": "5. Publish", "body": "bash {baseDir}/scripts/publish.sh --slug --version \n\nPushes to ClawHub. Requires clawhub login first." }, { "title": "One-liner (for simple skills)", "body": "bash {baseDir}/scripts/scaffold.sh my-skill && \\\n # edit skills/my-skill/SKILL.md ... && \\\n bash {baseDir}/scripts/validate.sh skills/my-skill && \\\n bash {baseDir}/scripts/security-scan.sh skills/my-skill && \\\n bash {baseDir}/scripts/publish.sh skills/my-skill --slug my-skill --version 1.0.0" }, { "title": "Skill Anatomy Reminder", "body": "my-skill/\n├── SKILL.md ← Required. Frontmatter (name, description) + instructions.\n├── scripts/ ← Optional. Executable code (bash, python, etc.)\n├── references/ ← Optional. Docs loaded on-demand into context.\n└── assets/ ← Optional. Templates, images, files used in output.\n\nKey principles:\n\nBe concise. Context window is shared real estate.\nDescription in frontmatter is the trigger — make it comprehensive.\nProgressive disclosure: SKILL.md body only loads when triggered.\nScripts > inline code for deterministic, repeated operations." } ], "body": "Skill Publisher\n\nBuild and publish skills to ClawHub in one flow.\n\nQuick Start\n1. Scaffold a new skill\nbash {baseDir}/scripts/scaffold.sh [--dir ]\n\n\nCreates a new skill folder with SKILL.md template and scripts/ directory. Default output: ./skills/\n\n2. Fill in the skill\n\nEdit the generated SKILL.md:\n\nSet name and description in frontmatter (description is critical for triggering)\nWrite clear instructions in the body\nAdd scripts/ for executable code, references/ for docs, assets/ for templates\n3. Validate\nbash {baseDir}/scripts/validate.sh \n\n\nChecks:\n\nRequired files exist (SKILL.md)\nFrontmatter has name and description\nNaming conventions (lowercase, hyphens)\nNo forbidden files (README.md, CHANGELOG.md, etc.)\n4. Security scan\nbash {baseDir}/scripts/security-scan.sh \n\n\nScans for red flags:\n\nRemote code execution / eval patterns\nData exfiltration (curl to unknown hosts)\nEnvironment variable harvesting\nPrompt injection in markdown files\nSuspicious file permissions\n5. Publish\nbash {baseDir}/scripts/publish.sh --slug --version \n\n\nPushes to ClawHub. Requires clawhub login first.\n\nOne-liner (for simple skills)\nbash {baseDir}/scripts/scaffold.sh my-skill && \\\n # edit skills/my-skill/SKILL.md ... && \\\n bash {baseDir}/scripts/validate.sh skills/my-skill && \\\n bash {baseDir}/scripts/security-scan.sh skills/my-skill && \\\n bash {baseDir}/scripts/publish.sh skills/my-skill --slug my-skill --version 1.0.0\n\nSkill Anatomy Reminder\nmy-skill/\n├── SKILL.md ← Required. Frontmatter (name, description) + instructions.\n├── scripts/ ← Optional. Executable code (bash, python, etc.)\n├── references/ ← Optional. Docs loaded on-demand into context.\n└── assets/ ← Optional. Templates, images, files used in output.\n\n\nKey principles:\n\nBe concise. Context window is shared real estate.\nDescription in frontmatter is the trigger — make it comprehensive.\nProgressive disclosure: SKILL.md body only loads when triggered.\nScripts > inline code for deterministic, repeated operations." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/theashbhat/skillpub", "publisherUrl": "https://clawhub.ai/theashbhat/skillpub", "owner": "theashbhat", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/skillpub", "downloadUrl": "https://openagent3.xyz/downloads/skillpub", "agentUrl": "https://openagent3.xyz/skills/skillpub/agent", "manifestUrl": "https://openagent3.xyz/skills/skillpub/agent.json", "briefUrl": "https://openagent3.xyz/skills/skillpub/agent.md" } }