{ "schemaVersion": "1.0", "item": { "slug": "skill-refiner", "name": "skill-refiner", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/1va7/skill-refiner", "canonicalUrl": "https://clawhub.ai/1va7/skill-refiner", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/skill-refiner", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-refiner", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "README.zh.md", "SKILL.md", "bin/skill-refiner.sh", "package.json", "scripts/audit_skill.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": "2026-04-30T16:55:25.780Z", "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-refiner" }, "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-refiner", "agentPageUrl": "https://openagent3.xyz/skills/skill-refiner/agent", "manifestUrl": "https://openagent3.xyz/skills/skill-refiner/agent.json", "briefUrl": "https://openagent3.xyz/skills/skill-refiner/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": "Skill Refiner", "body": "Finds every skill in the workspace, audits each against skill-creator requirements, and fixes non-compliant ones." }, { "title": "Step 1 — Discover all skills", "body": "bash scripts/find_skills.sh [workspace_dir]\n\nThis searches the entire workspace for SKILL.md files (not just skills/). Skills created without following skill-creator conventions may end up anywhere." }, { "title": "Step 2 — Audit each skill", "body": "python3 scripts/audit_skill.py \n\nReturns JSON with:\n\nissues — blocking problems that must be fixed\nwarnings — advisory improvements\ncompliant — true only when issues is empty\n\nRun this on every path returned by Step 1. Batch example:\n\nbash scripts/find_skills.sh | while read dir; do\n python3 scripts/audit_skill.py \"$dir\"\ndone" }, { "title": "Step 3 — Report findings", "body": "Summarize results in a table:\n\nSkillLocationIssuesWarningsStatusmy-skillskills/my-skill01⚠️bad-skilltemp/bad-skill20❌" }, { "title": "Step 4 — Fix non-compliant skills", "body": "For each skill with issues, fix in this order:\n\nMissing/malformed frontmatter — Add or correct the --- block with name and description only\nExtra frontmatter fields — Remove any fields other than name and description\nWeak description — Rewrite to include: what the skill does + trigger conditions (\"Use when...\")\nExtraneous files — Delete README.md, INSTALLATION_GUIDE.md, CHANGELOG.md, etc.\nWrong location — If a skill is outside skills/, move it to ~/.openclaw/workspace/skills//\nNaming violations — Rename directory to lowercase-hyphen-case\n\nFor warnings (advisory):\n\nLong SKILL.md (>500 lines): extract detailed content into references/ files and link from SKILL.md\nUnlinked references: add links in SKILL.md body\nWeak description: improve trigger language" }, { "title": "Step 5 — Validate fixes", "body": "Re-run audit_skill.py on each fixed skill to confirm \"compliant\": true.\n\nOptionally package with:\n\npython3 /opt/homebrew/lib/node_modules/openclaw/skills/skill-creator/scripts/package_skill.py " }, { "title": "Compliance Checklist", "body": "A compliant skill must have:\n\nSKILL.md at the root of a named directory\n YAML frontmatter with exactly name and description (no other fields)\n description includes what the skill does AND when to trigger it\n Directory name: lowercase letters, digits, hyphens only; ≤64 chars\n No extraneous files (README.md, CHANGELOG.md, etc.)\n Resources only in scripts/, references/, or assets/\n All references/ files linked from SKILL.md body\n SKILL.md body ≤500 lines (split into references/ if longer)" } ], "body": "Skill Refiner\n\nFinds every skill in the workspace, audits each against skill-creator requirements, and fixes non-compliant ones.\n\nWorkflow\nStep 1 — Discover all skills\nbash scripts/find_skills.sh [workspace_dir]\n\n\nThis searches the entire workspace for SKILL.md files (not just skills/). Skills created without following skill-creator conventions may end up anywhere.\n\nStep 2 — Audit each skill\npython3 scripts/audit_skill.py \n\n\nReturns JSON with:\n\nissues — blocking problems that must be fixed\nwarnings — advisory improvements\ncompliant — true only when issues is empty\n\nRun this on every path returned by Step 1. Batch example:\n\nbash scripts/find_skills.sh | while read dir; do\n python3 scripts/audit_skill.py \"$dir\"\ndone\n\nStep 3 — Report findings\n\nSummarize results in a table:\n\nSkill\tLocation\tIssues\tWarnings\tStatus\nmy-skill\tskills/my-skill\t0\t1\t⚠️\nbad-skill\ttemp/bad-skill\t2\t0\t❌\nStep 4 — Fix non-compliant skills\n\nFor each skill with issues, fix in this order:\n\nMissing/malformed frontmatter — Add or correct the --- block with name and description only\nExtra frontmatter fields — Remove any fields other than name and description\nWeak description — Rewrite to include: what the skill does + trigger conditions (\"Use when...\")\nExtraneous files — Delete README.md, INSTALLATION_GUIDE.md, CHANGELOG.md, etc.\nWrong location — If a skill is outside skills/, move it to ~/.openclaw/workspace/skills//\nNaming violations — Rename directory to lowercase-hyphen-case\n\nFor warnings (advisory):\n\nLong SKILL.md (>500 lines): extract detailed content into references/ files and link from SKILL.md\nUnlinked references: add links in SKILL.md body\nWeak description: improve trigger language\nStep 5 — Validate fixes\n\nRe-run audit_skill.py on each fixed skill to confirm \"compliant\": true.\n\nOptionally package with:\n\npython3 /opt/homebrew/lib/node_modules/openclaw/skills/skill-creator/scripts/package_skill.py \n\nCompliance Checklist\n\nA compliant skill must have:\n\n SKILL.md at the root of a named directory\n YAML frontmatter with exactly name and description (no other fields)\n description includes what the skill does AND when to trigger it\n Directory name: lowercase letters, digits, hyphens only; ≤64 chars\n No extraneous files (README.md, CHANGELOG.md, etc.)\n Resources only in scripts/, references/, or assets/\n All references/ files linked from SKILL.md body\n SKILL.md body ≤500 lines (split into references/ if longer)" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/1va7/skill-refiner", "publisherUrl": "https://clawhub.ai/1va7/skill-refiner", "owner": "1va7", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/skill-refiner", "downloadUrl": "https://openagent3.xyz/downloads/skill-refiner", "agentUrl": "https://openagent3.xyz/skills/skill-refiner/agent", "manifestUrl": "https://openagent3.xyz/skills/skill-refiner/agent.json", "briefUrl": "https://openagent3.xyz/skills/skill-refiner/agent.md" } }