{ "schemaVersion": "1.0", "item": { "slug": "lum-skill-publisher", "name": "ClawHub Skill Publisher", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ragesaq/lum-skill-publisher", "canonicalUrl": "https://clawhub.ai/ragesaq/lum-skill-publisher", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/lum-skill-publisher", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=lum-skill-publisher", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "examples/gap-analysis.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. 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/lum-skill-publisher" }, "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/lum-skill-publisher", "agentPageUrl": "https://openagent3.xyz/skills/lum-skill-publisher/agent", "manifestUrl": "https://openagent3.xyz/skills/lum-skill-publisher/agent.json", "briefUrl": "https://openagent3.xyz/skills/lum-skill-publisher/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": "ClawHub Skill Publisher v1", "body": "Turn a rough skill idea into a polished, publish-ready ClawHub listing — informed by what's actually working in the marketplace.\n\nUse this skill when you want to:\n\nPublish a new skill to ClawHub\nAudit an existing skill draft against marketplace standards\nResearch what top-performing skills look like before writing yours" }, { "title": "Step 1 — Research Top Listings", "body": "Install the most relevant published skills in a temp directory and read their SKILL.md + README.md:\n\nmkdir -p /tmp/ch-research\n\n# Search for skills in your category\nclawhub search \"your-category-keyword\"\n\n# Install top 3-5 results for analysis\nclawhub install --dir /tmp/ch-research --force\nclawhub install --dir /tmp/ch-research --force\n# (rate limit: add 3s sleep between installs)\n\nWhat to capture per skill:\n\nDescription line: length, tone, value-first or feature-first?\nFirst sentence of SKILL.md: does it state the use case immediately?\nStructure: does it use tables, code blocks, headers?\nWord count (target: 400–700 words for SKILL.md)\nSections present: commands, when-to-use, safety, version history\nTrust signals: safety section, version history, explicit opt-outs" }, { "title": "Step 2 — Gap Analysis", "body": "Compare your draft against findings. Score each dimension:\n\nDimensionBest PracticeYour DraftActionDescription line≤160 chars, value-first, no buzzwords?Patch or OK\"When to use\"Explicit trigger + do/don't?Patch or OKCommands/interfaceSlash commands or trigger phrases?Patch or OKWord count (SKILL.md)400–700 words?Trim or expandTables vs. proseTables preferred for comparisons?Patch or OKVersion historyPresent, at bottom?Add or OKSafety sectionExplicit \"never does X\" list?Add or OKExamplesConcrete ✅/❌ pairs?Add or OKAttributionLink back to openclaw.ai / clawhub.ai?Add or OK" }, { "title": "Step 3 — Patch the Draft", "body": "Apply gap findings. Priority order:\n\nDescription line (most visible — fix first)\n\"When to use\" section (drives installs)\nTrim word count if over 700 (cut prose, keep tables)\nAdd missing sections (safety, version history)\nConvert prose comparisons to tables\nAdd examples file if none exists" }, { "title": "Step 4 — Publish", "body": "# Verify auth\nclawhub whoami\n\n# Publish (run from workspace root or skill parent dir)\nclawhub publish ./skills/ \\\n --slug \\\n --name \"Your Skill Name\" \\\n --version 1.0.0 \\\n --changelog \"Initial release\"\n\nPublished URL: https://clawhub.ai/skills/" }, { "title": "Description Field (≤160 chars)", "body": "The most important text. Shows in search results and install prompts.\n\nFormula: [What it does] + [how] + [key outcome].\n\n✅ Good: \"Reduce AI costs by batching related asks into fewer responses. ~30–50% fewer API calls, no quality loss.\"\n❌ Bad: \"ClawSaver — Combines Linked Asks into Well-structured Sets for Affordable, Verified, Efficient Responses\"" }, { "title": "SKILL.md Structure (what the agent reads)", "body": "---\nname: skill-name\nversion: X.Y.Z\ndescription: \"Same as listing description\"\nmetadata: {\"openclaw\":{\"emoji\":\"🔧\"}}\n---\n\n# Skill Name vX\n\n> One-line positioning statement.\n\n[One paragraph: what it does and why.]\n\n## When to Use\n[Use / Do not use — explicit conditions]\n\n## Core Behavior / Commands\n[Tables preferred. Trigger phrases, commands, decision rules.]\n\n## Safety\n[What it never does. Explicit opt-outs.]\n\n## Installation\n[clawhub install command]\n\n## Version History\n[- X.Y.Z — what changed]" }, { "title": "README.md Structure (humans + listing body)", "body": "# Skill Name\n> Tagline\n\n## Why [Skill Name]?\n[Problem → solution in 2-3 sentences]\n\n## What It Does\n[Numbered or bulleted feature list]\n\n## [Key Decision Table or Usage Example]\n\n## Safety Model\n\n## Installation\n\n## Version" }, { "title": "What top skills have in common", "body": "Value-first description (outcome before feature list)\n\"When to use\" is explicit — most top skills have do/don't lists\nTables over prose for anything comparative\nSafety section is a trust signal — include it even if short\nVersion history at the bottom — shows maintenance\nWord count 400–700 for SKILL.md; README can be longer" }, { "title": "What separates good from great", "body": "Great: examples file with concrete ✅/❌ pairs\nGreat: trigger phrase detection (tells agent when to activate)\nGreat: explicit opt-outs (\"say X to disable\")\nGood but not great: long prose descriptions, missing opt-outs\nAvoid: backronyms or clever names in the description line (save for README)" }, { "title": "Category density (as of Feb 2026)", "body": "Cost/token tracking: saturated — need a differentiated angle\nBatch/workflow: sparse — opportunity\nProvider-specific tools: mixed — Kimi-heavy, OpenAI moderate\nProductivity/meta-skills: sparse — opportunity" }, { "title": "File Checklist Before Publishing", "body": "SKILL.md — frontmatter has name, version, description\n SKILL.md — word count 400–700\n SKILL.md — has \"When to Use\" section\n SKILL.md — has Safety section\n SKILL.md — has Version History\n README.md — value-first, ≤600 words\n README.md — installation command correct\n examples/ — at least one example file (optional but recommended)\n Description line — ≤160 chars, value-first\n clawhub whoami — auth confirmed before publish" }, { "title": "Skill Type: Behavior-Change vs. Active Tool", "body": "Most ClawHub skills are behavior-change skills — they work by shaping agent judgment through instructions, not by running code or intercepting requests at the system level. This is the same mechanism as execution-loop-breaker, token-saver, and most top listings.\n\nWhen writing a behavior-change skill:\n\nBe explicit in the description that it works through agent behavior, not automated interception\nUse language like \"trains your agent to...\" or \"gives your agent the judgment to...\" — not \"automatically detects\" or \"intercepts\"\nDon't overstate automation. \"Teaches your agent to consolidate related asks\" is honest. \"Automatically batches requests\" implies system-level routing that the skill doesn't do.\nThe benefit is still real — behavior change produces real cost and efficiency improvements\n\nWhen a skill needs to be an active tool:\n\nRequires pre-response hooks or middleware (OpenClaw doesn't currently expose these)\nRequires script files (analyzer.js, optimizer.js) that actually run\nExample: a real token optimizer that reads context size and trims it before sending\n\nBottom line: Instruction-based skills are legitimate and valuable. Just be honest about the scope. Users trust skills that set accurate expectations." }, { "title": "Version History", "body": "1.0.1 — Added \"Skill Type: Behavior-Change vs. Active Tool\" lesson from ClawSaver development\n1.0.0 — Initial release. Research workflow, gap analysis framework, listing anatomy, marketplace patterns from Feb 2026 analysis." } ], "body": "ClawHub Skill Publisher v1\n\nTurn a rough skill idea into a polished, publish-ready ClawHub listing — informed by what's actually working in the marketplace.\n\nUse this skill when you want to:\n\nPublish a new skill to ClawHub\nAudit an existing skill draft against marketplace standards\nResearch what top-performing skills look like before writing yours\nWorkflow\nStep 1 — Research Top Listings\n\nInstall the most relevant published skills in a temp directory and read their SKILL.md + README.md:\n\nmkdir -p /tmp/ch-research\n\n# Search for skills in your category\nclawhub search \"your-category-keyword\"\n\n# Install top 3-5 results for analysis\nclawhub install --dir /tmp/ch-research --force\nclawhub install --dir /tmp/ch-research --force\n# (rate limit: add 3s sleep between installs)\n\n\nWhat to capture per skill:\n\nDescription line: length, tone, value-first or feature-first?\nFirst sentence of SKILL.md: does it state the use case immediately?\nStructure: does it use tables, code blocks, headers?\nWord count (target: 400–700 words for SKILL.md)\nSections present: commands, when-to-use, safety, version history\nTrust signals: safety section, version history, explicit opt-outs\nStep 2 — Gap Analysis\n\nCompare your draft against findings. Score each dimension:\n\nDimension\tBest Practice\tYour Draft\tAction\nDescription line\t≤160 chars, value-first, no buzzwords\t?\tPatch or OK\n\"When to use\"\tExplicit trigger + do/don't\t?\tPatch or OK\nCommands/interface\tSlash commands or trigger phrases\t?\tPatch or OK\nWord count (SKILL.md)\t400–700 words\t?\tTrim or expand\nTables vs. prose\tTables preferred for comparisons\t?\tPatch or OK\nVersion history\tPresent, at bottom\t?\tAdd or OK\nSafety section\tExplicit \"never does X\" list\t?\tAdd or OK\nExamples\tConcrete ✅/❌ pairs\t?\tAdd or OK\nAttribution\tLink back to openclaw.ai / clawhub.ai\t?\tAdd or OK\nStep 3 — Patch the Draft\n\nApply gap findings. Priority order:\n\nDescription line (most visible — fix first)\n\"When to use\" section (drives installs)\nTrim word count if over 700 (cut prose, keep tables)\nAdd missing sections (safety, version history)\nConvert prose comparisons to tables\nAdd examples file if none exists\nStep 4 — Publish\n# Verify auth\nclawhub whoami\n\n# Publish (run from workspace root or skill parent dir)\nclawhub publish ./skills/ \\\n --slug \\\n --name \"Your Skill Name\" \\\n --version 1.0.0 \\\n --changelog \"Initial release\"\n\n\nPublished URL: https://clawhub.ai/skills/\n\nClawHub Listing Anatomy\nDescription Field (≤160 chars)\n\nThe most important text. Shows in search results and install prompts.\n\nFormula: [What it does] + [how] + [key outcome].\n\n✅ Good: \"Reduce AI costs by batching related asks into fewer responses. ~30–50% fewer API calls, no quality loss.\" ❌ Bad: \"ClawSaver — Combines Linked Asks into Well-structured Sets for Affordable, Verified, Efficient Responses\"\n\nSKILL.md Structure (what the agent reads)\n---\nname: skill-name\nversion: X.Y.Z\ndescription: \"Same as listing description\"\nmetadata: {\"openclaw\":{\"emoji\":\"🔧\"}}\n---\n\n# Skill Name vX\n\n> One-line positioning statement.\n\n[One paragraph: what it does and why.]\n\n## When to Use\n[Use / Do not use — explicit conditions]\n\n## Core Behavior / Commands\n[Tables preferred. Trigger phrases, commands, decision rules.]\n\n## Safety\n[What it never does. Explicit opt-outs.]\n\n## Installation\n[clawhub install command]\n\n## Version History\n[- X.Y.Z — what changed]\n\nREADME.md Structure (humans + listing body)\n# Skill Name\n> Tagline\n\n## Why [Skill Name]?\n[Problem → solution in 2-3 sentences]\n\n## What It Does\n[Numbered or bulleted feature list]\n\n## [Key Decision Table or Usage Example]\n\n## Safety Model\n\n## Installation\n\n## Version\n\nMarketplace Patterns (Observed Feb 2026)\nWhat top skills have in common\nValue-first description (outcome before feature list)\n\"When to use\" is explicit — most top skills have do/don't lists\nTables over prose for anything comparative\nSafety section is a trust signal — include it even if short\nVersion history at the bottom — shows maintenance\nWord count 400–700 for SKILL.md; README can be longer\nWhat separates good from great\nGreat: examples file with concrete ✅/❌ pairs\nGreat: trigger phrase detection (tells agent when to activate)\nGreat: explicit opt-outs (\"say X to disable\")\nGood but not great: long prose descriptions, missing opt-outs\nAvoid: backronyms or clever names in the description line (save for README)\nCategory density (as of Feb 2026)\nCost/token tracking: saturated — need a differentiated angle\nBatch/workflow: sparse — opportunity\nProvider-specific tools: mixed — Kimi-heavy, OpenAI moderate\nProductivity/meta-skills: sparse — opportunity\nFile Checklist Before Publishing\n SKILL.md — frontmatter has name, version, description\n SKILL.md — word count 400–700\n SKILL.md — has \"When to Use\" section\n SKILL.md — has Safety section\n SKILL.md — has Version History\n README.md — value-first, ≤600 words\n README.md — installation command correct\n examples/ — at least one example file (optional but recommended)\n Description line — ≤160 chars, value-first\n clawhub whoami — auth confirmed before publish\nSkill Type: Behavior-Change vs. Active Tool\n\nMost ClawHub skills are behavior-change skills — they work by shaping agent judgment through instructions, not by running code or intercepting requests at the system level. This is the same mechanism as execution-loop-breaker, token-saver, and most top listings.\n\nWhen writing a behavior-change skill:\n\nBe explicit in the description that it works through agent behavior, not automated interception\nUse language like \"trains your agent to...\" or \"gives your agent the judgment to...\" — not \"automatically detects\" or \"intercepts\"\nDon't overstate automation. \"Teaches your agent to consolidate related asks\" is honest. \"Automatically batches requests\" implies system-level routing that the skill doesn't do.\nThe benefit is still real — behavior change produces real cost and efficiency improvements\n\nWhen a skill needs to be an active tool:\n\nRequires pre-response hooks or middleware (OpenClaw doesn't currently expose these)\nRequires script files (analyzer.js, optimizer.js) that actually run\nExample: a real token optimizer that reads context size and trims it before sending\n\nBottom line: Instruction-based skills are legitimate and valuable. Just be honest about the scope. Users trust skills that set accurate expectations.\n\nVersion History\n1.0.1 — Added \"Skill Type: Behavior-Change vs. Active Tool\" lesson from ClawSaver development\n1.0.0 — Initial release. Research workflow, gap analysis framework, listing anatomy, marketplace patterns from Feb 2026 analysis." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ragesaq/lum-skill-publisher", "publisherUrl": "https://clawhub.ai/ragesaq/lum-skill-publisher", "owner": "ragesaq", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/lum-skill-publisher", "downloadUrl": "https://openagent3.xyz/downloads/lum-skill-publisher", "agentUrl": "https://openagent3.xyz/skills/lum-skill-publisher/agent", "manifestUrl": "https://openagent3.xyz/skills/lum-skill-publisher/agent.json", "briefUrl": "https://openagent3.xyz/skills/lum-skill-publisher/agent.md" } }