{ "schemaVersion": "1.0", "item": { "slug": "skill-condenser", "name": "skill-condenser", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/killerapp/skill-condenser", "canonicalUrl": "https://clawhub.ai/killerapp/skill-condenser", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/skill-condenser", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-condenser", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "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": "2026-04-30T16:55:25.780Z", "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-condenser" }, "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-condenser", "agentPageUrl": "https://openagent3.xyz/skills/skill-condenser/agent", "manifestUrl": "https://openagent3.xyz/skills/skill-condenser/agent.json", "briefUrl": "https://openagent3.xyz/skills/skill-condenser/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 Condenser", "body": "Compress SKILL.md files using CoD with skill-format awareness. Optimized for 2-3 passes (not 5) since skills are structured, not prose." }, { "title": "When to Use", "body": "SKILL.md exceeds 200 lines\nSkill contains prose paragraphs instead of bullets\nRefactoring verbose documentation to terse style" }, { "title": "Process", "body": "Read the skill to condense\nRun 2-3 iterations of cod-iteration with skill-format context\nEach iteration: extract key entities, compress to bullets/tables\nOutput: condensed skill maintaining structure" }, { "title": "Iteration 1: Structure Extraction", "body": "Pass to cod-iteration:\n\niteration: 1\ntarget_words: [current_words * 0.6]\nformat_context: |\n OUTPUT FORMAT: Agent Skills SKILL.md\n - Use ## headers for sections\n - Bullet lists, not prose paragraphs\n - Tables for comparisons/options\n - Code blocks for commands\n - No filler phrases (\"this skill helps you...\")\n\ntext: [FULL SKILL.MD CONTENT]" }, { "title": "Iteration 2: Entity Densification", "body": "iteration: 2\ntarget_words: [iteration_1_words]\nformat_context: |\n SKILL.md TERSE RULES:\n - Each bullet = one fact\n - Combine related bullets with semicolons\n - Remove redundant examples (keep 1 best)\n - Tables compress better than lists for options\n\ntext: [ITERATION 1 OUTPUT]\nsource: [ORIGINAL SKILL.MD]" }, { "title": "Iteration 3 (Optional): Final Polish", "body": "Only if still >150 lines:\n\niteration: 3\ntarget_words: [iteration_2_words]\nformat_context: |\n FINAL PASS:\n - Move detailed content to references/ links\n - Keep only: Quick Start, Core Pattern, Troubleshooting\n - Each section <20 lines\n\ntext: [ITERATION 2 OUTPUT]\nsource: [ORIGINAL SKILL.MD]" }, { "title": "Expected Output Format", "body": "Each iteration returns:\n\nMissing_Entities: \"entity1\"; \"entity2\"; \"entity3\"\n\nDenser_Summary:\n---\nname: skill-name\ndescription: ...\n---\n# Skill Name\n[Condensed content in proper SKILL.md format]" }, { "title": "Skill-Specific Entities", "body": "When condensing skills, prioritize these entity types:\n\nEntity TypeKeepRemoveCommandsdeploy.py --env prodVerbose explanationsOptionsTable rowParagraph per optionErrorsError β†’ FixLong troubleshooting proseExamples1 best exampleMultiple similar examplesPrerequisitesBullet listExplanation of why needed" }, { "title": "Target Compression", "body": "OriginalTargetIterations200-300 lines100-1502300-500 lines150-2002-3500+ lines200 + refs3 + refactor" }, { "title": "Example: Compressing Verbose Section", "body": "Before (45 words):\n\n## Configuration\nThe configuration system allows you to customize various aspects of the deployment.\nYou can set environment variables, adjust timeouts, and configure retry behavior.\nEach setting has sensible defaults but can be overridden as needed.\n\nAfter (18 words):\n\n## Configuration\n| Setting | Default | Override |\n|---------|---------|----------|\n| `ENV` | prod | `--env dev` |\n| `TIMEOUT` | 30s | `--timeout 60` |\n| `RETRIES` | 3 | `--retries 5` |" }, { "title": "Integration with Progressive Disclosure", "body": "If skill is too large after 3 iterations:\n\nKeep in SKILL.md: Overview, Quick Start, Common Errors\nMove to references/: API details, advanced config, examples\nUpdate SKILL.md with links: See [advanced config](references/config.md)" }, { "title": "Constraints", "body": "Preserve frontmatter exactly (don't condense metadata)\nKeep all ## section headers (structure matters)\nDon't remove code blocks (commands are entities)\nMaintain one concrete example per workflow" } ], "body": "Skill Condenser\n\nCompress SKILL.md files using CoD with skill-format awareness. Optimized for 2-3 passes (not 5) since skills are structured, not prose.\n\nWhen to Use\nSKILL.md exceeds 200 lines\nSkill contains prose paragraphs instead of bullets\nRefactoring verbose documentation to terse style\nProcess\nRead the skill to condense\nRun 2-3 iterations of cod-iteration with skill-format context\nEach iteration: extract key entities, compress to bullets/tables\nOutput: condensed skill maintaining structure\nOrchestration\nIteration 1: Structure Extraction\n\nPass to cod-iteration:\n\niteration: 1\ntarget_words: [current_words * 0.6]\nformat_context: |\n OUTPUT FORMAT: Agent Skills SKILL.md\n - Use ## headers for sections\n - Bullet lists, not prose paragraphs\n - Tables for comparisons/options\n - Code blocks for commands\n - No filler phrases (\"this skill helps you...\")\n\ntext: [FULL SKILL.MD CONTENT]\n\nIteration 2: Entity Densification\niteration: 2\ntarget_words: [iteration_1_words]\nformat_context: |\n SKILL.md TERSE RULES:\n - Each bullet = one fact\n - Combine related bullets with semicolons\n - Remove redundant examples (keep 1 best)\n - Tables compress better than lists for options\n\ntext: [ITERATION 1 OUTPUT]\nsource: [ORIGINAL SKILL.MD]\n\nIteration 3 (Optional): Final Polish\n\nOnly if still >150 lines:\n\niteration: 3\ntarget_words: [iteration_2_words]\nformat_context: |\n FINAL PASS:\n - Move detailed content to references/ links\n - Keep only: Quick Start, Core Pattern, Troubleshooting\n - Each section <20 lines\n\ntext: [ITERATION 2 OUTPUT]\nsource: [ORIGINAL SKILL.MD]\n\nExpected Output Format\n\nEach iteration returns:\n\nMissing_Entities: \"entity1\"; \"entity2\"; \"entity3\"\n\nDenser_Summary:\n---\nname: skill-name\ndescription: ...\n---\n# Skill Name\n[Condensed content in proper SKILL.md format]\n\nSkill-Specific Entities\n\nWhen condensing skills, prioritize these entity types:\n\nEntity Type\tKeep\tRemove\nCommands\tdeploy.py --env prod\tVerbose explanations\nOptions\tTable row\tParagraph per option\nErrors\tError β†’ Fix\tLong troubleshooting prose\nExamples\t1 best example\tMultiple similar examples\nPrerequisites\tBullet list\tExplanation of why needed\nTarget Compression\nOriginal\tTarget\tIterations\n200-300 lines\t100-150\t2\n300-500 lines\t150-200\t2-3\n500+ lines\t200 + refs\t3 + refactor\nExample: Compressing Verbose Section\n\nBefore (45 words):\n\n## Configuration\nThe configuration system allows you to customize various aspects of the deployment.\nYou can set environment variables, adjust timeouts, and configure retry behavior.\nEach setting has sensible defaults but can be overridden as needed.\n\n\nAfter (18 words):\n\n## Configuration\n| Setting | Default | Override |\n|---------|---------|----------|\n| `ENV` | prod | `--env dev` |\n| `TIMEOUT` | 30s | `--timeout 60` |\n| `RETRIES` | 3 | `--retries 5` |\n\nIntegration with Progressive Disclosure\n\nIf skill is too large after 3 iterations:\n\nKeep in SKILL.md: Overview, Quick Start, Common Errors\nMove to references/: API details, advanced config, examples\nUpdate SKILL.md with links: See [advanced config](references/config.md)\nConstraints\nPreserve frontmatter exactly (don't condense metadata)\nKeep all ## section headers (structure matters)\nDon't remove code blocks (commands are entities)\nMaintain one concrete example per workflow" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/killerapp/skill-condenser", "publisherUrl": "https://clawhub.ai/killerapp/skill-condenser", "owner": "killerapp", "version": "1.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/skill-condenser", "downloadUrl": "https://openagent3.xyz/downloads/skill-condenser", "agentUrl": "https://openagent3.xyz/skills/skill-condenser/agent", "manifestUrl": "https://openagent3.xyz/skills/skill-condenser/agent.json", "briefUrl": "https://openagent3.xyz/skills/skill-condenser/agent.md" } }