# Send Workspace Analyzer to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "workspace-analyzer", "name": "Workspace Analyzer", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/zendenho7/workspace-analyzer", "canonicalUrl": "https://clawhub.ai/zendenho7/workspace-analyzer", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/workspace-analyzer", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=workspace-analyzer", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "run.sh", "scripts/analyzer.py" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "workspace-analyzer", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-01T16:02:09.658Z", "expiresAt": "2026-05-08T16:02:09.658Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=workspace-analyzer", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=workspace-analyzer", "contentDisposition": "attachment; filename=\"workspace-analyzer-1.1.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "workspace-analyzer" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/workspace-analyzer" }, "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." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/workspace-analyzer", "downloadUrl": "https://openagent3.xyz/downloads/workspace-analyzer", "agentUrl": "https://openagent3.xyz/skills/workspace-analyzer/agent", "manifestUrl": "https://openagent3.xyz/skills/workspace-analyzer/agent.json", "briefUrl": "https://openagent3.xyz/skills/workspace-analyzer/agent.md" } } ``` ## Documentation ### Workspace Analyzer "Scans, analyzes, and reports. The agent decides." ### Overview A self-improving agent needs a clean workspace. This skill analyzes any OpenClaw workspace to: Detect core files dynamically (adapts to workspace changes) Analyze content for issues (bloat, duplicates, broken links) Validate single source of truth (content in multiple places) Report actionable insights for the agent to act upon Key Principle: The script analyzes → the agent decides → the agent acts. ### Installation # Clone or copy to your skills folder cp -r workspace-analyzer/ ~/.openclaw/workspace/skills/ ### Run Analysis # Full analysis (default) python3 skills/workspace-analyzer/scripts/analyzer.py # Quick scan (structure only, no content analysis) python3 skills/workspace-analyzer/scripts/analyzer.py --quick # Specific workspace python3 skills/workspace-analyzer/scripts/analyzer.py --root /path/to/workspace # Output to file python3 skills/workspace-analyzer/scripts/analyzer.py --output report.json ### Output Format { "scan_info": { "root": "/home/user/.openclaw/workspace", "timestamp": "2026-02-21T18:00:00Z", "files_scanned": 291 }, "core_files_detected": { "kai_core": { "files": ["SOUL.md", "OPERATING.md", ...], "count": 11 }, "mission_control": {...}, "agent_cores": {...}, "skills": {...} }, "analysis": { "SOUL.md": { "category": "kai_core", "line_count": 450, "sections": [...], "wiki_links": [...], "issues": [...] } }, "single_source_validation": { "skill_graph": { "status": "PASS/FAIL", "locations": ["AGENTS.md", "OPERATING.md", "SOUL.md"], "recommendation": "Reference all to SUB_CONSCIOUS.md" }, "memory_architecture": {...}, "image_handling": {...} }, "recommendations": [ {"action": "FIX_DUPLICATE_CONTENT", "topic": "skill_graph", "files": ["AGENTS.md", "OPERATING.md"], "severity": "CRITICAL"}, {"action": "REVIEW_BLOAT", "file": "OPERATING.md", "severity": "WARN"}, {"action": "CHECK_DUPLICATE", "severity": "WARN"}, {"action": "CHECK_BROKEN_LINK", "severity": "INFO"} ], "summary": { "total_files": 291, "total_issues": 17, "total_recommendations": 25 } } ### What It Checks The analyzer validates that each topic exists in exactly ONE place: TopicExpected Single SourceSkill GraphSUB_CONSCIOUS.mdMemory ArchitectureOPERATING.md or SUB_CONSCIOUS.mdMessage ReactionsSUB_CONSCIOUS.mdImage HandlingOPERATING.mdSession BootstrapAGENTS.md ### Detection Logic Scan all core files for key section headings Build content map of where each topic appears Flag violations where topic appears in 2+ places Recommend fix by pointing to single source ### Example Output { "single_source_validation": { "skill_graph": { "status": "FAIL", "locations": ["AGENTS.md:285", "OPERATING.md:56", "SOUL.md:52"], "severity": "CRITICAL", "recommendation": "Consolidate to SUB_CONSCIOUS.md, reference from others" }, "memory_architecture": { "status": "FAIL", "locations": ["AGENTS.md:157", "OPERATING.md:74", "OPERATING.md:193"], "severity": "CRITICAL", "recommendation": "Remove duplicate section at OPERATING.md:193" } } } ### Dynamic Core File Detection Automatically detects core files based on location patterns: CategoryPatternExampleKAI CoreRoot *.mdSOUL.md, OPERATING.mdMission Controlmission_control/*GUIDELINES.mdMISSION_CONTROL_GUIDELINES.mdAgent Coresmission_control/agents//.mddesigner/SOUL.mdSkillsskills/*/SKILL.mdreact-expert/SKILL.mdSUB_CONSCIOUSRoot SUB_CONSCIOUS.mdSUB_CONSCIOUS.md ### Category-Specific Thresholds Bloat thresholds vary by category: CategoryWarningCriticalkai_core400600mission_control500800agent_cores300500skills6001000memory500800docs400600SUB_CONSCIOUS100200 ### Issue Detection BLOAT_WARNING: File exceeds warning threshold BLOAT_CRITICAL: File exceeds critical threshold ORPHAN_WARNING: File not modified in 30+ days DUPLICATE_CONTENT: Same topic in multiple files BROKEN_WIKI_LINK: Wiki-link may not match any file ### Recommendations The analyzer generates actionable recommendations: ActionSeverityDescriptionWhat To DoFIX_DUPLICATE_CONTENTCRITICALSame content in 2+ filesConsolidate to single sourceREVIEW_BLOATWARN/CRITICALFile is too largeReview if legitimate or splitREVIEW_ORPHANINFOFile hasn't been modifiedArchive if no longer neededCHECK_DUPLICATEWARNPotential duplicate filesVerify if intentional or mergeCHECK_BROKEN_LINKINFOWiki-link may be brokenVerify if skill existsCHECK_MISSINGWARNExpected core files not foundCreate if needed ### Fix Instructions for Agents When duplicate content is detected, follow these steps: ### Step 1: Identify the True Source Determine which file should be the single source: TopicShould Be InReflex behaviorsSUB_CONSCIOUS.mdSession bootstrapAGENTS.mdProceduresOPERATING.mdIdentity principlesSOUL.mdKnowledge indexKNOWLEDGE_GRAPH.md ### Step 2: Update Non-Source Files Replace duplicate content with references: **Topic:** See [[SUB_CONSCIOUS.md]] for procedures. ### Step 3: Verify Bootstrap Injection Ensure new files are injected at session start: Check ~/.openclaw/openclaw.json: { "hooks": { "internal": { "entries": { "bootstrap-extra-files": { "enabled": true, "paths": ["SUB_CONSCIOUS.md", "self-improving/memory.md"] } } } } } ### Step 4: Commit Changes git add -A git commit -m "Fix duplicate content - consolidate to single source" ### How to Use Results Step 1: Prioritize by Severity CRITICAL → Review immediately WARN → Review during next maintenance INFO → Review during weekly cleanup Step 2: Check Single Source Validation FAIL → Fix duplicate content first (most important) PASS → Move to other issues Step 3: Understand Context BLOAT = Informational, not all need fixing Reference docs (skills//references/.md) can be legitimately large Research logs are consolidations - consider splitting by date Session logs - archive old ones DUPLICATES = Check if intentional IDENTITY files = Expected (agent templates) REVIEW files = May need consolidation LESSONS files = OK (different skills) BROKEN LINKS = Usually false positives Links to skills like [[blogwatcher]] ARE valid Skills have SKILL.md suffix - analyzer doesn't detect this Only flag if link to core file is truly broken Step 4: Take Action Don't auto-fix - review first Archive old session logs monthly Split large research logs by topic Keep reference docs as-is (legitimate) Fix duplicate content by consolidating to single source ### With Heartbeat Add to your HEARTBEAT.md maintenance section: ## 7. Memory + Workspace Maintenance ### Run Workspace Analyzer python3 skills/workspace-analyzer/scripts/analyzer.py --output /tmp/analysis.json ### Review Single Source Validation - Check for DUPLICATE_CONTENT issues - Fix by consolidating to single source ### Review Recommendations - Check recommendations in output - Prioritize by severity - Fix issues manually ### Output to Memory Save analysis results for later review: python3 skills/workspace-analyzer/scripts/analyzer.py \\ --output memory/$(date +%Y-%m-%d)-workspace-analysis.json ### Read-Only Never modifies files Only reads and analyzes ### No Secrets Never reads API keys Never accesses credentials Only analyzes file metadata and content structure ### Safe Output Only contains: file paths, sizes, line counts, recommendations No sensitive data exposed ### Limitations No auto-fix: Script reports, agent must decide and act Wiki-link false positives: Links to external skills may appear broken Date-based duplicate detection: May miss non-date-based duplicates ### Sample Output - Single Source Validation { "single_source_validation": { "skill_graph": { "status": "FAIL", "files": ["AGENTS.md", "OPERATING.md", "SOUL.md"], "severity": "CRITICAL", "recommendation": "Reference all to SUB_CONSCIOUS.md" }, "memory_architecture": { "status": "FAIL", "files": ["AGENTS.md", "OPERATING.md"], "severity": "CRITICAL", "recommendation": "Remove duplicate in OPERATING.md" }, "message_reactions": { "status": "PASS", "files": ["SUB_CONSCIOUS.md"], "severity": "OK" } } } ### Sample Output - Recommendations [ { "action": "FIX_DUPLICATE_CONTENT", "topic": "skill_graph", "files": ["AGENTS.md:285", "OPERATING.md:56", "SOUL.md:52"], "severity": "CRITICAL", "recommendation": "Replace with reference to SUB_CONSCIOUS.md" }, { "action": "REVIEW_BLOAT", "file": "OPERATING.md", "category": "kai_core", "reason": "503 lines - consider splitting (threshold: 400)", "severity": "WARN" } ] ### Skill Graph This skill is related to: [[mcporter]] - For MCP server analysis [[clean-workspace]] - For actual cleanup tasks [[qmd]] - For memory organization ### v1.1.0 (2026-02-24) Added single source of truth validation Added duplicate content detection (same topics in multiple files) Added FIX_DUPLICATE_CONTENT recommendation type Added SUB_CONSCIOUS category Added fix instructions for agents ### v1.0 (2026-02-21) Initial release Basic file analysis Core file detection Bloat detection Last updated: 2026-02-24 ## Trust - Source: tencent - Verification: Indexed source record - Publisher: zendenho7 - Version: 1.1.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-01T16:02:09.658Z - Expires at: 2026-05-08T16:02:09.658Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/workspace-analyzer) - [Send to Agent page](https://openagent3.xyz/skills/workspace-analyzer/agent) - [JSON manifest](https://openagent3.xyz/skills/workspace-analyzer/agent.json) - [Markdown brief](https://openagent3.xyz/skills/workspace-analyzer/agent.md) - [Download page](https://openagent3.xyz/downloads/workspace-analyzer)