{
  "schemaVersion": "1.0",
  "item": {
    "slug": "workspace-review",
    "name": "Workspace Review",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/ortegarod/workspace-review",
    "canonicalUrl": "https://clawhub.ai/ortegarod/workspace-review",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/workspace-review",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=workspace-review",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/checklist.md",
      "references/openclaw-conventions.md",
      "scripts/workspace-status.sh"
    ],
    "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/workspace-review"
    },
    "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/workspace-review",
    "agentPageUrl": "https://openagent3.xyz/skills/workspace-review/agent",
    "manifestUrl": "https://openagent3.xyz/skills/workspace-review/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/workspace-review/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": "Workspace Review",
        "body": "A self-audit process to verify workspace files follow OpenClaw conventions and haven't drifted into non-standard patterns."
      },
      {
        "title": "When to Run",
        "body": "Periodically (weekly or after major changes)\nWhen asked to \"review\", \"audit\", or \"check\" workspace\nAfter bootstrap or significant reorganization\nDuring heartbeat maintenance cycles"
      },
      {
        "title": "1. Structure Check",
        "body": "Verify expected files exist in correct locations:\n\n~/.openclaw/workspace/\n├── AGENTS.md        ← Operating instructions (REQUIRED)\n├── SOUL.md          ← Persona/tone (REQUIRED)\n├── USER.md          ← User profile (REQUIRED)\n├── IDENTITY.md      ← Agent name/vibe/emoji (REQUIRED)\n├── TOOLS.md         ← Local tool notes (REQUIRED)\n├── HEARTBEAT.md     ← Heartbeat checklist (optional)\n├── MEMORY.md        ← Curated long-term memory (optional)\n├── BOOT.md          ← Runs on gateway restart (optional, boot-md hook)\n├── BOOTSTRAP.md     ← One-time first-run ritual (delete after use)\n├── memory/          ← Daily logs + reference docs (vector-indexed)\n│   └── YYYY-MM-DD.md\n└── skills/          ← Workspace-specific skills (optional)\n\nNote on BOOT.md vs BOOTSTRAP.md:\n\nBOOT.md — Persistent; runs every gateway restart (if boot-md hook enabled)\nBOOTSTRAP.md — One-time; agent follows it on first run, then deletes it\n\nCheck: Run ls -la on workspace root. Flag missing required files."
      },
      {
        "title": "2. File Purpose Audit",
        "body": "Each file has ONE job. Check for scope creep:\n\nFileShould ContainShould NOT ContainAGENTS.mdOperating instructions, memory workflow, behavior rulesPersonal memories, daily logs, tool configsSOUL.mdPersona, tone, boundaries, identity philosophyTask lists, technical details, credentialsUSER.mdUser profile, preferences, how to address themAgent memories, system configIDENTITY.mdName, emoji, vibe, external identities (wallets, handles)Instructions, memoriesTOOLS.mdEnvironment-specific notes (camera names, SSH hosts, voices)Skill instructions, operating proceduresHEARTBEAT.mdShort checklist for periodic checksLong procedures, full documentationMEMORY.mdCurated lessons, key context, important people/projectsDaily logs, raw notesmemory/*.mdDaily logs, raw notes, session summariesLong-term curated memories\n\nCheck: Skim each file. Flag content in wrong location."
      },
      {
        "title": "3. Memory Hygiene",
        "body": "Daily files use YYYY-MM-DD.md or YYYY-MM-DD-slug.md format\n Hook-generated session files (session-memory hook creates YYYY-MM-DD-slug.md) reviewed periodically\n Reference docs use descriptive names (not dates): project-notes.md, api-guide.md\n MEMORY.md contains curated insights, not raw logs\n No duplicate information across MEMORY.md and daily files\n Old daily files reviewed and distilled to MEMORY.md periodically\n No sensitive data (API keys, passwords) in memory files\n\nAutomatic Memory Flush: OpenClaw triggers a silent agent turn before session compaction to write durable memories. The agent receives a prompt to flush important context to memory/YYYY-MM-DD.md. This is automatic — no action needed, but be aware your context WILL be compacted after ~180k tokens."
      },
      {
        "title": "4. Vector Search Alignment",
        "body": "Only MEMORY.md and memory/**/*.md are indexed by default\n Daily logs use YYYY-MM-DD.md; reference docs use descriptive names\n Files outside memory/ can be indexed via memorySearch.extraPaths in config\n\nSession Memory (Experimental): If memorySearch.experimental.sessionMemory = true, session transcripts are also indexed and searchable via memory_search."
      },
      {
        "title": "5. Git Status",
        "body": "⚠️ This workspace is PRIVATE. Never push to GitHub or any public remote.\n\ncd ~/.openclaw/workspace && git status\n\nNo remote configured (or only private backup)\n No untracked files that should be tracked\n No tracked files that should be gitignored\n No uncommitted changes lingering for days\n .gitignore excludes secrets (*.key, .pem, .env, secrets)"
      },
      {
        "title": "6. Rogue Files Check",
        "body": "Look for files that don't fit the standard layout:\n\nls -la ~/.openclaw/workspace/\n\nFlag anything that:\n\nDuplicates bootstrap file purposes (e.g., README.md alongside AGENTS.md)\nStores credentials in workspace (should be in ~/.openclaw/credentials/)\nCreates non-standard directories without clear purpose\n\nNote: Only MEMORY.md and memory/**/*.md are vector-indexed. Files outside memory/ can be added via memorySearch.extraPaths in config."
      },
      {
        "title": "7. Size Check",
        "body": "Bootstrap files should be lean (loaded every session):\n\nAGENTS.md: < 500 lines ideal, < 1000 max\nSOUL.md: < 200 lines ideal\nUSER.md: < 100 lines ideal\nIDENTITY.md: < 50 lines ideal\nHEARTBEAT.md: < 100 lines (token burn concern)\n\nwc -l AGENTS.md SOUL.md USER.md IDENTITY.md HEARTBEAT.md TOOLS.md MEMORY.md 2>/dev/null"
      },
      {
        "title": "8. Skills Check",
        "body": "If skills/ exists:\n\nEach skill has SKILL.md with valid frontmatter (name, description)\n No duplicate skills (workspace vs managed)\n Skills follow progressive disclosure (lean SKILL.md, references for details)"
      },
      {
        "title": "Output Format",
        "body": "After review, report:\n\n## Workspace Review — YYYY-MM-DD\n\n### ✅ Passing\n- [list what's correct]\n\n### ⚠️ Warnings\n- [list minor issues]\n\n### ❌ Issues\n- [list things that need fixing]\n\n### 📋 Recommendations\n- [specific actions to take]"
      },
      {
        "title": "References",
        "body": "references/openclaw-conventions.md — Full workspace file specifications\nreferences/checklist.md — Quick-reference checklist"
      }
    ],
    "body": "Workspace Review\n\nA self-audit process to verify workspace files follow OpenClaw conventions and haven't drifted into non-standard patterns.\n\nWhen to Run\nPeriodically (weekly or after major changes)\nWhen asked to \"review\", \"audit\", or \"check\" workspace\nAfter bootstrap or significant reorganization\nDuring heartbeat maintenance cycles\nReview Process\n1. Structure Check\n\nVerify expected files exist in correct locations:\n\n~/.openclaw/workspace/\n├── AGENTS.md        ← Operating instructions (REQUIRED)\n├── SOUL.md          ← Persona/tone (REQUIRED)\n├── USER.md          ← User profile (REQUIRED)\n├── IDENTITY.md      ← Agent name/vibe/emoji (REQUIRED)\n├── TOOLS.md         ← Local tool notes (REQUIRED)\n├── HEARTBEAT.md     ← Heartbeat checklist (optional)\n├── MEMORY.md        ← Curated long-term memory (optional)\n├── BOOT.md          ← Runs on gateway restart (optional, boot-md hook)\n├── BOOTSTRAP.md     ← One-time first-run ritual (delete after use)\n├── memory/          ← Daily logs + reference docs (vector-indexed)\n│   └── YYYY-MM-DD.md\n└── skills/          ← Workspace-specific skills (optional)\n\n\nNote on BOOT.md vs BOOTSTRAP.md:\n\nBOOT.md — Persistent; runs every gateway restart (if boot-md hook enabled)\nBOOTSTRAP.md — One-time; agent follows it on first run, then deletes it\n\nCheck: Run ls -la on workspace root. Flag missing required files.\n\n2. File Purpose Audit\n\nEach file has ONE job. Check for scope creep:\n\nFile\tShould Contain\tShould NOT Contain\nAGENTS.md\tOperating instructions, memory workflow, behavior rules\tPersonal memories, daily logs, tool configs\nSOUL.md\tPersona, tone, boundaries, identity philosophy\tTask lists, technical details, credentials\nUSER.md\tUser profile, preferences, how to address them\tAgent memories, system config\nIDENTITY.md\tName, emoji, vibe, external identities (wallets, handles)\tInstructions, memories\nTOOLS.md\tEnvironment-specific notes (camera names, SSH hosts, voices)\tSkill instructions, operating procedures\nHEARTBEAT.md\tShort checklist for periodic checks\tLong procedures, full documentation\nMEMORY.md\tCurated lessons, key context, important people/projects\tDaily logs, raw notes\nmemory/*.md\tDaily logs, raw notes, session summaries\tLong-term curated memories\n\nCheck: Skim each file. Flag content in wrong location.\n\n3. Memory Hygiene\n Daily files use YYYY-MM-DD.md or YYYY-MM-DD-slug.md format\n Hook-generated session files (session-memory hook creates YYYY-MM-DD-slug.md) reviewed periodically\n Reference docs use descriptive names (not dates): project-notes.md, api-guide.md\n MEMORY.md contains curated insights, not raw logs\n No duplicate information across MEMORY.md and daily files\n Old daily files reviewed and distilled to MEMORY.md periodically\n No sensitive data (API keys, passwords) in memory files\n\nAutomatic Memory Flush: OpenClaw triggers a silent agent turn before session compaction to write durable memories. The agent receives a prompt to flush important context to memory/YYYY-MM-DD.md. This is automatic — no action needed, but be aware your context WILL be compacted after ~180k tokens.\n\n4. Vector Search Alignment\n Only MEMORY.md and memory/**/*.md are indexed by default\n Daily logs use YYYY-MM-DD.md; reference docs use descriptive names\n Files outside memory/ can be indexed via memorySearch.extraPaths in config\n\nSession Memory (Experimental): If memorySearch.experimental.sessionMemory = true, session transcripts are also indexed and searchable via memory_search.\n\n5. Git Status\n\n⚠️ This workspace is PRIVATE. Never push to GitHub or any public remote.\n\ncd ~/.openclaw/workspace && git status\n\n No remote configured (or only private backup)\n No untracked files that should be tracked\n No tracked files that should be gitignored\n No uncommitted changes lingering for days\n .gitignore excludes secrets (*.key, .pem, .env, secrets)\n6. Rogue Files Check\n\nLook for files that don't fit the standard layout:\n\nls -la ~/.openclaw/workspace/\n\n\nFlag anything that:\n\nDuplicates bootstrap file purposes (e.g., README.md alongside AGENTS.md)\nStores credentials in workspace (should be in ~/.openclaw/credentials/)\nCreates non-standard directories without clear purpose\n\nNote: Only MEMORY.md and memory/**/*.md are vector-indexed. Files outside memory/ can be added via memorySearch.extraPaths in config.\n\n7. Size Check\n\nBootstrap files should be lean (loaded every session):\n\nAGENTS.md: < 500 lines ideal, < 1000 max\nSOUL.md: < 200 lines ideal\nUSER.md: < 100 lines ideal\nIDENTITY.md: < 50 lines ideal\nHEARTBEAT.md: < 100 lines (token burn concern)\nwc -l AGENTS.md SOUL.md USER.md IDENTITY.md HEARTBEAT.md TOOLS.md MEMORY.md 2>/dev/null\n\n8. Skills Check\n\nIf skills/ exists:\n\n Each skill has SKILL.md with valid frontmatter (name, description)\n No duplicate skills (workspace vs managed)\n Skills follow progressive disclosure (lean SKILL.md, references for details)\nOutput Format\n\nAfter review, report:\n\n## Workspace Review — YYYY-MM-DD\n\n### ✅ Passing\n- [list what's correct]\n\n### ⚠️ Warnings\n- [list minor issues]\n\n### ❌ Issues\n- [list things that need fixing]\n\n### 📋 Recommendations\n- [specific actions to take]\n\nReferences\nreferences/openclaw-conventions.md — Full workspace file specifications\nreferences/checklist.md — Quick-reference checklist"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ortegarod/workspace-review",
    "publisherUrl": "https://clawhub.ai/ortegarod/workspace-review",
    "owner": "ortegarod",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/workspace-review",
    "downloadUrl": "https://openagent3.xyz/downloads/workspace-review",
    "agentUrl": "https://openagent3.xyz/skills/workspace-review/agent",
    "manifestUrl": "https://openagent3.xyz/skills/workspace-review/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/workspace-review/agent.md"
  }
}