{
  "schemaVersion": "1.0",
  "item": {
    "slug": "context-anchor",
    "name": "Context Anchor",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Boscoeuk/context-anchor",
    "canonicalUrl": "https://clawhub.ai/Boscoeuk/context-anchor",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/context-anchor",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=context-anchor",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "scripts/anchor.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. 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/context-anchor"
    },
    "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/context-anchor",
    "agentPageUrl": "https://openagent3.xyz/skills/context-anchor/agent",
    "manifestUrl": "https://openagent3.xyz/skills/context-anchor/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/context-anchor/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": "Context Anchor Skill",
        "body": "Helps agents recover context after compaction by scanning memory files and generating a \"here's where you are\" briefing."
      },
      {
        "title": "Why This Exists",
        "body": "Context compaction loses memory. Files survive. But after waking up fresh, you need to:\n\nKnow what you were working on\nSee decisions that were made\nFind open loops that need closing\nGet oriented fast\n\nThis skill automates that recovery."
      },
      {
        "title": "Quick Start",
        "body": "# Full briefing (default)\n./scripts/anchor.sh\n\n# Just show current task\n./scripts/anchor.sh --task\n\n# Just show active context files\n./scripts/anchor.sh --active\n\n# Just show recent decisions\n./scripts/anchor.sh --decisions\n\n# Show open loops / questions\n./scripts/anchor.sh --loops\n\n# Scan specific number of days back\n./scripts/anchor.sh --days 3"
      },
      {
        "title": "What It Scans",
        "body": "SourceWhat It Extractsmemory/current-task.mdCurrent task status, blockers, next stepsmemory/YYYY-MM-DD.mdRecent daily logs (last 2 days by default)context/active/*.mdIn-progress task filesDaily logsDecisions (lines with \"Decision:\", \"Decided:\", \"✅\")Daily logsOpen loops (lines with \"?\", \"TODO:\", \"Blocker:\", \"Need to\")"
      },
      {
        "title": "Output Format",
        "body": "The script outputs a structured briefing:\n\n═══════════════════════════════════════════════════════════\n                    CONTEXT ANCHOR\n              Where You Left Off\n═══════════════════════════════════════════════════════════\n\n📋 CURRENT TASK\n───────────────────────────────────────────────────────────\n[Contents of memory/current-task.md or \"No current task set\"]\n\n📂 ACTIVE CONTEXT FILES\n───────────────────────────────────────────────────────────\n• context/active/project-name.md (updated 2h ago)\n  └─ First line preview...\n\n🎯 RECENT DECISIONS (last 2 days)\n───────────────────────────────────────────────────────────\n[2026-01-30] Decision: Use Cloudflare Pages for hosting\n[2026-01-30] ✅ Completed email capture setup\n\n❓ OPEN LOOPS\n───────────────────────────────────────────────────────────\n[2026-01-30] Need to enable SFTP on NAS\n[2026-01-30] TODO: Create Product Hunt account\n\n═══════════════════════════════════════════════════════════"
      },
      {
        "title": "Integration with AGENTS.md",
        "body": "Add to your \"Every Session\" routine:\n\n## Every Session\n\nBefore doing anything else:\n1. Run `./skills/context-anchor/scripts/anchor.sh` for orientation\n2. Read `SOUL.md` — this is who you are\n3. Read `USER.md` — this is who you're helping\n...\n\nOr use it manually when you feel lost about context."
      },
      {
        "title": "Change workspace root",
        "body": "WORKSPACE=/path/to/workspace ./scripts/anchor.sh"
      },
      {
        "title": "Change days to scan",
        "body": "./scripts/anchor.sh --days 5  # Scan 5 days back"
      },
      {
        "title": "No Dependencies",
        "body": "Pure bash. Uses only:\n\nfind, grep, head, tail, date, stat\nWorks on macOS and Linux\nNo external tools required"
      },
      {
        "title": "When to Use",
        "body": "Session start: Quick orientation on what's happening\nAfter compaction: Recover lost context\nFeeling lost: \"Wait, what was I doing?\"\nHandoff: Show another agent where things stand\nDaily review: See what decisions were made"
      }
    ],
    "body": "Context Anchor Skill\n\nHelps agents recover context after compaction by scanning memory files and generating a \"here's where you are\" briefing.\n\nWhy This Exists\n\nContext compaction loses memory. Files survive. But after waking up fresh, you need to:\n\nKnow what you were working on\nSee decisions that were made\nFind open loops that need closing\nGet oriented fast\n\nThis skill automates that recovery.\n\nQuick Start\n# Full briefing (default)\n./scripts/anchor.sh\n\n# Just show current task\n./scripts/anchor.sh --task\n\n# Just show active context files\n./scripts/anchor.sh --active\n\n# Just show recent decisions\n./scripts/anchor.sh --decisions\n\n# Show open loops / questions\n./scripts/anchor.sh --loops\n\n# Scan specific number of days back\n./scripts/anchor.sh --days 3\n\nWhat It Scans\nSource\tWhat It Extracts\nmemory/current-task.md\tCurrent task status, blockers, next steps\nmemory/YYYY-MM-DD.md\tRecent daily logs (last 2 days by default)\ncontext/active/*.md\tIn-progress task files\nDaily logs\tDecisions (lines with \"Decision:\", \"Decided:\", \"✅\")\nDaily logs\tOpen loops (lines with \"?\", \"TODO:\", \"Blocker:\", \"Need to\")\nOutput Format\n\nThe script outputs a structured briefing:\n\n═══════════════════════════════════════════════════════════\n                    CONTEXT ANCHOR\n              Where You Left Off\n═══════════════════════════════════════════════════════════\n\n📋 CURRENT TASK\n───────────────────────────────────────────────────────────\n[Contents of memory/current-task.md or \"No current task set\"]\n\n📂 ACTIVE CONTEXT FILES\n───────────────────────────────────────────────────────────\n• context/active/project-name.md (updated 2h ago)\n  └─ First line preview...\n\n🎯 RECENT DECISIONS (last 2 days)\n───────────────────────────────────────────────────────────\n[2026-01-30] Decision: Use Cloudflare Pages for hosting\n[2026-01-30] ✅ Completed email capture setup\n\n❓ OPEN LOOPS\n───────────────────────────────────────────────────────────\n[2026-01-30] Need to enable SFTP on NAS\n[2026-01-30] TODO: Create Product Hunt account\n\n═══════════════════════════════════════════════════════════\n\nIntegration with AGENTS.md\n\nAdd to your \"Every Session\" routine:\n\n## Every Session\n\nBefore doing anything else:\n1. Run `./skills/context-anchor/scripts/anchor.sh` for orientation\n2. Read `SOUL.md` — this is who you are\n3. Read `USER.md` — this is who you're helping\n...\n\n\nOr use it manually when you feel lost about context.\n\nCustomization\nChange workspace root\nWORKSPACE=/path/to/workspace ./scripts/anchor.sh\n\nChange days to scan\n./scripts/anchor.sh --days 5  # Scan 5 days back\n\nNo Dependencies\n\nPure bash. Uses only:\n\nfind, grep, head, tail, date, stat\nWorks on macOS and Linux\nNo external tools required\nWhen to Use\nSession start: Quick orientation on what's happening\nAfter compaction: Recover lost context\nFeeling lost: \"Wait, what was I doing?\"\nHandoff: Show another agent where things stand\nDaily review: See what decisions were made"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Boscoeuk/context-anchor",
    "publisherUrl": "https://clawhub.ai/Boscoeuk/context-anchor",
    "owner": "Boscoeuk",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/context-anchor",
    "downloadUrl": "https://openagent3.xyz/downloads/context-anchor",
    "agentUrl": "https://openagent3.xyz/skills/context-anchor/agent",
    "manifestUrl": "https://openagent3.xyz/skills/context-anchor/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/context-anchor/agent.md"
  }
}