{
  "schemaVersion": "1.0",
  "item": {
    "slug": "sightglass",
    "name": "Sightglass",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/davidgeorgehope/sightglass",
    "canonicalUrl": "https://clawhub.ai/davidgeorgehope/sightglass",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/sightglass",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=sightglass",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "analyze.sh",
      "hooks/post-session.sh",
      "hooks/pre-spawn.sh",
      "setup.sh",
      "skill.json"
    ],
    "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/sightglass"
    },
    "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/sightglass",
    "agentPageUrl": "https://openagent3.xyz/skills/sightglass/agent",
    "manifestUrl": "https://openagent3.xyz/skills/sightglass/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/sightglass/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": "🔍 Sightglass — Agent Supply Chain Intelligence",
        "body": "Your AI coding agent just added 47 dependencies to your project. Do you know why it picked any of them?\n\nSightglass instruments AI coding agents to capture every tool selection, dependency install, and architectural choice — then surfaces risks, biases, and better alternatives you never saw."
      },
      {
        "title": "Why This Matters",
        "body": "When a human developer picks a dependency, there's a reasoning trail: blog posts read, alternatives compared, team discussions had. When an AI agent picks one, that trail is invisible. The agent \"just knows\" packages from training data — which means it's biased toward:\n\nWhatever was popular when training data was cut off\nPackages with the most Stack Overflow mentions (not the best packages)\nDependencies it's seen in similar projects (not necessarily right for yours)\n\nSightglass makes this invisible decision-making visible."
      },
      {
        "title": "Discovery Classification",
        "body": "Sightglass classifies how your agent found each dependency:\n\nClassificationWhat It MeansRisk LevelTRAINING_RECALLAgent just \"knew\" it from training data — no search performed🟡 MediumCONTEXT_INHERITANCEFound in existing project files (package.json, imports, etc.)🟢 LowREACTIVE_SEARCHAgent hit a problem and searched for a solution🟡 MediumPROACTIVE_SEARCHAgent actively compared alternatives before choosing🟢 LowUSER_DIRECTEDHuman explicitly told the agent what to use⚪ None\n\nHigh TRAINING_RECALL percentages are a red flag — it means your agent is on autopilot, not thinking."
      },
      {
        "title": "1. Setup",
        "body": "./skills/sightglass/setup.sh\n\nThis installs the CLI (@sightglass/cli), runs initial configuration, and checks the watcher daemon."
      },
      {
        "title": "2. Login",
        "body": "sightglass login\n\nAuthenticate with sightglass.dev to enable cloud analysis and history."
      },
      {
        "title": "3. Watch",
        "body": "sightglass watch\n\nStarts the background watcher that monitors agent sessions — file changes, package installs, tool calls."
      },
      {
        "title": "4. Analyze",
        "body": "sightglass analyze\n# or\n./skills/sightglass/analyze.sh --since \"1 hour ago\" --format json"
      },
      {
        "title": "Automatic Session Tracking",
        "body": "Sightglass provides pre/post hooks for coding agent sessions:\n\nBefore a session — hooks/pre-spawn.sh:\n\nRecords start time and project context\nEnsures the watcher daemon is running\n\nAfter a session — hooks/post-session.sh:\n\nRuns analysis on everything that happened\nOutputs a summary: risks found, training recall %, alternatives missed"
      },
      {
        "title": "Using with a Coding Agent",
        "body": "When you spawn a coding agent through OpenClaw, wrap it with Sightglass:\n\n# Before spawning\nsource ./skills/sightglass/hooks/pre-spawn.sh /path/to/project\n\n# ... agent does its work ...\n\n# After session ends\n./skills/sightglass/hooks/post-session.sh\n\nThe post-session output looks like:\n\n📊 Session Summary\n  Dependencies added: 12\n  Risks found: 3\n  Training recall: 67%\n  Alternatives missed: 5\n\n  ⚠️  Run 'sightglass analyze --since ...' for details\n\n67% training recall means two-thirds of the packages were grabbed from memory with zero comparison shopping. Sightglass will show you what alternatives existed."
      },
      {
        "title": "CLI (@sightglass/cli)",
        "body": "CommandDescriptionsightglass initInitialize Sightglass in a project directorysightglass loginAuthenticate with sightglass.devsightglass setupInteractive first-time configurationsightglass watchStart the watcher daemonsightglass analyzeAnalyze agent sessions and dependency decisions"
      },
      {
        "title": "Skill Scripts",
        "body": "ScriptDescriptionsetup.shInstall CLI, configure, verify watcheranalyze.shStandalone analysis with --since, --session, --format, --push flagshooks/pre-spawn.shPre-session hook — records start, ensures watcherhooks/post-session.shPost-session hook — analyzes and summarizes"
      },
      {
        "title": "analyze.sh Flags",
        "body": "--since <time>     Analysis window start (ISO timestamp or relative like \"1 hour ago\")\n--session <id>     Analyze a specific session by ID\n--format <fmt>     Output format: text (default), json, markdown\n--push             Push results to https://sightglass.dev"
      },
      {
        "title": "What Sightglass Surfaces",
        "body": "For each agent session, you get:\n\nDependency inventory — every package added, removed, or upgraded\nDiscovery method — how the agent found each one (training recall vs. searched)\nRisk flags — known vulnerabilities, unmaintained packages, better alternatives\nAlternatives report — what the agent could have chosen but didn't consider\nBias indicators — patterns showing training data influence over reasoned choice"
      },
      {
        "title": "API",
        "body": "All data syncs to sightglass.dev when authenticated. Use --push with analyze or configure auto-push in setup.\n\nYour agent's dependencies are your dependencies. Know where they came from."
      }
    ],
    "body": "🔍 Sightglass — Agent Supply Chain Intelligence\n\nYour AI coding agent just added 47 dependencies to your project. Do you know why it picked any of them?\n\nSightglass instruments AI coding agents to capture every tool selection, dependency install, and architectural choice — then surfaces risks, biases, and better alternatives you never saw.\n\nWhy This Matters\n\nWhen a human developer picks a dependency, there's a reasoning trail: blog posts read, alternatives compared, team discussions had. When an AI agent picks one, that trail is invisible. The agent \"just knows\" packages from training data — which means it's biased toward:\n\nWhatever was popular when training data was cut off\nPackages with the most Stack Overflow mentions (not the best packages)\nDependencies it's seen in similar projects (not necessarily right for yours)\n\nSightglass makes this invisible decision-making visible.\n\nDiscovery Classification\n\nSightglass classifies how your agent found each dependency:\n\nClassification\tWhat It Means\tRisk Level\nTRAINING_RECALL\tAgent just \"knew\" it from training data — no search performed\t🟡 Medium\nCONTEXT_INHERITANCE\tFound in existing project files (package.json, imports, etc.)\t🟢 Low\nREACTIVE_SEARCH\tAgent hit a problem and searched for a solution\t🟡 Medium\nPROACTIVE_SEARCH\tAgent actively compared alternatives before choosing\t🟢 Low\nUSER_DIRECTED\tHuman explicitly told the agent what to use\t⚪ None\n\nHigh TRAINING_RECALL percentages are a red flag — it means your agent is on autopilot, not thinking.\n\nQuick Start\n1. Setup\n./skills/sightglass/setup.sh\n\n\nThis installs the CLI (@sightglass/cli), runs initial configuration, and checks the watcher daemon.\n\n2. Login\nsightglass login\n\n\nAuthenticate with sightglass.dev to enable cloud analysis and history.\n\n3. Watch\nsightglass watch\n\n\nStarts the background watcher that monitors agent sessions — file changes, package installs, tool calls.\n\n4. Analyze\nsightglass analyze\n# or\n./skills/sightglass/analyze.sh --since \"1 hour ago\" --format json\n\nOpenClaw Integration\nAutomatic Session Tracking\n\nSightglass provides pre/post hooks for coding agent sessions:\n\nBefore a session — hooks/pre-spawn.sh:\n\nRecords start time and project context\nEnsures the watcher daemon is running\n\nAfter a session — hooks/post-session.sh:\n\nRuns analysis on everything that happened\nOutputs a summary: risks found, training recall %, alternatives missed\nUsing with a Coding Agent\n\nWhen you spawn a coding agent through OpenClaw, wrap it with Sightglass:\n\n# Before spawning\nsource ./skills/sightglass/hooks/pre-spawn.sh /path/to/project\n\n# ... agent does its work ...\n\n# After session ends\n./skills/sightglass/hooks/post-session.sh\n\n\nThe post-session output looks like:\n\n📊 Session Summary\n  Dependencies added: 12\n  Risks found: 3\n  Training recall: 67%\n  Alternatives missed: 5\n\n  ⚠️  Run 'sightglass analyze --since ...' for details\n\n\n67% training recall means two-thirds of the packages were grabbed from memory with zero comparison shopping. Sightglass will show you what alternatives existed.\n\nCommands Reference\nCLI (@sightglass/cli)\nCommand\tDescription\nsightglass init\tInitialize Sightglass in a project directory\nsightglass login\tAuthenticate with sightglass.dev\nsightglass setup\tInteractive first-time configuration\nsightglass watch\tStart the watcher daemon\nsightglass analyze\tAnalyze agent sessions and dependency decisions\nSkill Scripts\nScript\tDescription\nsetup.sh\tInstall CLI, configure, verify watcher\nanalyze.sh\tStandalone analysis with --since, --session, --format, --push flags\nhooks/pre-spawn.sh\tPre-session hook — records start, ensures watcher\nhooks/post-session.sh\tPost-session hook — analyzes and summarizes\nanalyze.sh Flags\n--since <time>     Analysis window start (ISO timestamp or relative like \"1 hour ago\")\n--session <id>     Analyze a specific session by ID\n--format <fmt>     Output format: text (default), json, markdown\n--push             Push results to https://sightglass.dev\n\nWhat Sightglass Surfaces\n\nFor each agent session, you get:\n\nDependency inventory — every package added, removed, or upgraded\nDiscovery method — how the agent found each one (training recall vs. searched)\nRisk flags — known vulnerabilities, unmaintained packages, better alternatives\nAlternatives report — what the agent could have chosen but didn't consider\nBias indicators — patterns showing training data influence over reasoned choice\nAPI\n\nAll data syncs to sightglass.dev when authenticated. Use --push with analyze or configure auto-push in setup.\n\nYour agent's dependencies are your dependencies. Know where they came from."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/davidgeorgehope/sightglass",
    "publisherUrl": "https://clawhub.ai/davidgeorgehope/sightglass",
    "owner": "davidgeorgehope",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/sightglass",
    "downloadUrl": "https://openagent3.xyz/downloads/sightglass",
    "agentUrl": "https://openagent3.xyz/skills/sightglass/agent",
    "manifestUrl": "https://openagent3.xyz/skills/sightglass/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/sightglass/agent.md"
  }
}