{
  "schemaVersion": "1.0",
  "item": {
    "slug": "reflect-learn",
    "name": "Reflect",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/stevengonsalvez/reflect-learn",
    "canonicalUrl": "https://clawhub.ai/stevengonsalvez/reflect-learn",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/reflect-learn",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=reflect-learn",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CLAWDHUB-PUBLISHING-GUIDE.md",
      "SKILL.md",
      "assets/learnings_schema.yaml",
      "assets/reflection_template.md",
      "hooks/README.md",
      "hooks/precompact_reflect.py"
    ],
    "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/reflect-learn"
    },
    "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/reflect-learn",
    "agentPageUrl": "https://openagent3.xyz/skills/reflect-learn/agent",
    "manifestUrl": "https://openagent3.xyz/skills/reflect-learn/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/reflect-learn/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": "Quick Reference",
        "body": "CommandAction/reflectAnalyze conversation for learnings/reflect onEnable auto-reflection/reflect offDisable auto-reflection/reflect statusShow state and metrics/reflect reviewReview low-confidence learnings/reflect [agent]Focus on specific agent"
      },
      {
        "title": "Core Philosophy",
        "body": "\"Correct once, never again.\"\n\nWhen users correct behavior, those corrections become permanent improvements encoded into the agent system - across all future sessions."
      },
      {
        "title": "Step 1: Initialize State",
        "body": "Check and initialize state files using the state manager:\n\n# Check for existing state\npython scripts/state_manager.py init\n\n# State directory is configurable via REFLECT_STATE_DIR env var\n# Default: ~/.reflect/ (portable) or ~/.claude/session/ (Claude Code)\n\nState includes:\n\nreflect-state.yaml - Toggle state, pending reviews\nreflect-metrics.yaml - Aggregate metrics\nlearnings.yaml - Log of all applied learnings"
      },
      {
        "title": "Step 2: Scan Conversation for Signals",
        "body": "Use the signal detector to identify learnings:\n\npython scripts/signal_detector.py --input conversation.txt\n\nSignal Confidence Levels\n\nConfidenceTriggersExamplesHIGHExplicit corrections\"never\", \"always\", \"wrong\", \"stop\", \"the rule is\"MEDIUMApproved approaches\"perfect\", \"exactly\", accepted outputLOWObservationsPatterns that worked, not validated\n\nSee signal_patterns.md for full detection rules."
      },
      {
        "title": "Step 3: Classify & Match to Target Files",
        "body": "Map each signal to the appropriate target:\n\nLearning Categories:\n\nCategoryTarget FilesCode Stylecode-reviewer, backend-developer, frontend-developerArchitecturesolution-architect, api-architect, architecture-reviewerProcessCLAUDE.md, orchestrator agentsDomainDomain-specific agents, CLAUDE.mdToolsCLAUDE.md, relevant specialistsNew Skill.claude/skills/{name}/SKILL.md\n\nSee agent_mappings.md for mapping rules."
      },
      {
        "title": "Step 4: Check for Skill-Worthy Signals",
        "body": "Some learnings should become new skills rather than agent updates:\n\nSkill-Worthy Criteria:\n\nNon-obvious debugging (>10 min investigation)\nMisleading error (root cause different from message)\nWorkaround discovered through experimentation\nConfiguration insight (differs from documented)\nReusable pattern (helps in similar situations)\n\nQuality Gates (must pass all):\n\nReusable: Will help with future tasks\n Non-trivial: Requires discovery, not just docs\n Specific: Can describe exact trigger conditions\n Verified: Solution actually worked\n No duplication: Doesn't exist already\n\nSee skill_template.md for skill creation guidelines."
      },
      {
        "title": "Step 5: Generate Proposals",
        "body": "Produce output in this format:\n\n# Reflection Analysis\n\n## Session Context\n- **Date**: [timestamp]\n- **Messages Analyzed**: [count]\n- **Focus**: [all agents OR specific agent name]\n\n## Signals Detected\n\n| # | Signal | Confidence | Source Quote | Category |\n|---|--------|------------|--------------|----------|\n| 1 | [learning] | HIGH | \"[exact words]\" | Code Style |\n| 2 | [learning] | MEDIUM | \"[context]\" | Architecture |\n\n## Proposed Agent Updates\n\n### Change 1: Update [agent-name]\n\n**Target**: `[file path]`\n**Section**: [section name]\n**Confidence**: [HIGH/MEDIUM/LOW]\n**Rationale**: [why this change]\n\n```diff\n--- a/path/to/agent.md\n+++ b/path/to/agent.md\n@@ -82,6 +82,7 @@\n ## Section\n\n * Existing rule\n+* New rule from learning"
      },
      {
        "title": "Skill 1: [skill-name]",
        "body": "Quality Gate Check:\n\nReusable: [why]\n Non-trivial: [why]\n Specific: [trigger conditions]\n Verified: [how verified]\n No duplication: [checked against]\n\nWill create: .claude/skills/[skill-name]/SKILL.md"
      },
      {
        "title": "Conflict Check",
        "body": "No conflicts with existing rules detected\nOR: Warning - potential conflict with [file:line]"
      },
      {
        "title": "Commit Message",
        "body": "reflect: add learnings from session [date]\n\nAgent updates:\n- [learning 1 summary]\n\nNew skills:\n- [skill-name]: [brief description]\n\nExtracted: [N] signals ([H] high, [M] medium, [L] low confidence)"
      },
      {
        "title": "Review Prompt",
        "body": "Apply these changes?\n\nY - Apply all changes and commit\nN - Discard all changes\nmodify - Adjust specific changes\n1,3 - Apply only changes 1 and 3\ns1 - Apply only skill 1\nall-skills - Apply all skills, skip agent updates\n\n### Step 6: Handle User Response\n\n**On `Y` (approve):**\n1. Apply each change using Edit tool\n2. Run `git add` on modified files\n3. Commit with generated message\n4. Update learnings log\n5. Update metrics\n\n**On `N` (reject):**\n1. Discard proposed changes\n2. Log rejection for analysis\n3. Ask if user wants to modify any signals\n\n**On `modify`:**\n1. Present each change individually\n2. Allow editing the proposed addition\n3. Reconfirm before applying\n\n**On selective (e.g., `1,3`):**\n1. Apply only specified changes\n2. Log partial acceptance\n3. Commit only applied changes\n\n### Step 7: Update Metrics\n\n```bash\npython scripts/metrics_updater.py --accepted 3 --rejected 1 --confidence high:2,medium:1"
      },
      {
        "title": "Enable Auto-Reflection",
        "body": "/reflect on\n# Sets auto_reflect: true in state file\n# Will trigger on PreCompact hook"
      },
      {
        "title": "Disable Auto-Reflection",
        "body": "/reflect off\n# Sets auto_reflect: false in state file"
      },
      {
        "title": "Check Status",
        "body": "/reflect status\n# Shows current state and metrics"
      },
      {
        "title": "Review Pending",
        "body": "/reflect review\n# Shows low-confidence learnings awaiting validation"
      },
      {
        "title": "Output Locations",
        "body": "Project-level (versioned with repo):\n\n.claude/reflections/YYYY-MM-DD_HH-MM-SS.md - Full reflection\n.claude/reflections/index.md - Project summary\n.claude/skills/{name}/SKILL.md - New skills\n\nGlobal (user-level):\n\n~/.claude/reflections/by-project/{project}/ - Cross-project\n~/.claude/reflections/by-agent/{agent}/learnings.md - Per-agent\n~/.claude/reflections/index.md - Global summary"
      },
      {
        "title": "Memory Integration",
        "body": "Some learnings belong in auto-memory (~/.claude/projects/*/memory/MEMORY.md) rather than agent files:\n\nLearning TypeBest TargetBehavioral correction (\"always do X\")Agent fileProject-specific patternMEMORY.mdRecurring bug/workaroundNew skill OR MEMORY.mdTool preferenceCLAUDE.mdDomain knowledgeMEMORY.md or compound-docs\n\nWhen a signal is LOW confidence and project-specific, prefer writing to MEMORY.md over modifying agents."
      },
      {
        "title": "Human-in-the-Loop",
        "body": "NEVER apply changes without explicit user approval\nAlways show full diff before applying\nAllow selective application"
      },
      {
        "title": "Git Versioning",
        "body": "All changes committed with descriptive messages\nEasy rollback via git revert\nLearning history preserved"
      },
      {
        "title": "Incremental Updates",
        "body": "ONLY add to existing sections\nNEVER delete or rewrite existing rules\nPreserve original structure"
      },
      {
        "title": "Conflict Detection",
        "body": "Check if proposed rule contradicts existing\nWarn user if conflict detected\nSuggest resolution strategy"
      },
      {
        "title": "With /handover",
        "body": "If auto-reflection is enabled, PreCompact hook triggers reflection before handover."
      },
      {
        "title": "With Session Health",
        "body": "At 70%+ context (Yellow status), reminders to run /reflect are injected."
      },
      {
        "title": "Hook Integration (Claude Code)",
        "body": "The skill includes hook scripts for automatic integration:\n\n# Install hook to your Claude hooks directory\ncp hooks/precompact_reflect.py ~/.claude/hooks/\n\nConfigure in ~/.claude/settings.json:\n\n{\n  \"hooks\": {\n    \"PreCompact\": [\n      {\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"uv run ~/.claude/hooks/precompact_reflect.py --auto\"\n          }\n        ]\n      }\n    ]\n  }\n}\n\nSee hooks/README.md for full configuration options."
      },
      {
        "title": "Portability",
        "body": "This skill works with any LLM tool that supports:\n\nFile read/write operations\nText pattern matching\nGit operations (optional, for commits)"
      },
      {
        "title": "Configurable State Location",
        "body": "# Set custom state directory\nexport REFLECT_STATE_DIR=/path/to/state\n\n# Or use default\n# ~/.reflect/ (portable default)\n# ~/.claude/session/ (Claude Code default)"
      },
      {
        "title": "No Task Tool Dependency",
        "body": "Unlike the previous agent-based approach, this skill executes directly without spawning subagents. The LLM reads SKILL.md and follows the workflow."
      },
      {
        "title": "Git Operations Optional",
        "body": "Commits are wrapped with availability checks - if not in a git repo, changes are still saved but not committed."
      },
      {
        "title": "Troubleshooting",
        "body": "No signals detected:\n\nSession may not have had corrections\nTry /reflect review to check pending items\n\nConflict warning:\n\nReview the existing rule cited\nDecide if new rule should override\nCan modify before applying\n\nAgent file not found:\n\nCheck agent name spelling\nUse /reflect status to see available targets\nMay need to create agent file first"
      },
      {
        "title": "File Structure",
        "body": "reflect/\n├── SKILL.md                      # This file\n├── scripts/\n│   ├── state_manager.py          # State file CRUD\n│   ├── signal_detector.py        # Pattern matching\n│   ├── metrics_updater.py        # Metrics aggregation\n│   └── output_generator.py       # Reflection file & index generation\n├── hooks/\n│   ├── precompact_reflect.py     # PreCompact hook integration\n│   ├── settings-snippet.json     # Settings.json examples\n│   └── README.md                 # Hook configuration guide\n├── references/\n│   ├── signal_patterns.md        # Detection rules\n│   ├── agent_mappings.md         # Target mappings\n│   └── skill_template.md         # Skill generation\n└── assets/\n    ├── reflection_template.md    # Output template\n    └── learnings_schema.yaml     # Schema definition"
      }
    ],
    "body": "Reflect - Self-Improvement Skill\nQuick Reference\nCommand\tAction\n/reflect\tAnalyze conversation for learnings\n/reflect on\tEnable auto-reflection\n/reflect off\tDisable auto-reflection\n/reflect status\tShow state and metrics\n/reflect review\tReview low-confidence learnings\n/reflect [agent]\tFocus on specific agent\nCore Philosophy\n\n\"Correct once, never again.\"\n\nWhen users correct behavior, those corrections become permanent improvements encoded into the agent system - across all future sessions.\n\nWorkflow\nStep 1: Initialize State\n\nCheck and initialize state files using the state manager:\n\n# Check for existing state\npython scripts/state_manager.py init\n\n# State directory is configurable via REFLECT_STATE_DIR env var\n# Default: ~/.reflect/ (portable) or ~/.claude/session/ (Claude Code)\n\n\nState includes:\n\nreflect-state.yaml - Toggle state, pending reviews\nreflect-metrics.yaml - Aggregate metrics\nlearnings.yaml - Log of all applied learnings\nStep 2: Scan Conversation for Signals\n\nUse the signal detector to identify learnings:\n\npython scripts/signal_detector.py --input conversation.txt\n\nSignal Confidence Levels\nConfidence\tTriggers\tExamples\nHIGH\tExplicit corrections\t\"never\", \"always\", \"wrong\", \"stop\", \"the rule is\"\nMEDIUM\tApproved approaches\t\"perfect\", \"exactly\", accepted output\nLOW\tObservations\tPatterns that worked, not validated\n\nSee signal_patterns.md for full detection rules.\n\nStep 3: Classify & Match to Target Files\n\nMap each signal to the appropriate target:\n\nLearning Categories:\n\nCategory\tTarget Files\nCode Style\tcode-reviewer, backend-developer, frontend-developer\nArchitecture\tsolution-architect, api-architect, architecture-reviewer\nProcess\tCLAUDE.md, orchestrator agents\nDomain\tDomain-specific agents, CLAUDE.md\nTools\tCLAUDE.md, relevant specialists\nNew Skill\t.claude/skills/{name}/SKILL.md\n\nSee agent_mappings.md for mapping rules.\n\nStep 4: Check for Skill-Worthy Signals\n\nSome learnings should become new skills rather than agent updates:\n\nSkill-Worthy Criteria:\n\nNon-obvious debugging (>10 min investigation)\nMisleading error (root cause different from message)\nWorkaround discovered through experimentation\nConfiguration insight (differs from documented)\nReusable pattern (helps in similar situations)\n\nQuality Gates (must pass all):\n\n Reusable: Will help with future tasks\n Non-trivial: Requires discovery, not just docs\n Specific: Can describe exact trigger conditions\n Verified: Solution actually worked\n No duplication: Doesn't exist already\n\nSee skill_template.md for skill creation guidelines.\n\nStep 5: Generate Proposals\n\nProduce output in this format:\n\n# Reflection Analysis\n\n## Session Context\n- **Date**: [timestamp]\n- **Messages Analyzed**: [count]\n- **Focus**: [all agents OR specific agent name]\n\n## Signals Detected\n\n| # | Signal | Confidence | Source Quote | Category |\n|---|--------|------------|--------------|----------|\n| 1 | [learning] | HIGH | \"[exact words]\" | Code Style |\n| 2 | [learning] | MEDIUM | \"[context]\" | Architecture |\n\n## Proposed Agent Updates\n\n### Change 1: Update [agent-name]\n\n**Target**: `[file path]`\n**Section**: [section name]\n**Confidence**: [HIGH/MEDIUM/LOW]\n**Rationale**: [why this change]\n\n```diff\n--- a/path/to/agent.md\n+++ b/path/to/agent.md\n@@ -82,6 +82,7 @@\n ## Section\n\n * Existing rule\n+* New rule from learning\n\nProposed New Skills\nSkill 1: [skill-name]\n\nQuality Gate Check:\n\n Reusable: [why]\n Non-trivial: [why]\n Specific: [trigger conditions]\n Verified: [how verified]\n No duplication: [checked against]\n\nWill create: .claude/skills/[skill-name]/SKILL.md\n\nConflict Check\n No conflicts with existing rules detected\nOR: Warning - potential conflict with [file:line]\nCommit Message\nreflect: add learnings from session [date]\n\nAgent updates:\n- [learning 1 summary]\n\nNew skills:\n- [skill-name]: [brief description]\n\nExtracted: [N] signals ([H] high, [M] medium, [L] low confidence)\n\nReview Prompt\n\nApply these changes?\n\nY - Apply all changes and commit\nN - Discard all changes\nmodify - Adjust specific changes\n1,3 - Apply only changes 1 and 3\ns1 - Apply only skill 1\nall-skills - Apply all skills, skip agent updates\n\n### Step 6: Handle User Response\n\n**On `Y` (approve):**\n1. Apply each change using Edit tool\n2. Run `git add` on modified files\n3. Commit with generated message\n4. Update learnings log\n5. Update metrics\n\n**On `N` (reject):**\n1. Discard proposed changes\n2. Log rejection for analysis\n3. Ask if user wants to modify any signals\n\n**On `modify`:**\n1. Present each change individually\n2. Allow editing the proposed addition\n3. Reconfirm before applying\n\n**On selective (e.g., `1,3`):**\n1. Apply only specified changes\n2. Log partial acceptance\n3. Commit only applied changes\n\n### Step 7: Update Metrics\n\n```bash\npython scripts/metrics_updater.py --accepted 3 --rejected 1 --confidence high:2,medium:1\n\nToggle Commands\nEnable Auto-Reflection\n/reflect on\n# Sets auto_reflect: true in state file\n# Will trigger on PreCompact hook\n\nDisable Auto-Reflection\n/reflect off\n# Sets auto_reflect: false in state file\n\nCheck Status\n/reflect status\n# Shows current state and metrics\n\nReview Pending\n/reflect review\n# Shows low-confidence learnings awaiting validation\n\nOutput Locations\n\nProject-level (versioned with repo):\n\n.claude/reflections/YYYY-MM-DD_HH-MM-SS.md - Full reflection\n.claude/reflections/index.md - Project summary\n.claude/skills/{name}/SKILL.md - New skills\n\nGlobal (user-level):\n\n~/.claude/reflections/by-project/{project}/ - Cross-project\n~/.claude/reflections/by-agent/{agent}/learnings.md - Per-agent\n~/.claude/reflections/index.md - Global summary\nMemory Integration\n\nSome learnings belong in auto-memory (~/.claude/projects/*/memory/MEMORY.md) rather than agent files:\n\nLearning Type\tBest Target\nBehavioral correction (\"always do X\")\tAgent file\nProject-specific pattern\tMEMORY.md\nRecurring bug/workaround\tNew skill OR MEMORY.md\nTool preference\tCLAUDE.md\nDomain knowledge\tMEMORY.md or compound-docs\n\nWhen a signal is LOW confidence and project-specific, prefer writing to MEMORY.md over modifying agents.\n\nSafety Guardrails\nHuman-in-the-Loop\nNEVER apply changes without explicit user approval\nAlways show full diff before applying\nAllow selective application\nGit Versioning\nAll changes committed with descriptive messages\nEasy rollback via git revert\nLearning history preserved\nIncremental Updates\nONLY add to existing sections\nNEVER delete or rewrite existing rules\nPreserve original structure\nConflict Detection\nCheck if proposed rule contradicts existing\nWarn user if conflict detected\nSuggest resolution strategy\nIntegration\nWith /handover\n\nIf auto-reflection is enabled, PreCompact hook triggers reflection before handover.\n\nWith Session Health\n\nAt 70%+ context (Yellow status), reminders to run /reflect are injected.\n\nHook Integration (Claude Code)\n\nThe skill includes hook scripts for automatic integration:\n\n# Install hook to your Claude hooks directory\ncp hooks/precompact_reflect.py ~/.claude/hooks/\n\n\nConfigure in ~/.claude/settings.json:\n\n{\n  \"hooks\": {\n    \"PreCompact\": [\n      {\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"uv run ~/.claude/hooks/precompact_reflect.py --auto\"\n          }\n        ]\n      }\n    ]\n  }\n}\n\n\nSee hooks/README.md for full configuration options.\n\nPortability\n\nThis skill works with any LLM tool that supports:\n\nFile read/write operations\nText pattern matching\nGit operations (optional, for commits)\nConfigurable State Location\n# Set custom state directory\nexport REFLECT_STATE_DIR=/path/to/state\n\n# Or use default\n# ~/.reflect/ (portable default)\n# ~/.claude/session/ (Claude Code default)\n\nNo Task Tool Dependency\n\nUnlike the previous agent-based approach, this skill executes directly without spawning subagents. The LLM reads SKILL.md and follows the workflow.\n\nGit Operations Optional\n\nCommits are wrapped with availability checks - if not in a git repo, changes are still saved but not committed.\n\nTroubleshooting\n\nNo signals detected:\n\nSession may not have had corrections\nTry /reflect review to check pending items\n\nConflict warning:\n\nReview the existing rule cited\nDecide if new rule should override\nCan modify before applying\n\nAgent file not found:\n\nCheck agent name spelling\nUse /reflect status to see available targets\nMay need to create agent file first\nFile Structure\nreflect/\n├── SKILL.md                      # This file\n├── scripts/\n│   ├── state_manager.py          # State file CRUD\n│   ├── signal_detector.py        # Pattern matching\n│   ├── metrics_updater.py        # Metrics aggregation\n│   └── output_generator.py       # Reflection file & index generation\n├── hooks/\n│   ├── precompact_reflect.py     # PreCompact hook integration\n│   ├── settings-snippet.json     # Settings.json examples\n│   └── README.md                 # Hook configuration guide\n├── references/\n│   ├── signal_patterns.md        # Detection rules\n│   ├── agent_mappings.md         # Target mappings\n│   └── skill_template.md         # Skill generation\n└── assets/\n    ├── reflection_template.md    # Output template\n    └── learnings_schema.yaml     # Schema definition"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/stevengonsalvez/reflect-learn",
    "publisherUrl": "https://clawhub.ai/stevengonsalvez/reflect-learn",
    "owner": "stevengonsalvez",
    "version": "2.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/reflect-learn",
    "downloadUrl": "https://openagent3.xyz/downloads/reflect-learn",
    "agentUrl": "https://openagent3.xyz/skills/reflect-learn/agent",
    "manifestUrl": "https://openagent3.xyz/skills/reflect-learn/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/reflect-learn/agent.md"
  }
}