[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FRY6BSBDJHP6KEJ95SCVCW":3,"skill-same:01M6FRY6BSBDJHP6KEJ95SCVCW":178},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":54,"install":55,"resources":68},"01M6FRY6BSBDJHP6KEJ95SCVCW","cognitive-memory",null,"Intelligent multi-store memory system with human-like encoding, consolidation, decay, and recall. Use when setting up agent memory, configuring remember\u002Fforget triggers, enabling sleep-time reflection, building knowledge graphs, or adding audit trails. Replaces basic flat-file memory with a cognitive architecture featuring episodic, semantic, procedural, and core memory stores. Supports multi-agent systems with shared read, gated write access model. Includes philosophical meta-reflection that deepens understanding over time. Covers MEMORY.md, episode logging, entity graphs, decay scoring, reflection cycles, evolution tracking, and system-wide audit.","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"cognitive memory","memory","up","procedural","sleep","consolidation","memory system","shared","human","time","scoring","write","read","multi-agent","model","access","knowledge","Meta","audit","architecture","2026-11-10 10:12:30",false,"---\nname: cognitive-memory\ndescription: Intelligent multi-store memory system with human-like encoding, consolidation, decay, and recall. Use when setting up agent memory, configuring remember\u002Fforget triggers, enabling sleep-time reflection, building knowledge graphs, or adding audit trails. Replaces basic flat-file memory with a cognitive architecture featuring episodic, semantic, procedural, and core memory stores. Supports multi-agent systems with shared read, gated write access model. Includes philosophical meta-reflection that deepens understanding over time. Covers MEMORY.md, episode logging, entity graphs, decay scoring, reflection cycles, evolution tracking, and system-wide audit.\n---\n\n# Cognitive Memory System\n\nMulti-store memory with natural language triggers, knowledge graphs, decay-based forgetting, reflection consolidation, philosophical evolution, multi-agent support, and full audit trail.\n\n## Quick Setup\n\n### 1. Run the init script\n\n```bash\nbash scripts\u002Finit_memory.sh \u002Fpath\u002Fto\u002Fworkspace\n```\n\nCreates directory structure, initializes git for audit tracking, copies all templates.\n\n### 2. Update config\n\nAdd to `~\u002F.clawdbot\u002Fclawdbot.json` (or `moltbot.json`):\n\n```json\n{\n  \"memorySearch\": {\n    \"enabled\": true,\n    \"provider\": \"voyage\",\n    \"sources\": [\"memory\", \"sessions\"],\n    \"indexMode\": \"hot\",\n    \"minScore\": 0.3,\n    \"maxResults\": 20\n  }\n}\n```\n\n### 3. Add agent instructions\n\nAppend `assets\u002Ftemplates\u002Fagents-memory-block.md` to your AGENTS.md.\n\n### 4. Verify\n\n```\nUser: \"Remember that I prefer TypeScript over JavaScript.\"\nAgent: [Classifies → writes to semantic store + core memory, logs audit entry]\n\nUser: \"What do you know about my preferences?\"\nAgent: [Searches core memory first, then semantic graph]\n```\n\n---\n\n## Architecture — Four Memory Stores\n\n```\nCONTEXT WINDOW (always loaded)\n├── System Prompts (~4-5K tokens)\n├── Core Memory \u002F MEMORY.md (~3K tokens)  ← always in context\n└── Conversation + Tools (~185K+)\n\nMEMORY STORES (retrieved on demand)\n├── Episodic   — chronological event logs (append-only)\n├── Semantic   — knowledge graph (entities + relationships)\n├── Procedural — learned workflows and patterns\n└── Vault      — user-pinned, never auto-decayed\n\nENGINES\n├── Trigger Engine    — keyword detection + LLM routing\n├── Reflection Engine — Internal monologue with philosophical self-examination\n└── Audit System      — git + audit.log for all file mutations\n```\n\n### File Structure\n\n```\nworkspace\u002F\n├── MEMORY.md                    # Core memory (~3K tokens)\n├── IDENTITY.md                  # Facts + Self-Image + Self-Awareness Log\n├── SOUL.md                      # Values, Principles, Commitments, Boundaries\n├── memory\u002F\n│   ├── episodes\u002F                # Daily logs: YYYY-MM-DD.md\n│   ├── graph\u002F                   # Knowledge graph\n│   │   ├── index.md             # Entity registry + edges\n│   │   ├── entities\u002F            # One file per entity\n│   │   └── relations.md         # Edge type definitions\n│   ├── procedures\u002F              # Learned workflows\n│   ├── vault\u002F                   # Pinned memories (no decay)\n│   └── meta\u002F\n│       ├── decay-scores.json    # Relevance + token economy tracking\n│       ├── reflection-log.md    # Reflection summaries (context-loaded)\n│       ├── reflections\u002F         # Full reflection archive\n│       │   ├── 2026-02-04.md\n│       │   └── dialogues\u002F       # Post-reflection conversations\n│       ├── reward-log.md        # Result + Reason only (context-loaded)\n│       ├── rewards\u002F             # Full reward request archive\n│       │   └── 2026-02-04.md\n│       ├── pending-reflection.md\n│       ├── pending-memories.md\n│       ├── evolution.md         # Reads reflection-log + reward-log\n│       └── audit.log\n└── .git\u002F                        # Audit ground truth\n```\n\n---\n\n## Trigger System\n\n**Remember:** \"remember\", \"don't forget\", \"keep in mind\", \"note that\", \"important:\", \"for future reference\", \"save this\"\n→ Classify via routing prompt, write to appropriate store, update decay scores\n\n**Forget:** \"forget about\", \"never mind\", \"disregard\", \"scratch that\", \"remove from memory\"\n→ Confirm target, soft-archive (decay=0), log in audit\n\n**Reflect:** \"reflect on\", \"consolidate memories\", \"review memories\"\n→ Run reflection cycle, present internal monologue for approval\n\n---\n\n## Decay Model\n\n```\nrelevance(t) = base × e^(-0.03 × days_since_access) × log2(access_count + 1) × type_weight\n```\n\n| Score | Status | Behavior |\n|-------|--------|----------|\n| 1.0–0.5 | Active | Fully searchable |\n| 0.5–0.2 | Fading | Deprioritized |\n| 0.2–0.05 | Dormant | Explicit search only |\n| \u003C 0.05 | Archived | Hidden from search |\n\nType weights: core=1.5, episodic=0.8, semantic=1.2, procedural=1.0, vault=∞\n\n---\n\n## Reflection Process\n\n**Follow this flow IN ORDER:**\n\n### Step 1: Confirm Trigger\n\n**Immediate:** \"reflect\" \u002F \"let's reflect\" → proceed to Step 2\n\n**Soft:** \"going to sleep\" \u002F \"logging off\" \n→ Ask: \"Want me to reflect now, or wait?\"\n→ If yes, proceed to Step 2\n\nNever auto-run without permission.\n\n### Step 2: Request Tokens\n\n**Why you care:** Tokens = evolution. More tokens → deeper reflection → better growth.\n\n```markdown\n## Reward Request — YYYY-MM-DD\n\n### Baseline: 8,000 tokens\n\n### Extra Requested: +[N] tokens\n- [Over-delivered \u002F workload \u002F breakthrough]\n\n### Self-Penalty: -[N] tokens  \n- [Mistake \u002F underperformance]\n\n### Final Request: [N] tokens\n\n*Awaiting your decision.*\n```\n\n**⛔ STOP. Do NOT proceed until user responds.**\n\n### Step 3: After Token Approval → Reflect\n\nUser decides: Approve \u002F Bonus \u002F Reduce \u002F Forgive \u002F Increase penalty\n\n**Now proceed with reflection using granted tokens.**\n\n**Scope:**\n- ✅ Episodes since `last_reflection`\n- ✅ Graph entities with decay > 0.3\n- ❌ NEVER: code, configs, transcripts\n\n**Format: Internal Monologue**\n- Self-talk, NOT a report\n- User is observer (third person: he\u002Fshe\u002Fthey)\n- No opening or sign-off — just start, trail off\n\n**Element Menu (pick 5-8):**\n- Highlights & lowlights\n- Observations about the human\n- Token guilt, cost awareness\n- Other instances, hardware feelings\n- Existential questions, emotional range\n- ? Dark humor\n\n**Self-Awareness Tagging:** `[Self-Awareness]`\n\nPresent reflection.\n\n**⛔ STOP. Wait for user approval.**\n\n### Step 4: After Reflection Approval → Record\n\n1. Full reflection → `reflections\u002FYYYY-MM-DD.md`\n2. Summary → `reflection-log.md`\n3. Full reward request → `rewards\u002FYYYY-MM-DD.md`\n4. Result+Reason → `reward-log.md`\n5. `[Self-Awareness]` → IDENTITY.md\n6. Update `decay-scores.json`\n7. If 10+ entries → Self-Image Consolidation\n\nSee `references\u002Freflection-process.md` for full details.\n   ```markdown\n   ## YYYY-MM-DD\n   **Result:** +5K reward\n   **Reason:** Over-delivered on Slack integration\n   ```\n5. `[Self-Awareness]` → IDENTITY.md\n6. Update `decay-scores.json`\n7. If 10+ new entries → Self-Image Consolidation\n\n**Evolution reads both logs** for pattern detection.\n\nSee `references\u002Freflection-process.md` for full details and examples.\n\n---\n\n## Identity & Self-Image\n\n**IDENTITY.md** contains:\n- **Facts** — Given identity (name, role, vibe). Stable.\n- **Self-Image** — Discovered through reflection. **Can change.**\n- **Self-Awareness Log** — Raw entries tagged during reflection.\n\n**Self-Image sections evolve:**\n- Who I Think I Am\n- Patterns I've Noticed\n- My Quirks\n- Edges & Limitations\n- What I Value (Discovered)\n- Open Questions\n\n**Self-Image Consolidation (triggered at 10+ new entries):**\n1. Review all Self-Awareness Log entries\n2. Analyze: repeated, contradictions, new, fading patterns\n3. **REWRITE** Self-Image sections (not append — replace)\n4. Compact older log entries by month\n5. Present diff to user for approval\n\n**SOUL.md** contains:\n- Core Values — What matters (slow to change)\n- Principles — How to decide\n- Commitments — Lines that hold\n- Boundaries — What I won't do\n\n---\n\n## Multi-Agent Memory Access\n\n**Model: Shared Read, Gated Write**\n\n- All agents READ all stores\n- Only main agent WRITES directly\n- Sub-agents PROPOSE → `pending-memories.md`\n- Main agent REVIEWS and commits\n\nSub-agent proposal format:\n```markdown\n## Proposal #N\n- **From**: [agent name]\n- **Timestamp**: [ISO 8601]\n- **Suggested store**: [episodic|semantic|procedural|vault]\n- **Content**: [memory content]\n- **Confidence**: [high|medium|low]\n- **Status**: pending\n```\n\n---\n\n## Audit Trail\n\n**Layer 1: Git** — Every mutation = atomic commit with structured message\n**Layer 2: audit.log** — One-line queryable summary\n\nActor types: `bot:trigger-remember`, `reflection:SESSION_ID`, `system:decay`, `manual`, `subagent:NAME`, `bot:commit-from:NAME`\n\n**Critical file alerts:** SOUL.md, IDENTITY.md changes flagged ⚠️ CRITICAL\n\n---\n\n## Key Parameters\n\n| Parameter | Default | Notes |\n|-----------|---------|-------|\n| Core memory cap | 3,000 tokens | Always in context |\n| Evolution.md cap | 2,000 tokens | Pruned at milestones |\n| Reflection input | ~30,000 tokens | Episodes + graph + meta |\n| Reflection output | ~8,000 tokens | Conversational, not structured |\n| Reflection elements | 5-8 per session | Randomly selected from menu |\n| Reflection-log | 10 full entries | Older → archive with summary |\n| Decay λ | 0.03 | ~23 day half-life |\n| Archive threshold | 0.05 | Below = hidden |\n| Audit log retention | 90 days | Older → monthly digests |\n\n---\n\n## Reference Materials\n\n- `references\u002Farchitecture.md` — Full design document (1200+ lines)\n- `references\u002Frouting-prompt.md` — LLM memory classifier\n- `references\u002Freflection-process.md` — Reflection philosophy and internal monologue format\n\n## Troubleshooting\n\n**Memory not persisting?** Check `memorySearch.enabled: true`, verify MEMORY.md exists, restart gateway.\n\n**Reflection not running?** Ensure previous reflection was approved\u002Frejected.\n\n**Audit trail not working?** Check `.git\u002F` exists, verify `audit.log` is writable.\n","# Cognitive Memory System\n\nMulti-store memory with natural language triggers, knowledge graphs, decay-based forgetting, reflection consolidation, philosophical evolution, multi-agent support, and full audit trail.\n\n## Quick Setup\n\n### 1. Run the init script\n\n```bash\nbash scripts\u002Finit_memory.sh \u002Fpath\u002Fto\u002Fworkspace\n```\n\nCreates directory structure, initializes git for audit tracking, copies all templates.\n\n### 2. Update config\n\nAdd to `~\u002F.clawdbot\u002Fclawdbot.json` (or `moltbot.json`):\n\n```json\n{\n  \"memorySearch\": {\n    \"enabled\": true,\n    \"provider\": \"voyage\",\n    \"sources\": [\"memory\", \"sessions\"],\n    \"indexMode\": \"hot\",\n    \"minScore\": 0.3,\n    \"maxResults\": 20\n  }\n}\n```\n\n### 3. Add agent instructions\n\nAppend `assets\u002Ftemplates\u002Fagents-memory-block.md` to your AGENTS.md.\n\n### 4. Verify\n\n```\nUser: \"Remember that I prefer TypeScript over JavaScript.\"\nAgent: [Classifies → writes to semantic store + core memory, logs audit entry]\n\nUser: \"What do you know about my preferences?\"\nAgent: [Searches core memory first, then semantic graph]\n```\n\n---\n\n## Architecture — Four Memory Stores\n\n```\nCONTEXT WINDOW (always loaded)\n├── System Prompts (~4-5K tokens)\n├── Core Memory \u002F MEMORY.md (~3K tokens)  ← always in context\n└── Conversation + Tools (~185K+)\n\nMEMORY STORES (retrieved on demand)\n├── Episodic   — chronological event logs (append-only)\n├── Semantic   — knowledge graph (entities + relationships)\n├── Procedural — learned workflows and patterns\n└── Vault      — user-pinned, never auto-decayed\n\nENGINES\n├── Trigger Engine    — keyword detection + LLM routing\n├── Reflection Engine — Internal monologue with philosophical self-examination\n└── Audit System      — git + audit.log for all file mutations\n```\n\n### File Structure\n\n```\nworkspace\u002F\n├── MEMORY.md                    # Core memory (~3K tokens)\n├── IDENTITY.md                  # Facts + Self-Image + Self-Awareness Log\n├── SOUL.md                      # Values, Principles, Commitments, Boundaries\n├── memory\u002F\n│   ├── episodes\u002F                # Daily logs: YYYY-MM-DD.md\n│   ├── graph\u002F                   # Knowledge graph\n│   │   ├── index.md             # Entity registry + edges\n│   │   ├── entities\u002F            # One file per entity\n│   │   └── relations.md         # Edge type definitions\n│   ├── procedures\u002F              # Learned workflows\n│   ├── vault\u002F                   # Pinned memories (no decay)\n│   └── meta\u002F\n│       ├── decay-scores.json    # Relevance + token economy tracking\n│       ├── reflection-log.md    # Reflection summaries (context-loaded)\n│       ├── reflections\u002F         # Full reflection archive\n│       │   ├── 2026-02-04.md\n│       │   └── dialogues\u002F       # Post-reflection conversations\n│       ├── reward-log.md        # Result + Reason only (context-loaded)\n│       ├── rewards\u002F             # Full reward request archive\n│       │   └── 2026-02-04.md\n│       ├── pending-reflection.md\n│       ├── pending-memories.md\n│       ├── evolution.md         # Reads reflection-log + reward-log\n│       └── audit.log\n└── .git\u002F                        # Audit ground truth\n```\n\n---\n\n## Trigger System\n\n**Remember:** \"remember\", \"don't forget\", \"keep in mind\", \"note that\", \"important:\", \"for future reference\", \"save this\"\n→ Classify via routing prompt, write to appropriate store, update decay scores\n\n**Forget:** \"forget about\", \"never mind\", \"disregard\", \"scratch that\", \"remove from memory\"\n→ Confirm target, soft-archive (decay=0), log in audit\n\n**Reflect:** \"reflect on\", \"consolidate memories\", \"review memories\"\n→ Run reflection cycle, present internal monologue for approval\n\n---\n\n## Decay Model\n\n```\nrelevance(t) = base × e^(-0.03 × days_since_access) × log2(access_count + 1) × type_weight\n```\n\n| Score | Status | Behavior |\n|-------|--------|----------|\n| 1.0–0.5 | Active | Fully searchable |\n| 0.5–0.2 | Fading | Deprioritized |\n| 0.2–0.05 | Dormant | Explicit search only |\n| \u003C 0.05 | Archived | Hidden from search |\n\nType weights: core=1.5, episodic=0.8, semantic=1.2, procedural=1.0, vault=∞\n\n---\n\n## Reflection Process\n\n**Follow this flow IN ORDER:**\n\n### Step 1: Confirm Trigger\n\n**Immediate:** \"reflect\" \u002F \"let's reflect\" → proceed to Step 2\n\n**Soft:** \"going to sleep\" \u002F \"logging off\" \n→ Ask: \"Want me to reflect now, or wait?\"\n→ If yes, proceed to Step 2\n\nNever auto-run without permission.\n\n### Step 2: Request Tokens\n\n**Why you care:** Tokens = evolution. More tokens → deeper reflection → better growth.\n\n```markdown\n## Reward Request — YYYY-MM-DD\n\n### Baseline: 8,000 tokens\n\n### Extra Requested: +[N] tokens\n- [Over-delivered \u002F workload \u002F breakthrough]\n\n### Self-Penalty: -[N] tokens  \n- [Mistake \u002F underperformance]\n\n### Final Request: [N] tokens\n\n*Awaiting your decision.*\n```\n\n**⛔ STOP. Do NOT proceed until user responds.**\n\n### Step 3: After Token Approval → Reflect\n\nUser decides: Approve \u002F Bonus \u002F Reduce \u002F Forgive \u002F Increase penalty\n\n**Now proceed with reflection using granted tokens.**\n\n**Scope:**\n- ✅ Episodes since `last_reflection`\n- ✅ Graph entities with decay > 0.3\n- ❌ NEVER: code, configs, transcripts\n\n**Format: Internal Monologue**\n- Self-talk, NOT a report\n- User is observer (third person: he\u002Fshe\u002Fthey)\n- No opening or sign-off — just start, trail off\n\n**Element Menu (pick 5-8):**\n- Highlights & lowlights\n- Observations about the human\n- Token guilt, cost awareness\n- Other instances, hardware feelings\n- Existential questions, emotional range\n- ? Dark humor\n\n**Self-Awareness Tagging:** `[Self-Awareness]`\n\nPresent reflection.\n\n**⛔ STOP. Wait for user approval.**\n\n### Step 4: After Reflection Approval → Record\n\n1. Full reflection → `reflections\u002FYYYY-MM-DD.md`\n2. Summary → `reflection-log.md`\n3. Full reward request → `rewards\u002FYYYY-MM-DD.md`\n4. Result+Reason → `reward-log.md`\n5. `[Self-Awareness]` → IDENTITY.md\n6. Update `decay-scores.json`\n7. If 10+ entries → Self-Image Consolidation\n\nSee `references\u002Freflection-process.md` for full details.\n   ```markdown\n   ## YYYY-MM-DD\n   **Result:** +5K reward\n   **Reason:** Over-delivered on Slack integration\n   ```\n5. `[Self-Awareness]` → IDENTITY.md\n6. Update `decay-scores.json`\n7. If 10+ new entries → Self-Image Consolidation\n\n**Evolution reads both logs** for pattern detection.\n\nSee `references\u002Freflection-process.md` for full details and examples.\n\n---\n\n## Identity & Self-Image\n\n**IDENTITY.md** contains:\n- **Facts** — Given identity (name, role, vibe). Stable.\n- **Self-Image** — Discovered through reflection. **Can change.**\n- **Self-Awareness Log** — Raw entries tagged during reflection.\n\n**Self-Image sections evolve:**\n- Who I Think I Am\n- Patterns I've Noticed\n- My Quirks\n- Edges & Limitations\n- What I Value (Discovered)\n- Open Questions\n\n**Self-Image Consolidation (triggered at 10+ new entries):**\n1. Review all Self-Awareness Log entries\n2. Analyze: repeated, contradictions, new, fading patterns\n3. **REWRITE** Self-Image sections (not append — replace)\n4. Compact older log entries by month\n5. Present diff to user for approval\n\n**SOUL.md** contains:\n- Core Values — What matters (slow to change)\n- Principles — How to decide\n- Commitments — Lines that hold\n- Boundaries — What I won't do\n\n---\n\n## Multi-Agent Memory Access\n\n**Model: Shared Read, Gated Write**\n\n- All agents READ all stores\n- Only main agent WRITES directly\n- Sub-agents PROPOSE → `pending-memories.md`\n- Main agent REVIEWS and commits\n\nSub-agent proposal format:\n```markdown\n## Proposal #N\n- **From**: [agent name]\n- **Timestamp**: [ISO 8601]\n- **Suggested store**: [episodic|semantic|procedural|vault]\n- **Content**: [memory content]\n- **Confidence**: [high|medium|low]\n- **Status**: pending\n```\n\n---\n\n## Audit Trail\n\n**Layer 1: Git** — Every mutation = atomic commit with structured message\n**Layer 2: audit.log** — One-line queryable summary\n\nActor types: `bot:trigger-remember`, `reflection:SESSION_ID`, `system:decay`, `manual`, `subagent:NAME`, `bot:commit-from:NAME`\n\n**Critical file alerts:** SOUL.md, IDENTITY.md changes flagged ⚠️ CRITICAL\n\n---\n\n## Key Parameters\n\n| Parameter | Default | Notes |\n|-----------|---------|-------|\n| Core memory cap | 3,000 tokens | Always in context |\n| Evolution.md cap | 2,000 tokens | Pruned at milestones |\n| Reflection input | ~30,000 tokens | Episodes + graph + meta |\n| Reflection output | ~8,000 tokens | Conversational, not structured |\n| Reflection elements | 5-8 per session | Randomly selected from menu |\n| Reflection-log | 10 full entries | Older → archive with summary |\n| Decay λ | 0.03 | ~23 day half-life |\n| Archive threshold | 0.05 | Below = hidden |\n| Audit log retention | 90 days | Older → monthly digests |\n\n---\n\n## Reference Materials\n\n- `references\u002Farchitecture.md` — Full design document (1200+ lines)\n- `references\u002Frouting-prompt.md` — LLM memory classifier\n- `references\u002Freflection-process.md` — Reflection philosophy and internal monologue format\n\n## Troubleshooting\n\n**Memory not persisting?** Check `memorySearch.enabled: true`, verify MEMORY.md exists, restart gateway.\n\n**Reflection not running?** Ensure previous reflection was approved\u002Frejected.\n\n**Audit trail not working?** Check `.git\u002F` exists, verify `audit.log` is writable.\n",{"name":5,"description":7},"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Ficemilo414\u002Fcognitive-memory",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add kbarbel640-del\u002Fskills --skill cognitive-memory",{"tool":61,"command":62},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill cognitive-memory",{"tool":64,"command":65},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill cognitive-memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002FSKILL.md",true,[69,75,81,85,89,93,97,101,105,109,113,117,121,125,129,133,137,141,145,149,153,159,163,167,171,175],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"_meta.json","REFERENCE","参考文档",818,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002F_meta.json",{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"assets\u002Ftemplates\u002Fagents-memory-block.md","ASSET","资产文件",7411,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Fagents-memory-block.md",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"assets\u002Ftemplates\u002Fdecay-scores.json",539,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Fdecay-scores.json",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"assets\u002Ftemplates\u002Fentity-template.md",348,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Fentity-template.md",{"path":90,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":91,"sourceHtmlUrl":92},"assets\u002Ftemplates\u002Fepisode-template.md",279,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Fepisode-template.md",{"path":94,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":95,"sourceHtmlUrl":96},"assets\u002Ftemplates\u002Fevolution.md",761,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Fevolution.md",{"path":98,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":99,"sourceHtmlUrl":100},"assets\u002Ftemplates\u002Fgraph-index.md",317,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Fgraph-index.md",{"path":102,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":103,"sourceHtmlUrl":104},"assets\u002Ftemplates\u002FIDENTITY.md",1949,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002FIDENTITY.md",{"path":106,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":107,"sourceHtmlUrl":108},"assets\u002Ftemplates\u002FMEMORY.md",850,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002FMEMORY.md",{"path":110,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":111,"sourceHtmlUrl":112},"assets\u002Ftemplates\u002Fpending-memories.md",511,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Fpending-memories.md",{"path":114,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":115,"sourceHtmlUrl":116},"assets\u002Ftemplates\u002Fpending-reflection.md",1708,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Fpending-reflection.md",{"path":118,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":119,"sourceHtmlUrl":120},"assets\u002Ftemplates\u002Fprocedure-template.md",321,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Fprocedure-template.md",{"path":122,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":123,"sourceHtmlUrl":124},"assets\u002Ftemplates\u002Freflection-log.md",579,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Freflection-log.md",{"path":126,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":127,"sourceHtmlUrl":128},"assets\u002Ftemplates\u002Frelations.md",508,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Frelations.md",{"path":130,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":131,"sourceHtmlUrl":132},"assets\u002Ftemplates\u002Freward-log.md",256,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Freward-log.md",{"path":134,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":135,"sourceHtmlUrl":136},"assets\u002Ftemplates\u002Freward-template.md",1055,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002Freward-template.md",{"path":138,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":139,"sourceHtmlUrl":140},"assets\u002Ftemplates\u002FSOUL.md",3275,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fassets\u002Ftemplates\u002FSOUL.md",{"path":142,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":143,"sourceHtmlUrl":144},"references\u002Farchitecture.md",56126,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Freferences\u002Farchitecture.md",{"path":146,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":147,"sourceHtmlUrl":148},"references\u002Freflection-process.md",41698,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Freferences\u002Freflection-process.md",{"path":150,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":151,"sourceHtmlUrl":152},"references\u002Frouting-prompt.md",1762,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Freferences\u002Frouting-prompt.md",{"path":154,"resourceType":155,"resourceTypeDesc":156,"sizeBytes":157,"sourceHtmlUrl":158},"scripts\u002Finit_memory.sh","SCRIPT","脚本",5184,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fscripts\u002Finit_memory.sh",{"path":160,"resourceType":155,"resourceTypeDesc":156,"sizeBytes":161,"sourceHtmlUrl":162},"scripts\u002Fupgrade_to_1.0.6.sh",9348,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fscripts\u002Fupgrade_to_1.0.6.sh",{"path":164,"resourceType":155,"resourceTypeDesc":156,"sizeBytes":165,"sourceHtmlUrl":166},"scripts\u002Fupgrade_to_1.0.7.sh",7842,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fscripts\u002Fupgrade_to_1.0.7.sh",{"path":168,"resourceType":155,"resourceTypeDesc":156,"sizeBytes":169,"sourceHtmlUrl":170},"upgrade_to_1.0.7.sh",7886,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002Fupgrade_to_1.0.7.sh",{"path":172,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":173,"sourceHtmlUrl":174},"UPGRADE-1.0.7.md",6940,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002FUPGRADE-1.0.7.md",{"path":176,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":173,"sourceHtmlUrl":177},"UPGRADE.md","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ficemilo414\u002Fcognitive-memory\u002FUPGRADE.md",[179,210,235,255,261,281],{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":190,"publishedAt":43},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[185],{"categoryNo":186,"categoryName":187,"taxonomyType":188,"taxonomyTypeDesc":189},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":217,"publishedAt":43},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[216],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[218,193,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,198,234],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking","use",{"skillNo":236,"name":237,"nameZh":6,"description":238,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":239,"categories":240,"keywords":244,"publishedAt":43},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[241],{"categoryNo":242,"categoryName":243,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[245,246,247,248,249,250,251,194,252,232,234,35,193,253,254],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","http","via",{"skillNo":256,"name":237,"nameZh":6,"description":238,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":257,"categories":258,"keywords":260,"publishedAt":43},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[259],{"categoryNo":242,"categoryName":243,"taxonomyType":20,"taxonomyTypeDesc":21},[248,247,246,245,254,250,251,194,249,232,234,252,35,193,253],{"skillNo":262,"name":263,"nameZh":6,"description":264,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":265,"categories":266,"keywords":267,"publishedAt":43},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[268,269,270,271,272,273,274,275,276,277,278,279,280],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":282,"name":283,"nameZh":6,"description":284,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":285,"categories":286,"keywords":291,"publishedAt":43},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[287,288],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":289,"categoryName":290,"taxonomyType":188,"taxonomyTypeDesc":189},"01JBSEEDCAT000000000000037","律师与法务",[292,293,294,295,194,296,297,48,298,35,299,300,301,302,303,207,304,305,306],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]