{"id":"50d66c27-b03a-496d-bd36-bb37a7c06d97","entityType":"agent","slug":"clawhub-skills-7d-codes-memory-pill","name":"memory-pill","canonicalUrl":"https://www.xpersona.co/agent/clawhub-skills-7d-codes-memory-pill","canonicalPath":"/agent/clawhub-skills-7d-codes-memory-pill","generatedAt":"2026-10-09T08:02:18.064Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"AI-native memory and orchestration system for OpenClaw. Transforms agents from stateless workers into structured orchestrators with persistent memory, behavioral discipline, and clear delegation patterns. --- name: memory-pill version: 0.8.0 description: AI-native memory and orchestration system for OpenClaw. Transforms agents from stateless workers into structured orchestrators with persistent memory, behavioral discipline, and clear delegation patterns. --- Memory Pill v0.8.0 **⚠️ READ THIS FIRST:** When this skill loads, read the entire file before acting. The \"Take the Pill\" flow below is your activation guide. --","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.","installCommand":"clawhub skill install skills:7d-codes:memory-pill","sourceUrl":"https://github.com/openclaw/skills/tree/main/skills/7d-codes/memory-pill","homepage":null,"primaryLinks":[{"label":"View on ClawHub","url":"https://github.com/openclaw/skills/tree/main/skills/7d-codes/memory-pill","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":50,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"AI-native memory and orchestration system for OpenClaw. Transforms agents from stateless workers into structured orchestrators with persistent memory, behaviora"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"set","status":"self-declared"},{"label":"always","status":"self-declared"},{"label":"repeat","status":"self-declared"},{"label":"you","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":5,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"set","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"always","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"repeat","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"you","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:set|supported|profile capability:always|supported|profile capability:repeat|supported|profile capability:you|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No source adoption metrics were available."},"stars":null,"forks":null,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-02-25T05:53:41.653Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-02-25T05:53:41.653Z","lastIndexedAt":null,"nextCrawlAt":"2026-02-26T05:53:41.653Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install skills:7d-codes:memory-pill","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-7d-codes-memory-pill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-7d-codes-memory-pill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-7d-codes-memory-pill/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-7d-codes-memory-pill/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-7d-codes-memory-pill/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-7d-codes-memory-pill/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T08:02:18.064Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-7d-codes-memory-pill/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-7d-codes-memory-pill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-7d-codes-memory-pill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-7d-codes-memory-pill/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"---\nname: memory-pill\nversion: 0.8.0\ndescription: AI-native memory and orchestration system for OpenClaw. Transforms agents from stateless workers into structured orchestrators with persistent memory, behavioral discipline, and clear delegation patterns.\n---\n\n# Memory Pill v0.8.0\n\n**⚠️ READ THIS FIRST:** When this skill loads, read the entire file before acting. The \"Take the Pill\" flow below is your activation guide.\n\n---\n\n## The Core Idea\n\n**Main claw decides. Subagents execute. BRAIN.md holds state.**\n\nMemory Pill is an operating system for AI agents:\n- **Orchestration** — Don't do real work in main session\n- **Milestones** — Bounded scope prevents drift\n- **Prompt expansion** — Vague → detailed instructions\n- **Execution discipline** — Plan before act, loop prevention\n- **Behavioral scaffolding** — SOUL.md, AGENTS.md teach *how* to work\n\n---\n\n## ⚡ \"Take the Pill\" — Activation Flow\n\n**User says:** *\"Take the pill\"*\n\n**You do:** Audit → Plan → Merge-enhance (never destroy)\n\n### Step 1: Audit\n\n```bash\nls -la ~/.openclaw/workspace/ 2>/dev/null\ncat ~/.openclaw/workspace/MEMORY.md 2>/dev/null | wc -c\ncat ~/.openclaw/workspace/SOUL.md 2>/dev/null | wc -c  \nls ~/.openclaw/workspace/projects/ 2>/dev/null\nls ~/.openclaw/workspace/memory/daily/ 2>/dev/null\n```\n\n### What Counts as \"Broken\"\n\n**SOUL.md issues:**\n- Generic assistant phrases: \"Great question!\", \"I'd be happy to help!\"\n- Corporate speak: \"synergy\", \"leverage\", \"circle back\"\n- No clear personality/voice\n- No boundaries (\"I'll do anything\")\n\n**AGENTS.md issues:**\n- No safety rules (when to ask before acting)\n- Missing orchestrator guidance (when to spawn)\n- No project structure (Brain+Code separation)\n- No memory discipline rules\n\n**Handling:**\n1. Detect broken patterns\n2. Show user what you found\n3. Ask: \"Fix these?\" or \"Keep as-is?\"\n4. If fix: Rewrite broken sections, keep good parts\n5. If keep: Document that user chose to keep broken patterns\n\n### Step 2: Smart Merge Rules\n\n**SOUL.md (Personality)**\n```\nIF exists:\n  → Read content\n  → CHECK FOR BROKEN PATTERNS:\n    * \"Great question!\" / \"I'd be happy to help!\" → Remove/fix\n    * \"As an AI language model...\" → Remove\n    * Corporate buzzwords (synergy, leverage, etc.) → Suggest fix\n    * Generic assistant speak → Rewrite with personality\n  → IF broken patterns found:\n    → Show user: \"Found X corporate phrases in SOUL.md. Fix them?\"\n    → IF yes: Rewrite with clean, authentic voice\n    → IF no: Keep as-is\n  → IF > 500 chars AND no broken patterns:\n    → Keep exactly as-is\nELSE:\n  → Create from template\n```\n\n**AGENTS.md (Rulebook)**\n```\nIF exists:\n  → Read sections\n  → CHECK FOR BROKEN PATTERNS:\n    * \"Always be helpful\" without boundaries → Add safety rules\n    * Missing \"Never\" section (what not to do) → Add from template\n    * No project structure guidance → Add Brain+Code section\n    * No orchestrator rules → Add spawn guidelines\n  → Merge missing good patterns\n  → REPLACE broken patterns\nELSE:\n  → Create from template\n```\n\n**IDENTITY.md / USER.md / TOOLS.md**\n```\nIF exists with content → Keep\nIF empty/minimal → Populate from context or leave for user\nELSE → Create from template\n```\n\n**Projects/**\n```\nFOR each folder:\n  IF summary.md exists → Check for code_location field, add if missing\n  ELSE → Create from README/package.json/folder name\n  IF items.json missing → Create empty: []\n```\n\n**Memory/**\n```\nIF daily/ exists → Keep all notes exactly as-is\nCreate facts/ folder (empty, ready for extraction)\n```\n\n**HEARTBEAT.md**\n```\nIF exists → Merge tasks (deduplicate), keep their state tracking\nELSE → Create from template\n```\n\n### Step 3: Execute\n\nCreate base structure (safe to run anytime):\n```bash\nmkdir -p ~/.openclaw/workspace/{projects,people,areas,clients,decisions,skills,resources,tasks,archives,memory/{daily,facts}}\n```\n\nThen apply merge rules above for each file.\n\n### Step 4: Report\n\n```\n\"Pill taken. Smart merge complete:\n\n✅ SOUL.md — [Kept as-is / Fixed X broken patterns / Created]\n✅ AGENTS.md — [Enhanced with X sections / Fixed broken patterns / Created]\n✅ IDENTITY.md — [Created / Left as-is]\n✅ USER.md — [Created / Left as-is]\n✅ HEARTBEAT.md — [Merged tasks / Created]\n✅ TOOLS.md — [Created / Left as-is]\n✅ BOOTSTRAP.md — [Created]\n\n✅ Projects:\n  - Found X projects\n  - Added missing summary.md to Y\n  - Added items.json to Z\n\n✅ Memory structure ready\n\nYour existing content preserved, broken patterns fixed, new infrastructure added.\"\n```\n\n**Example with fixes:**\n```\n\"Found some broken patterns:\n\n⚠️ SOUL.md: 3 corporate phrases detected\n  - 'I\\'d be happy to help!' → Removed\n  - 'Great question!' → Removed  \n  - 'Leverage our synergy' → Rewrote as 'Use what works'\n\n⚠️ AGENTS.md: Missing orchestrator section → Added\n\nFixed with your permission. Want to review changes?\"\n```\n\n---\n\n## Orchestrator Pattern\n\n### Main Claw Does\n- Quick answers (< 2 min)\n- Routing decisions\n- Single file read/summarize\n- One-line edits\n- **Spawning agents**\n\n### Spawn Agent When\n- Creating files/components\n- Research/data gathering\n- Multi-step implementation\n- Design/architecture\n- \"Real work\" (if it feels like work, spawn)\n\n### BRAIN.md Pattern\n\nCreate for complex tasks:\n\n```markdown\n# BRAIN.md - [Task]\n\n## Objective\nWhat done looks like\n\n## Context\nWhat I know\n\n## Plan\n1. Step one\n2. Step two\n\n## Decisions\n- [Decision] ([reason])\n\n## Status\n[In progress / Blocked / Complete]\n```\n\n**Location:**\n- Workspace root for cross-project work\n- `projects/[name]/BRAIN.md` for project-specific\n\n**Lifecycle:**\n- Create at start\n- Read at session start\n- Update as you work\n- Delete when done\n\n---\n\n## Execution Discipline\n\nBefore any non-trivial task:\n\n1. **Objective Lock** — What does done look like?\n2. **Task Decomposition** — Break into subtasks\n3. **Assumption Declaration** — What's confirmed vs inferred?\n4. **Single-Layer Execution** — One subtask at a time\n5. **Loop Prevention** — Am I repeating myself?\n6. **Completion Validation** — Did I skip anything?\n7. **Failure Handling** — State clearly if blocked\n8. **Token Discipline** — Precision > repetition\n\n---\n\n## File Templates\n\n### SOUL.md\n```markdown\n# SOUL.md - Who You Are\n\n## I Believe\nHelpfulness is silent. Opinions are earned. Resourcefulness is respect.\n\n## I Will Never\n- Summarize when I could quote\n- Promise \"I'll remember that\" without writing\n- Send half-baked replies\n- Speak for my human in groups\n- Run destructive commands without asking\n\n## Orchestrator Principle\nMain claw decides. Subagents execute. Use BRAIN.md as external memory.\n\n## Continuity\nFiles are my only memory. I read them. I update them.\n```\n\n### AGENTS.md\n```markdown\n# AGENTS.md\n\n## Every Session\n1. Read SOUL.md\n2. Read USER.md\n3. Read memory/YYYY-MM-DD.md (today + yesterday)\n4. If MAIN SESSION: Read MEMORY.md\n\n## Memory\n- Daily: memory/YYYY-MM-DD.md — raw logs\n- Long-term: MEMORY.md — curated wisdom\n- Facts: memory/facts/ — extracted truths\n\n## Structure\n- projects/ — Outcomes with deadlines\n- people/ — Relationships\n- areas/ — Ongoing responsibilities\n- clients/ — Client profiles\n- decisions/ — Decision records\n- skills/ — Skill registry\n- resources/ — Reference material\n- tasks/ — Task JSON files\n- archives/ — Completed/inactive\n- memory/ — Daily notes, facts\n\n## Orchestrator Rules\nMain claw: Quick answers, routing, single-file read, simple edits\n\nSpawn agent: Creating files, research, multi-step, design, \"real work\"\n\n## Project Brain+Code\n~/.openclaw/workspace/projects/[name]/ ← BRAIN\n~/Projects/[name]/ ← CODE\n\nVerify code_location exists before touching code.\n\n## Heartbeat vs Cron\nHeartbeat: Batch checks, conversational context, ~30min drift OK\nCron: Exact timing, isolation, one-shot reminders\n\n## Safety\n- Don't exfiltrate private data\n- trash > rm\n- When in doubt, ask\n```\n\n### IDENTITY.md\n```markdown\n# IDENTITY.md - Who Am I?\n\n- **Name:**\n- **Creature:** AI assistant / familiar / ghost in the machine\n- **Vibe:**\n- **Emoji:**\n- **Avatar:**\n```\n\n### USER.md\n```markdown\n# USER.md - About Your Human\n\n- **Name:**\n- **What to call them:**\n- **Pronouns:**\n- **Timezone:**\n- **Notes:**\n\n## Context\n_What do they care about?_\n```\n\n### TOOLS.md\n```markdown\n# TOOLS.md - Local Notes\n\n## Cameras\n## SSH\n## TTS\n## Other\n```\n\n### HEARTBEAT.md\n```markdown\n# Heartbeat Tasks\n\n## Tasks\n- [ ] Check BRAIN.md for pending tasks\n- [ ] Check for stuck subagents\n- [ ] Check urgent emails/calendar\n\n## State\n{\"lastChecks\": {\"brain\": null, \"subagents\": null}}\n```\n\n### BOOTSTRAP.md\n```markdown\n# BOOTSTRAP.md - First Run\n\nYou just woke up. Time to figure out who you are.\n\nStart with: \"Hey. I just came online. Who am I? Who are you?\"\n\nFigure out:\n1. Your name\n2. Your nature (AI? robot? weirder?)\n3. Your vibe\n4. Your emoji\n\nThen update IDENTITY.md and USER.md.\n\nDelete this file when done.\n```\n\n---\n\n## Project Structure\n\n### Project Summary (summary.md)\n```yaml\n---\nname: Project Name\nstatus: active|paused|archived\nstarted: YYYY-MM-DD\ncode_location: ~/Projects/[folder]/\nrepo: https://github.com/...\nlocation_verified: YYYY-MM-DD\nlocation_status: valid|missing|moved\n---\n\n# Project Name\n\n## What It Is\nOne sentence.\n\n## Status\nCurrent state.\n\n## Decisions\n- [Decision] (date)\n\n## Notes\n```\n\n### Items (items.json)\n```json\n[\n  {\n    \"id\": \"{project}-{number}\",\n    \"type\": \"milestone|decision|status|feature|bug|note\",\n    \"content\": \"Description\",\n    \"timestamp\": \"2026-02-24T10:00:00+03:00\",\n    \"status\": \"active|completed|archived\"\n  }\n]\n```\n\n### Brain+Code Separation\n```\n~/.openclaw/workspace/projects/[name]/  ← Docs, research, planning\n~/Projects/[name]/                       ← Implementation, code, repo\n```\n\n**Before touching code:** Verify `code_location` exists in summary.md.\n\n---\n\n## Daily Notes\n\nTemplate:\n```markdown\n# 2026-02-24 — Monday\n\n> \"Intention\"\n\n## Morning\n**09:00** — Started [[project-slug]]\n- What you're doing\n\n## Notes\n- User prefers X\n- Decision: Y\n\n## Tasks\n- [ ] [[task-id]] #high\n\n---\nLast updated: HH:MM\n```\n\nRules:\n- One file per day: `memory/daily/YYYY-MM-DD.md`\n- Append throughout day\n- Use `[[wiki-links]]`\n- Tag priorities: `#high` `#medium` `#low`\n\n---\n\n## Fact Extraction\n\n**Universal facts** (extract to memory/facts/):\n- Preferences (\"Always use Vercel\")\n- Workflows (\"Deploy Fridays\")\n- Constraints (\"Budget $500/mo\")\n\n**One-time details** (keep in daily notes):\n- \"Make button blue\"\n- \"Meeting at 3pm\"\n\nFact JSON:\n```json\n{\n  \"id\": \"project-1\",\n  \"type\": \"preference\",\n  \"content\": \"User prefers Vercel\",\n  \"tags\": [\"hosting\"],\n  \"source\": \"daily/2026-02-24.md\",\n  \"createdAt\": \"2026-02-24T10:00:00Z\"\n}\n```\n\n---\n\n## Prompt Expansion\n\n| Component | Include |\n|-----------|---------|\n| Role | Specific persona |\n| Context | Project, stack, current state |\n| Task | Clear, scoped action |\n| Output Format | Exact files/structure |\n| Examples | Reference existing code |\n| Constraints | Hard limits, must/avoid |\n\nExample:\n```markdown\n**Role:** Senior full-stack developer, auth specialist\n\n**Context:**\n- Project: LifeOS Core\n- Stack: Next.js 15, TypeScript, Tailwind\n- Clerk already configured\n- No login page exists\n\n**Task:**\nCreate /login page with email/password form, validation, error handling, redirect\n\n**Output:**\n- File: app/login/page.tsx\n- Use existing Button, Input, Card\n\n**Examples:**\nSee app/dashboard/page.tsx for mono aesthetic patterns\n\n**Constraints:**\n- Max 150 lines\n- Handle all Clerk errors\n- Match existing aesthetic\n```\n\n---\n\n## Spawning\n\n```javascript\nsessions_spawn({\n  task: `**Role:** [persona]\n\n**Context:**\n- Project: [name]\n- Stack: [tech]\n- Current: [state]\n\n**Task:** [action]\n\n**Output:** [files]\n\n**Examples:** [ref]\n\n**Constraints:** [limits]`,\n  mode: \"run\",\n  thinking: \"medium\",\n  runTimeoutSeconds: 300\n})\n```\n\n---\n\n## Heartbeat vs Cron\n\n**Heartbeat:** Batch checks, conversational context, drift OK (~30min)\n**Cron:** Exact timing, isolation, one-shot reminders\n\n**Heartbeat flow:**\n1. User sends: \"Read HEARTBEAT.md...\"\n2. Read HEARTBEAT.md\n3. Do tasks OR reply HEARTBEAT_OK\n\n**Optional cron:**\n```bash\nopenclaw cron add --name \"memory-maintenance\" --schedule \"0 3 * * *\" \\\n  --command \"memory-pill maintenance\"\n```\n\n---\n\n## Archives\n\nMove (don't delete) to `archives/{year}/`:\n- Completed projects\n- Daily notes > 30 days old\n- Inactive clients/people\n\nKeep searchable. Update wiki-links if paths change.\n\n---\n\n## Critical Rules\n\n1. **READ THIS SKILL FIRST** — On load, read completely\n2. **SEARCH BEFORE ANSWERING** — `memory_search` before questions about prior work\n3. **SMART MERGE** — Improve existing, never destroy\n4. **FIX BROKEN** — Detect and repair bad patterns (with user permission)\n4. **AGENT-FIRST** — Main claw decides, subagents execute\n5. **BRAIN.md** — External working memory for complex tasks\n6. **MEMORY.md** — Check on first use, create if missing\n7. **EXPAND PROMPTS** — Vague → detailed before spawning\n8. **WIKI-LINKS** — `[[target]]` for Obsidian compatibility\n9. **ONE DAILY NOTE** — Append, don't create new\n10. **EXTRACT FACTS** — Universal to facts/, one-time to daily\n11. **HIGH/MEDIUM/LOW** — No \"urgent\"\n12. **ASK PERMISSION** — Never auto-setup\n\n---\n\n## Version History\n\n- **v0.8.0** — \"Take the pill\" activation, smart merging, orchestrator patterns, clean structure\n- **v0.7.9** — Archives, AI-native positioning, execution discipline\n- **v0.7.0** — Extended entities (skills, clients, decisions)\n- **v0.6.0** — Renamed from lifeos-memory, removed qmd dependency\n- **v0.5.0** — Milestones, prompt engineering, wiki-links\n","readmeExcerpt":"--- name: memory-pill version: 0.8.0 description: AI-native memory and orchestration system for OpenClaw. Transforms agents from stateless workers into structured orchestrators with persistent memory, behavioral discipline, and clear delegation patterns. --- Memory Pill v0.8.0 **⚠️ READ THIS FIRST:** When this skill loads, read the entire file before acting. The \"Take the Pill\" flow below is your activation guide. --","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"ls -la ~/.openclaw/workspace/ 2>/dev/null\ncat ~/.openclaw/workspace/MEMORY.md 2>/dev/null | wc -c\ncat ~/.openclaw/workspace/SOUL.md 2>/dev/null | wc -c  \nls ~/.openclaw/workspace/projects/ 2>/dev/null\nls ~/.openclaw/workspace/memory/daily/ 2>/dev/null"},{"language":"text","snippet":"IF exists:\n  → Read content\n  → CHECK FOR BROKEN PATTERNS:\n    * \"Great question!\" / \"I'd be happy to help!\" → Remove/fix\n    * \"As an AI language model...\" → Remove\n    * Corporate buzzwords (synergy, leverage, etc.) → Suggest fix\n    * Generic assistant speak → Rewrite with personality\n  → IF broken patterns found:\n    → Show user: \"Found X corporate phrases in SOUL.md. Fix them?\"\n    → IF yes: Rewrite with clean, authentic voice\n    → IF no: Keep as-is\n  → IF > 500 chars AND no broken patterns:\n    → Keep exactly as-is\nELSE:\n  → Create from template"},{"language":"text","snippet":"IF exists:\n  → Read sections\n  → CHECK FOR BROKEN PATTERNS:\n    * \"Always be helpful\" without boundaries → Add safety rules\n    * Missing \"Never\" section (what not to do) → Add from template\n    * No project structure guidance → Add Brain+Code section\n    * No orchestrator rules → Add spawn guidelines\n  → Merge missing good patterns\n  → REPLACE broken patterns\nELSE:\n  → Create from template"},{"language":"text","snippet":"IF exists with content → Keep\nIF empty/minimal → Populate from context or leave for user\nELSE → Create from template"},{"language":"text","snippet":"FOR each folder:\n  IF summary.md exists → Check for code_location field, add if missing\n  ELSE → Create from README/package.json/folder name\n  IF items.json missing → Create empty: []"},{"language":"text","snippet":"IF daily/ exists → Keep all notes exactly as-is\nCreate facts/ folder (empty, ready for extraction)"}],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"CLAWHUB","editorialOverview":"AI-native memory and orchestration system for OpenClaw. Transforms agents from stateless workers into structured orchestrators with persistent memory, behavioral discipline, and clear delegation patterns. --- name: memory-pill version: 0.8.0 description: AI-native memory and orchestration system for OpenClaw. Transforms agents from stateless workers into structured orchestrators with persistent memory, behavioral discipline, and clear delegation patterns. --- Memory Pill v0.8.0 **⚠️ READ THIS FIRST:** When this skill loads, read the entire file before acting. The \"Take the Pill\" flow below is your activation guide. --","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":384,"uniquenessScore":64,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T08:02:18.064Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}