{
"schemaVersion": "1.0",
"item": {
"slug": "ai-compound-1-0-1",
"name": "Ai Compound 1.0.1",
"source": "tencent",
"type": "skill",
"category": "AI 智能",
"sourceUrl": "https://clawhub.ai/AmanGarg1999/ai-compound-1-0-1",
"canonicalUrl": "https://clawhub.ai/AmanGarg1999/ai-compound-1-0-1",
"targetPlatform": "OpenClaw"
},
"install": {
"downloadMode": "redirect",
"downloadUrl": "/downloads/ai-compound-1-0-1",
"sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-compound-1-0-1",
"sourcePlatform": "tencent",
"targetPlatform": "OpenClaw",
"installMethod": "Manual import",
"extraction": "Extract archive",
"prerequisites": [
"OpenClaw"
],
"packageFormat": "ZIP package",
"includedAssets": [
"SKILL.md"
],
"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": "2026-04-23T16:43:11.935Z",
"expiresAt": "2026-04-30T16:43:11.935Z",
"httpStatus": 200,
"finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
"contentType": "application/zip",
"probeMethod": "head",
"details": {
"probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
"contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/ai-compound-1-0-1"
},
"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/ai-compound-1-0-1",
"agentPageUrl": "https://openagent3.xyz/skills/ai-compound-1-0-1/agent",
"manifestUrl": "https://openagent3.xyz/skills/ai-compound-1-0-1/agent.json",
"briefUrl": "https://openagent3.xyz/skills/ai-compound-1-0-1/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": "Compound Engineering",
"body": "Make your AI agent learn automatically. Extract learnings from sessions, update memory files, and compound knowledge over time.\n\nThe idea: Your agent reviews its own work, extracts patterns and lessons, and updates its instructions. Tomorrow's agent is smarter than today's."
},
{
"title": "Quick Start",
"body": "# Review last 24 hours and update memory\nnpx compound-engineering review\n\n# Create hourly memory snapshot\nnpx compound-engineering snapshot\n\n# Set up automated nightly review (cron)\nnpx compound-engineering setup-cron"
},
{
"title": "The Compound Loop",
"body": "┌─────────────────────────────────────────┐\n│ DAILY WORK │\n│ Sessions, chats, tasks, decisions │\n└────────────────┬────────────────────────┘\n │\n ▼\n┌─────────────────────────────────────────┐\n│ NIGHTLY REVIEW (10:30 PM) │\n│ • Scan all sessions from last 24h │\n│ • Extract learnings and patterns │\n│ • Update MEMORY.md and AGENTS.md │\n│ • Commit and push changes │\n└────────────────┬────────────────────────┘\n │\n ▼\n┌─────────────────────────────────────────┐\n│ NEXT DAY │\n│ Agent reads updated instructions │\n│ Benefits from yesterday's learnings │\n└─────────────────────────────────────────┘"
},
{
"title": "What Gets Extracted",
"body": "Patterns: Recurring approaches that worked\nGotchas: Things that failed or caused issues\nPreferences: User preferences discovered\nDecisions: Key decisions and their reasoning\nTODOs: Unfinished items to remember"
},
{
"title": "Automatic Hourly Memory",
"body": "Add to your HEARTBEAT.md:\n\n# Hourly Memory Snapshot\nEvery hour, append a brief summary to memory/YYYY-MM-DD.md:\n- What was accomplished\n- Key decisions made\n- Anything to remember\n\nOr use cron:\n\n# Add to clawdbot config or crontab\n0 * * * * clawdbot cron run compound-hourly"
},
{
"title": "Nightly Review Job",
"body": "Add this cron job to Clawdbot:\n\n{\n \"id\": \"compound-nightly\",\n \"schedule\": \"30 22 * * *\",\n \"text\": \"Review all sessions from the last 24 hours. For each session, extract: 1) Key learnings and patterns, 2) Mistakes or gotchas to avoid, 3) User preferences discovered, 4) Unfinished items. Update MEMORY.md with a summary. Update memory/YYYY-MM-DD.md with details. Commit changes to git.\"\n}"
},
{
"title": "Manual Review Command",
"body": "When you want to trigger a review manually:\n\nReview the last 24 hours of work. Extract:\n\n1. **Patterns that worked** - approaches to repeat\n2. **Gotchas encountered** - things to avoid\n3. **Preferences learned** - user likes/dislikes\n4. **Key decisions** - and their reasoning\n5. **Open items** - unfinished work\n\nUpdate:\n- MEMORY.md with significant long-term learnings\n- memory/YYYY-MM-DD.md with today's details\n- AGENTS.md if workflow changes needed\n\nCommit changes with message \"compound: daily review YYYY-MM-DD\""
},
{
"title": "MEMORY.md (Long-term)",
"body": "# Long-Term Memory\n\n## Patterns That Work\n- When doing X, always Y first\n- User prefers Z approach for...\n\n## Gotchas to Avoid \n- Don't do X without checking Y\n- API Z has rate limit of...\n\n## User Preferences\n- Prefers concise responses\n- Timezone: PST\n- ...\n\n## Project Context\n- Main repo at /path/to/project\n- Deploy process is..."
},
{
"title": "memory/YYYY-MM-DD.md (Daily)",
"body": "# 2026-01-28 (Tuesday)\n\n## Sessions\n- 09:00 - Built security audit tool\n- 14:00 - Published 40 skills to MoltHub\n\n## Decisions\n- Chose to batch publish in parallel (5 sub-agents)\n- Security tool covers 6 check categories\n\n## Learnings\n- ClawdHub publish can timeout, retry with new version\n- npm publish hangs sometimes, may need to retry\n\n## Open Items\n- [ ] Finish remaining MoltHub uploads\n- [ ] Set up analytics tracker"
},
{
"title": "Hourly Snapshots",
"body": "For more granular memory, create hourly snapshots:\n\n# Creates memory/YYYY-MM-DD-HH.md every hour\n*/60 * * * * echo \"## $(date +%H):00 Snapshot\" >> ~/clawd/memory/$(date +%Y-%m-%d).md\n\nOr have the agent do it via heartbeat by checking time and appending to daily file."
},
{
"title": "The Compound Effect",
"body": "Week 1: Agent knows basics\nWeek 2: Agent remembers your preferences\nWeek 4: Agent anticipates your needs\nMonth 2: Agent is an expert in your workflow\n\nKnowledge compounds. Every session makes future sessions better."
},
{
"title": "Nightly Review (launchd - macOS)",
"body": "\n\n\n\n\n Label\n com.clawdbot.compound-review\n ProgramArguments\n \n /opt/homebrew/bin/clawdbot\n cron\n run\n compound-nightly\n \n StartCalendarInterval\n \n Hour\n 22\n Minute\n 30\n \n\n"
},
{
"title": "Hourly Memory (crontab)",
"body": "# Add with: crontab -e\n0 * * * * /opt/homebrew/bin/clawdbot cron run compound-hourly 2>&1 >> ~/clawd/logs/compound.log"
},
{
"title": "Best Practices",
"body": "Review before sleep - Let the nightly job run when you're done for the day\nDon't over-extract - Focus on significant learnings, not noise\nPrune regularly - Remove outdated info from MEMORY.md monthly\nGit everything - Memory files should be version controlled\nTrust the compound - Effects are subtle at first, dramatic over time\n\nBuilt by LXGIC Studios - @lxgicstudios\n\nBuilt by LXGIC Studios\n\nGitHub: github.com/lxgicstudios/ai-compound\nTwitter: @lxgicstudios"
}
],
"body": "Compound Engineering\n\nMake your AI agent learn automatically. Extract learnings from sessions, update memory files, and compound knowledge over time.\n\nThe idea: Your agent reviews its own work, extracts patterns and lessons, and updates its instructions. Tomorrow's agent is smarter than today's.\n\nQuick Start\n# Review last 24 hours and update memory\nnpx compound-engineering review\n\n# Create hourly memory snapshot\nnpx compound-engineering snapshot\n\n# Set up automated nightly review (cron)\nnpx compound-engineering setup-cron\n\nHow It Works\nThe Compound Loop\n┌─────────────────────────────────────────┐\n│ DAILY WORK │\n│ Sessions, chats, tasks, decisions │\n└────────────────┬────────────────────────┘\n │\n ▼\n┌─────────────────────────────────────────┐\n│ NIGHTLY REVIEW (10:30 PM) │\n│ • Scan all sessions from last 24h │\n│ • Extract learnings and patterns │\n│ • Update MEMORY.md and AGENTS.md │\n│ • Commit and push changes │\n└────────────────┬────────────────────────┘\n │\n ▼\n┌─────────────────────────────────────────┐\n│ NEXT DAY │\n│ Agent reads updated instructions │\n│ Benefits from yesterday's learnings │\n└─────────────────────────────────────────┘\n\nWhat Gets Extracted\nPatterns: Recurring approaches that worked\nGotchas: Things that failed or caused issues\nPreferences: User preferences discovered\nDecisions: Key decisions and their reasoning\nTODOs: Unfinished items to remember\nClawdbot Integration\nAutomatic Hourly Memory\n\nAdd to your HEARTBEAT.md:\n\n# Hourly Memory Snapshot\nEvery hour, append a brief summary to memory/YYYY-MM-DD.md:\n- What was accomplished\n- Key decisions made\n- Anything to remember\n\n\nOr use cron:\n\n# Add to clawdbot config or crontab\n0 * * * * clawdbot cron run compound-hourly\n\nNightly Review Job\n\nAdd this cron job to Clawdbot:\n\n{\n \"id\": \"compound-nightly\",\n \"schedule\": \"30 22 * * *\",\n \"text\": \"Review all sessions from the last 24 hours. For each session, extract: 1) Key learnings and patterns, 2) Mistakes or gotchas to avoid, 3) User preferences discovered, 4) Unfinished items. Update MEMORY.md with a summary. Update memory/YYYY-MM-DD.md with details. Commit changes to git.\"\n}\n\nManual Review Command\n\nWhen you want to trigger a review manually:\n\nReview the last 24 hours of work. Extract:\n\n1. **Patterns that worked** - approaches to repeat\n2. **Gotchas encountered** - things to avoid\n3. **Preferences learned** - user likes/dislikes\n4. **Key decisions** - and their reasoning\n5. **Open items** - unfinished work\n\nUpdate:\n- MEMORY.md with significant long-term learnings\n- memory/YYYY-MM-DD.md with today's details\n- AGENTS.md if workflow changes needed\n\nCommit changes with message \"compound: daily review YYYY-MM-DD\"\n\nMemory File Structure\nMEMORY.md (Long-term)\n# Long-Term Memory\n\n## Patterns That Work\n- When doing X, always Y first\n- User prefers Z approach for...\n\n## Gotchas to Avoid \n- Don't do X without checking Y\n- API Z has rate limit of...\n\n## User Preferences\n- Prefers concise responses\n- Timezone: PST\n- ...\n\n## Project Context\n- Main repo at /path/to/project\n- Deploy process is...\n\nmemory/YYYY-MM-DD.md (Daily)\n# 2026-01-28 (Tuesday)\n\n## Sessions\n- 09:00 - Built security audit tool\n- 14:00 - Published 40 skills to MoltHub\n\n## Decisions\n- Chose to batch publish in parallel (5 sub-agents)\n- Security tool covers 6 check categories\n\n## Learnings\n- ClawdHub publish can timeout, retry with new version\n- npm publish hangs sometimes, may need to retry\n\n## Open Items\n- [ ] Finish remaining MoltHub uploads\n- [ ] Set up analytics tracker\n\nHourly Snapshots\n\nFor more granular memory, create hourly snapshots:\n\n# Creates memory/YYYY-MM-DD-HH.md every hour\n*/60 * * * * echo \"## $(date +%H):00 Snapshot\" >> ~/clawd/memory/$(date +%Y-%m-%d).md\n\n\nOr have the agent do it via heartbeat by checking time and appending to daily file.\n\nThe Compound Effect\n\nWeek 1: Agent knows basics Week 2: Agent remembers your preferences\nWeek 4: Agent anticipates your needs Month 2: Agent is an expert in your workflow\n\nKnowledge compounds. Every session makes future sessions better.\n\nSetup Scripts\nNightly Review (launchd - macOS)\n\n\n\n\n\n Label\n com.clawdbot.compound-review\n ProgramArguments\n \n /opt/homebrew/bin/clawdbot\n cron\n run\n compound-nightly\n \n StartCalendarInterval\n \n Hour\n 22\n Minute\n 30\n \n\n\n\nHourly Memory (crontab)\n# Add with: crontab -e\n0 * * * * /opt/homebrew/bin/clawdbot cron run compound-hourly 2>&1 >> ~/clawd/logs/compound.log\n\nBest Practices\nReview before sleep - Let the nightly job run when you're done for the day\nDon't over-extract - Focus on significant learnings, not noise\nPrune regularly - Remove outdated info from MEMORY.md monthly\nGit everything - Memory files should be version controlled\nTrust the compound - Effects are subtle at first, dramatic over time\n\nBuilt by LXGIC Studios - @lxgicstudios\n\nBuilt by LXGIC Studios\n\nGitHub: github.com/lxgicstudios/ai-compound\nTwitter: @lxgicstudios"
},
"trust": {
"sourceLabel": "tencent",
"provenanceUrl": "https://clawhub.ai/AmanGarg1999/ai-compound-1-0-1",
"publisherUrl": "https://clawhub.ai/AmanGarg1999/ai-compound-1-0-1",
"owner": "AmanGarg1999",
"version": "1.0.0",
"license": null,
"verificationStatus": "Indexed source record"
},
"links": {
"detailUrl": "https://openagent3.xyz/skills/ai-compound-1-0-1",
"downloadUrl": "https://openagent3.xyz/downloads/ai-compound-1-0-1",
"agentUrl": "https://openagent3.xyz/skills/ai-compound-1-0-1/agent",
"manifestUrl": "https://openagent3.xyz/skills/ai-compound-1-0-1/agent.json",
"briefUrl": "https://openagent3.xyz/skills/ai-compound-1-0-1/agent.md"
}
}