[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MXK71JG99P10T6ZRS3ZPZF":3,"skill-same:01M6MXK71JG99P10T6ZRS3ZPZF":106},{"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":54,"updatedAt":55,"install":56,"resources":69},"01M6MXK71JG99P10T6ZRS3ZPZF","causal-inference",null,"Add causal reasoning to agent actions. Trigger on ANY high-level action with observable outcomes - emails, messages, calendar changes, file operations, API calls, notifications, reminders, purchases, deployments. Use for planning interventions, debugging failures, predicting outcomes, backfilling historical data for analysis, or answering \"what happens if I do X?\" Also trigger when reviewing past actions to understand what worked\u002Ffailed and why.","Kernel8901\u002Fai-agent-skills-classification","Kernel8901","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F72647553?v=4","01M6KV388J2H5PNC8D8P940BJD","01M6KV38CS5B3AY63RKZB410YM",7,"MIT","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fcausal-inference\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000005","邮件与沟通","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],"causal inference","inference","what worked","for","action","past","add","do","calendar","file operations","why","api","analysis","data","messages","actions","notifications","planning","debugging","reminders","2026-11-10 10:12:30",false,"---\nname: causal-inference\ndescription: Add causal reasoning to agent actions. Trigger on ANY high-level action with observable outcomes - emails, messages, calendar changes, file operations, API calls, notifications, reminders, purchases, deployments. Use for planning interventions, debugging failures, predicting outcomes, backfilling historical data for analysis, or answering \"what happens if I do X?\" Also trigger when reviewing past actions to understand what worked\u002Ffailed and why.\n---\n\n# Causal Inference\n\nA lightweight causal layer for predicting action outcomes, not by pattern-matching correlations, but by modeling interventions and counterfactuals.\n\n## Core Invariant\n\n**Every action must be representable as an explicit intervention on a causal model, with predicted effects + uncertainty + a falsifiable audit trail.**\n\nPlans must be *causally valid*, not just plausible.\n\n## When to Trigger\n\n**Trigger this skill on ANY high-level action**, including but not limited to:\n\n| Domain | Actions to Log |\n|--------|---------------|\n| **Communication** | Send email, send message, reply, follow-up, notification, mention |\n| **Calendar** | Create\u002Fmove\u002Fcancel meeting, set reminder, RSVP |\n| **Tasks** | Create\u002Fcomplete\u002Fdefer task, set priority, assign |\n| **Files** | Create\u002Fedit\u002Fshare document, commit code, deploy |\n| **Social** | Post, react, comment, share, DM |\n| **Purchases** | Order, subscribe, cancel, refund |\n| **System** | Config change, permission grant, integration setup |\n\nAlso trigger when:\n- **Reviewing outcomes** — \"Did that email get a reply?\" → log outcome, update estimates\n- **Debugging failures** — \"Why didn't this work?\" → trace causal graph\n- **Backfilling history** — \"Analyze my past emails\u002Fcalendar\" → parse logs, reconstruct actions\n- **Planning** — \"Should I send now or later?\" → query causal model\n\n## Backfill: Bootstrap from Historical Data\n\nDon't start from zero. Parse existing logs to reconstruct past actions + outcomes.\n\n### Email Backfill\n\n```bash\n# Extract sent emails with reply status\ngog gmail list --sent --after 2024-01-01 --format json > \u002Ftmp\u002Fsent_emails.json\n\n# For each sent email, check if reply exists\npython3 scripts\u002Fbackfill_email.py \u002Ftmp\u002Fsent_emails.json\n```\n\n### Calendar Backfill\n\n```bash\n# Extract past events with attendance\ngog calendar list --after 2024-01-01 --format json > \u002Ftmp\u002Fevents.json\n\n# Reconstruct: did meeting happen? was it moved? attendee count?\npython3 scripts\u002Fbackfill_calendar.py \u002Ftmp\u002Fevents.json\n```\n\n### Message Backfill (WhatsApp\u002FDiscord\u002FSlack)\n\n```bash\n# Parse message history for send\u002Freply patterns\nwacli search --after 2024-01-01 --from me --format json > \u002Ftmp\u002Fwa_sent.json\npython3 scripts\u002Fbackfill_messages.py \u002Ftmp\u002Fwa_sent.json\n```\n\n### Generic Backfill Pattern\n\n```python\n# For any historical data source:\nfor record in historical_data:\n    action_event = {\n        \"action\": infer_action_type(record),\n        \"context\": extract_context(record),\n        \"time\": record[\"timestamp\"],\n        \"pre_state\": reconstruct_pre_state(record),\n        \"post_state\": extract_post_state(record),\n        \"outcome\": determine_outcome(record),\n        \"backfilled\": True  # Mark as reconstructed\n    }\n    append_to_log(action_event)\n```\n\n## Architecture\n\n### A. Action Log (required)\n\nEvery executed action emits a structured event:\n\n```json\n{\n  \"action\": \"send_followup\",\n  \"domain\": \"email\",\n  \"context\": {\"recipient_type\": \"warm_lead\", \"prior_touches\": 2},\n  \"time\": \"2025-01-26T10:00:00Z\",\n  \"pre_state\": {\"days_since_last_contact\": 7},\n  \"post_state\": {\"reply_received\": true, \"reply_delay_hours\": 4},\n  \"outcome\": \"positive_reply\",\n  \"outcome_observed_at\": \"2025-01-26T14:00:00Z\",\n  \"backfilled\": false\n}\n```\n\nStore in `memory\u002Fcausal\u002Faction_log.jsonl`.\n\n### B. Causal Graphs (per domain)\n\nStart with 10-30 observable variables per domain.\n\n**Email domain:**\n```\nsend_time → reply_prob\nsubject_style → open_rate\nrecipient_type → reply_prob\nfollowup_count → reply_prob (diminishing)\ntime_since_last → reply_prob\n```\n\n**Calendar domain:**\n```\nmeeting_time → attendance_rate\nattendee_count → slip_risk\nconflict_degree → reschedule_prob\nbuffer_time → focus_quality\n```\n\n**Messaging domain:**\n```\nresponse_delay → conversation_continuation\nmessage_length → response_length\ntime_of_day → response_prob\nplatform → response_delay\n```\n\n**Task domain:**\n```\ndue_date_proximity → completion_prob\npriority_level → completion_speed\ntask_size → deferral_risk\ncontext_switches → error_rate\n```\n\nStore graph definitions in `memory\u002Fcausal\u002Fgraphs\u002F`.\n\n### C. Estimation\n\nFor each \"knob\" (intervention variable), estimate treatment effects:\n\n```python\n# Pseudo: effect of morning vs evening sends\neffect = mean(reply_prob | send_time=morning) - mean(reply_prob | send_time=evening)\nuncertainty = std_error(effect)\n```\n\nUse simple regression or propensity matching first. Graduate to do-calculus when graphs are explicit and identification is needed.\n\n### D. Decision Policy\n\nBefore executing actions:\n\n1. Identify intervention variable(s)\n2. Query causal model for expected outcome distribution\n3. Compute expected utility + uncertainty bounds\n4. If uncertainty > threshold OR expected harm > threshold → refuse or escalate to user\n5. Log prediction for later validation\n\n## Workflow\n\n### On Every Action\n\n```\nBEFORE executing:\n1. Log pre_state\n2. If enough historical data: query model for expected outcome\n3. If high uncertainty or risk: confirm with user\n\nAFTER executing:\n1. Log action + context + time\n2. Set reminder to check outcome (if not immediate)\n\nWHEN outcome observed:\n1. Update action log with post_state + outcome\n2. Re-estimate treatment effects if enough new data\n```\n\n### Planning an Action\n\n```\n1. User request → identify candidate actions\n2. For each action:\n   a. Map to intervention(s) on causal graph\n   b. Predict P(outcome | do(action))\n   c. Estimate uncertainty\n   d. Compute expected utility\n3. Rank by expected utility, filter by safety\n4. Execute best action, log prediction\n5. Observe outcome, update model\n```\n\n### Debugging a Failure\n\n```\n1. Identify failed outcome\n2. Trace back through causal graph\n3. For each upstream node:\n   a. Was the value as expected?\n   b. Did the causal link hold?\n4. Identify broken link(s)\n5. Compute minimal intervention set that would have prevented failure\n6. Log counterfactual for learning\n```\n\n## Quick Start: Bootstrap Today\n\n```bash\n# 1. Create the infrastructure\nmkdir -p memory\u002Fcausal\u002Fgraphs memory\u002Fcausal\u002Festimates\n\n# 2. Initialize config\ncat > memory\u002Fcausal\u002Fconfig.yaml \u003C\u003C 'EOF'\ndomains:\n  - email\n  - calendar\n  - messaging\n  - tasks\n\nthresholds:\n  max_uncertainty: 0.3\n  min_expected_utility: 0.1\n\nprotected_actions:\n  - delete_email\n  - cancel_meeting\n  - send_to_new_contact\n  - financial_transaction\nEOF\n\n# 3. Backfill one domain (start with email)\npython3 scripts\u002Fbackfill_email.py\n\n# 4. Estimate initial effects\npython3 scripts\u002Festimate_effect.py --treatment send_time --outcome reply_received --values morning,evening\n```\n\n## Safety Constraints\n\nDefine \"protected variables\" that require explicit user approval:\n\n```yaml\nprotected:\n  - delete_email\n  - cancel_meeting\n  - send_to_new_contact\n  - financial_transaction\n\nthresholds:\n  max_uncertainty: 0.3  # don't act if P(outcome) uncertainty > 30%\n  min_expected_utility: 0.1  # don't act if expected gain \u003C 10%\n```\n\n## Files\n\n- `memory\u002Fcausal\u002Faction_log.jsonl` — all logged actions with outcomes\n- `memory\u002Fcausal\u002Fgraphs\u002F` — domain-specific causal graph definitions\n- `memory\u002Fcausal\u002Festimates\u002F` — learned treatment effects\n- `memory\u002Fcausal\u002Fconfig.yaml` — safety thresholds and protected variables\n\n## References\n\n- See `references\u002Fdo-calculus.md` for formal intervention semantics\n- See `references\u002Festimation.md` for treatment effect estimation methods\n","# Causal Inference\n\nA lightweight causal layer for predicting action outcomes, not by pattern-matching correlations, but by modeling interventions and counterfactuals.\n\n## Core Invariant\n\n**Every action must be representable as an explicit intervention on a causal model, with predicted effects + uncertainty + a falsifiable audit trail.**\n\nPlans must be *causally valid*, not just plausible.\n\n## When to Trigger\n\n**Trigger this skill on ANY high-level action**, including but not limited to:\n\n| Domain | Actions to Log |\n|--------|---------------|\n| **Communication** | Send email, send message, reply, follow-up, notification, mention |\n| **Calendar** | Create\u002Fmove\u002Fcancel meeting, set reminder, RSVP |\n| **Tasks** | Create\u002Fcomplete\u002Fdefer task, set priority, assign |\n| **Files** | Create\u002Fedit\u002Fshare document, commit code, deploy |\n| **Social** | Post, react, comment, share, DM |\n| **Purchases** | Order, subscribe, cancel, refund |\n| **System** | Config change, permission grant, integration setup |\n\nAlso trigger when:\n- **Reviewing outcomes** — \"Did that email get a reply?\" → log outcome, update estimates\n- **Debugging failures** — \"Why didn't this work?\" → trace causal graph\n- **Backfilling history** — \"Analyze my past emails\u002Fcalendar\" → parse logs, reconstruct actions\n- **Planning** — \"Should I send now or later?\" → query causal model\n\n## Backfill: Bootstrap from Historical Data\n\nDon't start from zero. Parse existing logs to reconstruct past actions + outcomes.\n\n### Email Backfill\n\n```bash\n# Extract sent emails with reply status\ngog gmail list --sent --after 2024-01-01 --format json > \u002Ftmp\u002Fsent_emails.json\n\n# For each sent email, check if reply exists\npython3 scripts\u002Fbackfill_email.py \u002Ftmp\u002Fsent_emails.json\n```\n\n### Calendar Backfill\n\n```bash\n# Extract past events with attendance\ngog calendar list --after 2024-01-01 --format json > \u002Ftmp\u002Fevents.json\n\n# Reconstruct: did meeting happen? was it moved? attendee count?\npython3 scripts\u002Fbackfill_calendar.py \u002Ftmp\u002Fevents.json\n```\n\n### Message Backfill (WhatsApp\u002FDiscord\u002FSlack)\n\n```bash\n# Parse message history for send\u002Freply patterns\nwacli search --after 2024-01-01 --from me --format json > \u002Ftmp\u002Fwa_sent.json\npython3 scripts\u002Fbackfill_messages.py \u002Ftmp\u002Fwa_sent.json\n```\n\n### Generic Backfill Pattern\n\n```python\n# For any historical data source:\nfor record in historical_data:\n    action_event = {\n        \"action\": infer_action_type(record),\n        \"context\": extract_context(record),\n        \"time\": record[\"timestamp\"],\n        \"pre_state\": reconstruct_pre_state(record),\n        \"post_state\": extract_post_state(record),\n        \"outcome\": determine_outcome(record),\n        \"backfilled\": True  # Mark as reconstructed\n    }\n    append_to_log(action_event)\n```\n\n## Architecture\n\n### A. Action Log (required)\n\nEvery executed action emits a structured event:\n\n```json\n{\n  \"action\": \"send_followup\",\n  \"domain\": \"email\",\n  \"context\": {\"recipient_type\": \"warm_lead\", \"prior_touches\": 2},\n  \"time\": \"2025-01-26T10:00:00Z\",\n  \"pre_state\": {\"days_since_last_contact\": 7},\n  \"post_state\": {\"reply_received\": true, \"reply_delay_hours\": 4},\n  \"outcome\": \"positive_reply\",\n  \"outcome_observed_at\": \"2025-01-26T14:00:00Z\",\n  \"backfilled\": false\n}\n```\n\nStore in `memory\u002Fcausal\u002Faction_log.jsonl`.\n\n### B. Causal Graphs (per domain)\n\nStart with 10-30 observable variables per domain.\n\n**Email domain:**\n```\nsend_time → reply_prob\nsubject_style → open_rate\nrecipient_type → reply_prob\nfollowup_count → reply_prob (diminishing)\ntime_since_last → reply_prob\n```\n\n**Calendar domain:**\n```\nmeeting_time → attendance_rate\nattendee_count → slip_risk\nconflict_degree → reschedule_prob\nbuffer_time → focus_quality\n```\n\n**Messaging domain:**\n```\nresponse_delay → conversation_continuation\nmessage_length → response_length\ntime_of_day → response_prob\nplatform → response_delay\n```\n\n**Task domain:**\n```\ndue_date_proximity → completion_prob\npriority_level → completion_speed\ntask_size → deferral_risk\ncontext_switches → error_rate\n```\n\nStore graph definitions in `memory\u002Fcausal\u002Fgraphs\u002F`.\n\n### C. Estimation\n\nFor each \"knob\" (intervention variable), estimate treatment effects:\n\n```python\n# Pseudo: effect of morning vs evening sends\neffect = mean(reply_prob | send_time=morning) - mean(reply_prob | send_time=evening)\nuncertainty = std_error(effect)\n```\n\nUse simple regression or propensity matching first. Graduate to do-calculus when graphs are explicit and identification is needed.\n\n### D. Decision Policy\n\nBefore executing actions:\n\n1. Identify intervention variable(s)\n2. Query causal model for expected outcome distribution\n3. Compute expected utility + uncertainty bounds\n4. If uncertainty > threshold OR expected harm > threshold → refuse or escalate to user\n5. Log prediction for later validation\n\n## Workflow\n\n### On Every Action\n\n```\nBEFORE executing:\n1. Log pre_state\n2. If enough historical data: query model for expected outcome\n3. If high uncertainty or risk: confirm with user\n\nAFTER executing:\n1. Log action + context + time\n2. Set reminder to check outcome (if not immediate)\n\nWHEN outcome observed:\n1. Update action log with post_state + outcome\n2. Re-estimate treatment effects if enough new data\n```\n\n### Planning an Action\n\n```\n1. User request → identify candidate actions\n2. For each action:\n   a. Map to intervention(s) on causal graph\n   b. Predict P(outcome | do(action))\n   c. Estimate uncertainty\n   d. Compute expected utility\n3. Rank by expected utility, filter by safety\n4. Execute best action, log prediction\n5. Observe outcome, update model\n```\n\n### Debugging a Failure\n\n```\n1. Identify failed outcome\n2. Trace back through causal graph\n3. For each upstream node:\n   a. Was the value as expected?\n   b. Did the causal link hold?\n4. Identify broken link(s)\n5. Compute minimal intervention set that would have prevented failure\n6. Log counterfactual for learning\n```\n\n## Quick Start: Bootstrap Today\n\n```bash\n# 1. Create the infrastructure\nmkdir -p memory\u002Fcausal\u002Fgraphs memory\u002Fcausal\u002Festimates\n\n# 2. Initialize config\ncat > memory\u002Fcausal\u002Fconfig.yaml \u003C\u003C 'EOF'\ndomains:\n  - email\n  - calendar\n  - messaging\n  - tasks\n\nthresholds:\n  max_uncertainty: 0.3\n  min_expected_utility: 0.1\n\nprotected_actions:\n  - delete_email\n  - cancel_meeting\n  - send_to_new_contact\n  - financial_transaction\nEOF\n\n# 3. Backfill one domain (start with email)\npython3 scripts\u002Fbackfill_email.py\n\n# 4. Estimate initial effects\npython3 scripts\u002Festimate_effect.py --treatment send_time --outcome reply_received --values morning,evening\n```\n\n## Safety Constraints\n\nDefine \"protected variables\" that require explicit user approval:\n\n```yaml\nprotected:\n  - delete_email\n  - cancel_meeting\n  - send_to_new_contact\n  - financial_transaction\n\nthresholds:\n  max_uncertainty: 0.3  # don't act if P(outcome) uncertainty > 30%\n  min_expected_utility: 0.1  # don't act if expected gain \u003C 10%\n```\n\n## Files\n\n- `memory\u002Fcausal\u002Faction_log.jsonl` — all logged actions with outcomes\n- `memory\u002Fcausal\u002Fgraphs\u002F` — domain-specific causal graph definitions\n- `memory\u002Fcausal\u002Festimates\u002F` — learned treatment effects\n- `memory\u002Fcausal\u002Fconfig.yaml` — safety thresholds and protected variables\n\n## References\n\n- See `references\u002Fdo-calculus.md` for formal intervention semantics\n- See `references\u002Festimation.md` for treatment effect estimation methods\n",{"name":5,"description":7},"main","f4cb2d49f7667e79ef7804f50396d5aaffdf1f56","人工智能与大型语言模型\u002Fcausal-inference",1,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification","https:\u002F\u002Fgithub.com\u002FKernel8901","a little little little dobe in life but science geek","2026-04-05 16:43:56",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add Kernel8901\u002Fai-agent-skills-classification --skill causal-inference",{"tool":62,"command":63},"bunx","bunx skills add Kernel8901\u002Fai-agent-skills-classification --skill causal-inference",{"tool":65,"command":66},"pnpm","pnpm dlx skills add Kernel8901\u002Fai-agent-skills-classification --skill causal-inference","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fcausal-inference\u002FSKILL.md",true,[70,76,80,84,90,94,98,102],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"_meta.json","REFERENCE","参考文档",467,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fcausal-inference\u002F_meta.json",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fdo-calculus.md",1884,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fcausal-inference\u002Freferences\u002Fdo-calculus.md",{"path":81,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Festimation.md",3665,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fcausal-inference\u002Freferences\u002Festimation.md",{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"scripts\u002Fbackfill_calendar.py","SCRIPT","脚本",6008,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fcausal-inference\u002Fscripts\u002Fbackfill_calendar.py",{"path":91,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":92,"sourceHtmlUrl":93},"scripts\u002Fbackfill_email.py",6016,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fcausal-inference\u002Fscripts\u002Fbackfill_email.py",{"path":95,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Fbackfill_messages.py",6537,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fcausal-inference\u002Fscripts\u002Fbackfill_messages.py",{"path":99,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002Festimate_effect.py",4813,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fcausal-inference\u002Fscripts\u002Festimate_effect.py",{"path":103,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Flog_action.py",2038,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Fcausal-inference\u002Fscripts\u002Flog_action.py",[107,131,164,175,185,214],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":43},"01M6Q5R6WZ06RRB9RQTW54B34B","zyfai","Earn yield on any Ethereum wallet on Base, Arbitrum, and Plasma. Use when a user wants passive DeFi yield on their funds. Deploys a non-custodial subaccount (Safe) linked to their EOA, enables automated yield optimization, and lets them deposit\u002Fwithdraw anytime.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzyfai-sdk\u002FSKILL.md",[],[109,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130],"safe","ethereum","defi","Optimization","user","use","Wallet","base","deposit","withdraw","yield","arbitrum","non-custodial","passive","defi yield","earn","yield optimization",{"skillNo":132,"name":133,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":147,"publishedAt":43},"01M6Q5R337B5JSNER4P4YS03TN","zerion-api","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api\u002FSKILL.md",[136,139,142],{"categoryNo":137,"categoryName":138,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":140,"categoryName":141,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":143,"categoryName":144,"taxonomyType":145,"taxonomyTypeDesc":146},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[34,148,149,150,151,152,153,116,154,120,155,156,157,158,159,160,161,162,163],"zerion api","zerion","MCP","mcp server","server","blockchain","transactions","crypto wallet","crypto","evm","solana","query","across","positions","token","prices",{"skillNo":165,"name":166,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":172,"publishedAt":43},"01M6Q5QZFYTDAZMZ27BN5VZXAR","zerion-api-skill","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-skill\u002FSKILL.md",[169,170,171],{"categoryNo":137,"categoryName":138,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":140,"categoryName":141,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":143,"categoryName":144,"taxonomyType":145,"taxonomyTypeDesc":146},[34,173,174,148,149,150,151,152,153,116,154,120,156,157,158,159,160,161,162,163],"api skill","zerion api skill",{"skillNo":176,"name":177,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":183,"publishedAt":43},"01M6Q5QW17QW98RA3FE45E4RD8","zerion-api-mcp","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-mcp\u002FSKILL.md",[180,181,182],{"categoryNo":137,"categoryName":138,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":140,"categoryName":141,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":143,"categoryName":144,"taxonomyType":145,"taxonomyTypeDesc":146},[150,34,184,148,149,151,152,116,154,120,155,156,157,158,159,160,161,162,163],"zerion api mcp",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":194,"publishedAt":43},"01M6Q5QQYZB7A501BDEQWKGSJT","yahoo-finance-forex","Fetches real-time FOREX news and market data from Yahoo Finance for major currency pairs (EUR\u002FUSD, GBP\u002FUSD, USD\u002FJPY, etc.). Analyzes sentiment and provides trading context.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-forex\u002FSKILL.md",[191],{"categoryNo":192,"categoryName":193,"taxonomyType":145,"taxonomyTypeDesc":146},"01JBSEEDCAT000000000000040","财务",[195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,26],"finance","yahoo finance","forex","yahoo","yahoo finance forex","github","https","sentiment","real-time","python3","install","Market","usd","news","time","currency","gbp","pip","market data",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":221,"publishedAt":43},"01M6Q5QM6VS84WZVM7BKXXPF32","yahoo-finance","This skill should be used when the user asks to \"get stock prices\", \"check stock quotes\", \"look up earnings\", \"get financial data\", \"find trending stocks\", or needs stock market data from Yahoo Finance.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-cli\u002FSKILL.md",[220],{"categoryNo":192,"categoryName":193,"taxonomyType":145,"taxonomyTypeDesc":146},[195,196,198,222,223,224,225,226,227,206,228,229,230,231,232,233,234,235,163,213],"cli","homebrew","find","check","brew","up","local","get","stock","link","trending","sf","quotes","ln"]