[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M713CWQCFHDVEK0SQ1MMDPAA":3,"skill-same:01M713CWQCFHDVEK0SQ1MMDPAA":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":56,"updatedAt":57,"install":58,"resources":70},"01M713CWQCFHDVEK0SQ1MMDPAA","pipeline-4",null,"End-to-end source processing -- seed, reduce, process all claims through reflect\u002Freweave\u002Fverify, archive. The full pipeline in one command. Triggers on \"\u002Fpipeline\", \"\u002Fpipeline [file]\", \"process this end to end\", \"full pipeline\".","FDU-INS\u002FInsurance-Skills","FDU-INS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F167067594?v=4","01M6XEYMRS4CVJMZ834YWE66BV","FDU-Insurance","01M6XEYMXPDA34HFM0ZE6AY78G",82,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fpipeline-4\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"pipeline 4","pipeline","process","command","full pipeline","fork","verify","claims","reflect","reweave","task","file","Bash","v1","reduce","true","triggers","archive","end","processing","2026-11-10 10:12:30",false,"---\nname: pipeline-4\ndescription: End-to-end source processing -- seed, reduce, process all claims through reflect\u002Freweave\u002Fverify, archive. The full pipeline in one command. Triggers on \"\u002Fpipeline\", \"\u002Fpipeline [file]\", \"process this end to end\", \"full pipeline\".\nversion: \"1.0\"\ngenerated_from: \"arscontexta-v1.6\"\nuser-invocable: true\ncontext: fork\nmodel: sonnet\nallowed-tools: Read, Write, Edit, Grep, Glob, Bash, Task\nargument-hint: \"[file] — path to source file to process end-to-end\"\n---\n\n## EXECUTE NOW\n\n**Target: $ARGUMENTS**\n\nParse immediately:\n- Source file path: the file to process (required)\n- `--handoff`: output RALPH HANDOFF block at end (for chaining)\n- If target is empty: list files in {DOMAIN:inbox}\u002F and ask which to process\n\n### Step 0: Read Vocabulary\n\nRead `ops\u002Fderivation-manifest.md` (or fall back to `ops\u002Fderivation.md`) for domain vocabulary mapping. All output must use domain-native terms. If neither file exists, use universal terms.\n\n**START NOW.** Run the full pipeline.\n\n---\n\n## Pipeline Overview\n\nThe pipeline chains four phases. Each phase uses skill invocation or \u002Fralph for subagent-based processing. State lives in the queue file — the pipeline is stateless orchestration on top of stateful queue entries.\n\n```\nSource file\n    |\n    v\nPhase 1: \u002Fseed — create extract task, move source to archive\n    |\n    v\nPhase 2: \u002Freduce (via \u002Fralph) — extract claims from source\n    |\n    v\nPhase 3: \u002Fralph (all claims) — create -> reflect -> reweave -> verify\n    |\n    v\nPhase 4: \u002Farchive-batch — move task files, generate summary\n    |\n    v\nComplete\n```\n\nThe pipeline is the convenience wrapper. \u002Fralph is the engine. \u002Fseed is the entry point.\n\n---\n\n## Phase 1: Seed\n\nInvoke \u002Fseed on the target file to create the extract task, check for duplicates, and move the source to its archive folder.\n\n**How to invoke:**\n\nUse the Skill tool if available, otherwise execute the \u002Fseed workflow directly:\n- Validate source exists\n- Check for prior processing (duplicate detection)\n- Create archive folder\n- Move source from {DOMAIN:inbox} to archive\n- Create extract task file\n- Add extract task to queue\n\n**Capture from seed output:**\n- **Batch ID**: the source basename (used for --batch filtering in subsequent steps)\n- **Archive folder path**: where the source was moved\n- **next_claim_start**: the claim numbering start\n\nReport: `$ Seeded: {source-name}`\n\n**If seed reports the file was already processed:** Ask the user whether to proceed or skip. Do NOT auto-skip — the user may want to re-process with different scope.\n\n---\n\n## Phase 2: Extract (Reduce)\n\nProcess the extract task via \u002Fralph. This spawns a subagent that runs \u002Freduce, extracting claims from the source and creating task entries in the queue.\n\n**How to invoke:**\n\n```\n\u002Fralph 1 --batch {batch_id} --type extract\n```\n\nOr via Task tool:\n```\nTask(\n  prompt = \"Run \u002Fralph 1 --batch {batch_id} --type extract\",\n  description = \"extract: {batch_id}\"\n)\n```\n\nAfter completion, read the queue to count extracted claims and enrichments:\n\nCheck how many pending tasks exist for this batch. The reduce phase creates 1 queue entry per claim and 1 per enrichment.\n\nReport:\n```\n$ Extracted: {N} {DOMAIN:note_plural}, {M} enrichments\n  Processing {total_tasks} tasks through the pipeline...\n```\n\n**If zero claims extracted:** Report the issue. For TFT sources, zero extraction is a bug — the source almost certainly contains extractable content. Ask the user whether to retry with different scope or skip.\n\n---\n\n## Phase 3: Process All Claims\n\nCount total pending tasks for this batch from the queue. Then process all of them through the full phase sequence.\n\n**How to invoke:**\n\n```\n\u002Fralph {remaining_count} --batch {batch_id}\n```\n\nOr via Task tool:\n```\nTask(\n  prompt = \"Run \u002Fralph {remaining_count} --batch {batch_id}\",\n  description = \"process: {batch_id} ({remaining_count} tasks)\"\n)\n```\n\nThis processes every claim through: create -> reflect -> reweave -> verify. And every enrichment through: enrich -> reflect -> reweave -> verify.\n\nEach phase runs in an isolated subagent with fresh context. \u002Fralph handles all the orchestration: subagent spawning, handoff parsing, queue advancement, learnings capture.\n\n**Progress reporting:**\n\nThe \u002Fralph invocation reports progress per task. The pipeline relays this:\n```\n$ Processing {DOMAIN:note} 1\u002F{total}: {title}\n  $ create... done\n  $ reflect... done (3 connections found)\n  $ reweave... done (2 {DOMAIN:note_plural} updated)\n  $ verify... done (PASS)\n```\n\n**For large batches (20+ claims):** \u002Fralph handles context isolation automatically via subagents. The pipeline does NOT need to chunk — \u002Fralph processes N tasks sequentially with fresh context per phase.\n\n---\n\n## Phase 4: Verify Completion\n\nAfter \u002Fralph finishes, verify all tasks for this batch are done.\n\nCheck the queue: count tasks for this batch that are NOT done.\n\n**If tasks remain pending:**\n- Report which tasks are incomplete and at which phase\n- Show the specific task IDs and their current_phase\n- Suggest: \"Run `\u002Fralph --batch {batch_id}` to continue from where it stopped\"\n- Do NOT proceed to archive\n\n**If all tasks are done:** Proceed to Phase 5.\n\n---\n\n## Phase 5: Archive Batch\n\nWhen all tasks for the batch are complete, archive the batch.\n\n**How to invoke:**\n\n```\n\u002Farchive-batch {batch_id}\n```\n\nOr execute directly:\n1. Move all task files from `ops\u002Fqueue\u002F` to `ops\u002Fqueue\u002Farchive\u002F{date}-{batch_id}\u002F`\n2. Generate a batch summary file: `{batch_id}-summary.md`\n3. Remove completed entries from the queue (or mark as archived)\n\nThe summary should include:\n- Source file name and original location\n- Number of claims extracted\n- Number of enrichments\n- List of created {DOMAIN:note_plural} with titles\n- Any notable learnings from the batch\n\n---\n\n## Phase 6: Final Report\n\n```\n--=={ pipeline }==--\n\nSource: {source_file}\nBatch: {batch_id}\n\nExtraction:\n  {DOMAIN:note_plural} extracted: {N}\n  Enrichments identified: {M}\n\nProcessing:\n  {DOMAIN:note_plural} created: {N}\n  Existing {DOMAIN:note_plural} enriched: {M}\n  Connections added: {C}\n  {DOMAIN:topic map}s updated: {T}\n  Older {DOMAIN:note_plural} updated via reweave: {R}\n\nQuality:\n  All verify checks: {PASS\u002FFAIL count}\n\nArchive: ops\u002Fqueue\u002Farchive\u002F{date}-{batch_id}\u002F\nSummary: {batch_id}-summary.md\n\n{DOMAIN:note_plural} created:\n- [[claim title 1]]\n- [[claim title 2]]\n- ...\n```\n\nIf `--handoff` flag was set, also output:\n\n```\n=== RALPH HANDOFF: pipeline ===\nTarget: {source_file}\n\nWork Done:\n- Seeded source: {batch_id}\n- Extracted {N} {DOMAIN:note_plural} and {M} enrichments\n- Processed all claims through 4-phase pipeline\n- Archived batch to {archive_path}\n\nFiles Modified:\n- {DOMAIN:notes}\u002F ({N} new {DOMAIN:note_plural})\n- ops\u002Fqueue\u002Farchive\u002F{date}-{batch_id}\u002F (archived)\n\nLearnings:\n- [Friction]: {description} | NONE\n- [Surprise]: {description} | NONE\n- [Methodology]: {description} | NONE\n- [Process gap]: {description} | NONE\n\nQueue Updates:\n- All tasks for batch {batch_id} marked done and archived\n=== END HANDOFF ===\n```\n\n---\n\n## Error Handling\n\n**Phase failure at any stage:**\n1. Report the failure with context (which phase, which task, what error)\n2. Show the current queue state for this batch\n3. Suggest remediation: \"Run `\u002Fralph --batch {batch_id}` to continue from where it stopped\"\n4. Do NOT attempt to continue automatically past failures\n\n**The pipeline is resumable.** Queue state persists across sessions:\n- \u002Fseed detects prior processing and asks whether to proceed\n- \u002Fralph picks up from the last completed phase (queue is the source of truth)\n- \u002Farchive-batch verifies completeness before archiving\n\n**Seed failure:** If \u002Fseed fails (file not found, duplicate detected and user declines), stop the pipeline entirely.\n\n**Extract failure:** If \u002Freduce extracts zero claims, report and stop. Do not proceed to an empty processing phase.\n\n**Processing failure:** If \u002Fralph fails mid-batch, the queue preserves state. Individual claims resume from their failed phase on next \u002Fralph invocation.\n\n**Archive failure:** If archiving fails, the claims are still created and connected. Only the organizational cleanup is missing — re-run \u002Farchive-batch manually.\n\n---\n\n## Resumability\n\nThe pipeline is designed to be interrupted and resumed at any point:\n\n| Interrupted At | How to Resume |\n|----------------|---------------|\n| Before seed | Run \u002Fpipeline again (starts fresh) |\n| After seed, before reduce | \u002Fralph 1 --batch {id} --type extract |\n| After reduce, during claims | \u002Fralph --batch {id} (picks up from failed phase) |\n| After all claims, before archive | \u002Farchive-batch {id} |\n\nState lives in the queue file. The pipeline reads queue state, not session state. This means you can interrupt, close the session, and resume later.\n\n---\n\n## Edge Cases\n\n**No target file:** List {DOMAIN:inbox}\u002F candidates, suggest the best one based on age and relevance.\n\n**Source already seeded:** \u002Fseed detects this and asks the user. If they decline, the pipeline stops cleanly.\n\n**Large source (2500+ lines):** \u002Freduce handles chunking automatically. The pipeline does not need special handling.\n\n**No ops\u002Fderivation-manifest.md:** Use universal vocabulary for all output.\n\n---\n\n## Critical Constraints\n\n**never:**\n- Skip the seed phase (duplicate detection is important)\n- Continue past a failed phase automatically\n- Process claims inline instead of via \u002Fralph subagents\n- Archive a batch with incomplete tasks\n\n**always:**\n- Report progress at each phase boundary\n- Verify all tasks are done before archiving\n- Show the user what was created (list of {DOMAIN:note_plural})\n- Suggest next steps if interrupted\n- Use domain-native vocabulary from derivation manifest\n","## EXECUTE NOW\n\n**Target: $ARGUMENTS**\n\nParse immediately:\n- Source file path: the file to process (required)\n- `--handoff`: output RALPH HANDOFF block at end (for chaining)\n- If target is empty: list files in {DOMAIN:inbox}\u002F and ask which to process\n\n### Step 0: Read Vocabulary\n\nRead `ops\u002Fderivation-manifest.md` (or fall back to `ops\u002Fderivation.md`) for domain vocabulary mapping. All output must use domain-native terms. If neither file exists, use universal terms.\n\n**START NOW.** Run the full pipeline.\n\n---\n\n## Pipeline Overview\n\nThe pipeline chains four phases. Each phase uses skill invocation or \u002Fralph for subagent-based processing. State lives in the queue file — the pipeline is stateless orchestration on top of stateful queue entries.\n\n```\nSource file\n    |\n    v\nPhase 1: \u002Fseed — create extract task, move source to archive\n    |\n    v\nPhase 2: \u002Freduce (via \u002Fralph) — extract claims from source\n    |\n    v\nPhase 3: \u002Fralph (all claims) — create -> reflect -> reweave -> verify\n    |\n    v\nPhase 4: \u002Farchive-batch — move task files, generate summary\n    |\n    v\nComplete\n```\n\nThe pipeline is the convenience wrapper. \u002Fralph is the engine. \u002Fseed is the entry point.\n\n---\n\n## Phase 1: Seed\n\nInvoke \u002Fseed on the target file to create the extract task, check for duplicates, and move the source to its archive folder.\n\n**How to invoke:**\n\nUse the Skill tool if available, otherwise execute the \u002Fseed workflow directly:\n- Validate source exists\n- Check for prior processing (duplicate detection)\n- Create archive folder\n- Move source from {DOMAIN:inbox} to archive\n- Create extract task file\n- Add extract task to queue\n\n**Capture from seed output:**\n- **Batch ID**: the source basename (used for --batch filtering in subsequent steps)\n- **Archive folder path**: where the source was moved\n- **next_claim_start**: the claim numbering start\n\nReport: `$ Seeded: {source-name}`\n\n**If seed reports the file was already processed:** Ask the user whether to proceed or skip. Do NOT auto-skip — the user may want to re-process with different scope.\n\n---\n\n## Phase 2: Extract (Reduce)\n\nProcess the extract task via \u002Fralph. This spawns a subagent that runs \u002Freduce, extracting claims from the source and creating task entries in the queue.\n\n**How to invoke:**\n\n```\n\u002Fralph 1 --batch {batch_id} --type extract\n```\n\nOr via Task tool:\n```\nTask(\n  prompt = \"Run \u002Fralph 1 --batch {batch_id} --type extract\",\n  description = \"extract: {batch_id}\"\n)\n```\n\nAfter completion, read the queue to count extracted claims and enrichments:\n\nCheck how many pending tasks exist for this batch. The reduce phase creates 1 queue entry per claim and 1 per enrichment.\n\nReport:\n```\n$ Extracted: {N} {DOMAIN:note_plural}, {M} enrichments\n  Processing {total_tasks} tasks through the pipeline...\n```\n\n**If zero claims extracted:** Report the issue. For TFT sources, zero extraction is a bug — the source almost certainly contains extractable content. Ask the user whether to retry with different scope or skip.\n\n---\n\n## Phase 3: Process All Claims\n\nCount total pending tasks for this batch from the queue. Then process all of them through the full phase sequence.\n\n**How to invoke:**\n\n```\n\u002Fralph {remaining_count} --batch {batch_id}\n```\n\nOr via Task tool:\n```\nTask(\n  prompt = \"Run \u002Fralph {remaining_count} --batch {batch_id}\",\n  description = \"process: {batch_id} ({remaining_count} tasks)\"\n)\n```\n\nThis processes every claim through: create -> reflect -> reweave -> verify. And every enrichment through: enrich -> reflect -> reweave -> verify.\n\nEach phase runs in an isolated subagent with fresh context. \u002Fralph handles all the orchestration: subagent spawning, handoff parsing, queue advancement, learnings capture.\n\n**Progress reporting:**\n\nThe \u002Fralph invocation reports progress per task. The pipeline relays this:\n```\n$ Processing {DOMAIN:note} 1\u002F{total}: {title}\n  $ create... done\n  $ reflect... done (3 connections found)\n  $ reweave... done (2 {DOMAIN:note_plural} updated)\n  $ verify... done (PASS)\n```\n\n**For large batches (20+ claims):** \u002Fralph handles context isolation automatically via subagents. The pipeline does NOT need to chunk — \u002Fralph processes N tasks sequentially with fresh context per phase.\n\n---\n\n## Phase 4: Verify Completion\n\nAfter \u002Fralph finishes, verify all tasks for this batch are done.\n\nCheck the queue: count tasks for this batch that are NOT done.\n\n**If tasks remain pending:**\n- Report which tasks are incomplete and at which phase\n- Show the specific task IDs and their current_phase\n- Suggest: \"Run `\u002Fralph --batch {batch_id}` to continue from where it stopped\"\n- Do NOT proceed to archive\n\n**If all tasks are done:** Proceed to Phase 5.\n\n---\n\n## Phase 5: Archive Batch\n\nWhen all tasks for the batch are complete, archive the batch.\n\n**How to invoke:**\n\n```\n\u002Farchive-batch {batch_id}\n```\n\nOr execute directly:\n1. Move all task files from `ops\u002Fqueue\u002F` to `ops\u002Fqueue\u002Farchive\u002F{date}-{batch_id}\u002F`\n2. Generate a batch summary file: `{batch_id}-summary.md`\n3. Remove completed entries from the queue (or mark as archived)\n\nThe summary should include:\n- Source file name and original location\n- Number of claims extracted\n- Number of enrichments\n- List of created {DOMAIN:note_plural} with titles\n- Any notable learnings from the batch\n\n---\n\n## Phase 6: Final Report\n\n```\n--=={ pipeline }==--\n\nSource: {source_file}\nBatch: {batch_id}\n\nExtraction:\n  {DOMAIN:note_plural} extracted: {N}\n  Enrichments identified: {M}\n\nProcessing:\n  {DOMAIN:note_plural} created: {N}\n  Existing {DOMAIN:note_plural} enriched: {M}\n  Connections added: {C}\n  {DOMAIN:topic map}s updated: {T}\n  Older {DOMAIN:note_plural} updated via reweave: {R}\n\nQuality:\n  All verify checks: {PASS\u002FFAIL count}\n\nArchive: ops\u002Fqueue\u002Farchive\u002F{date}-{batch_id}\u002F\nSummary: {batch_id}-summary.md\n\n{DOMAIN:note_plural} created:\n- [[claim title 1]]\n- [[claim title 2]]\n- ...\n```\n\nIf `--handoff` flag was set, also output:\n\n```\n=== RALPH HANDOFF: pipeline ===\nTarget: {source_file}\n\nWork Done:\n- Seeded source: {batch_id}\n- Extracted {N} {DOMAIN:note_plural} and {M} enrichments\n- Processed all claims through 4-phase pipeline\n- Archived batch to {archive_path}\n\nFiles Modified:\n- {DOMAIN:notes}\u002F ({N} new {DOMAIN:note_plural})\n- ops\u002Fqueue\u002Farchive\u002F{date}-{batch_id}\u002F (archived)\n\nLearnings:\n- [Friction]: {description} | NONE\n- [Surprise]: {description} | NONE\n- [Methodology]: {description} | NONE\n- [Process gap]: {description} | NONE\n\nQueue Updates:\n- All tasks for batch {batch_id} marked done and archived\n=== END HANDOFF ===\n```\n\n---\n\n## Error Handling\n\n**Phase failure at any stage:**\n1. Report the failure with context (which phase, which task, what error)\n2. Show the current queue state for this batch\n3. Suggest remediation: \"Run `\u002Fralph --batch {batch_id}` to continue from where it stopped\"\n4. Do NOT attempt to continue automatically past failures\n\n**The pipeline is resumable.** Queue state persists across sessions:\n- \u002Fseed detects prior processing and asks whether to proceed\n- \u002Fralph picks up from the last completed phase (queue is the source of truth)\n- \u002Farchive-batch verifies completeness before archiving\n\n**Seed failure:** If \u002Fseed fails (file not found, duplicate detected and user declines), stop the pipeline entirely.\n\n**Extract failure:** If \u002Freduce extracts zero claims, report and stop. Do not proceed to an empty processing phase.\n\n**Processing failure:** If \u002Fralph fails mid-batch, the queue preserves state. Individual claims resume from their failed phase on next \u002Fralph invocation.\n\n**Archive failure:** If archiving fails, the claims are still created and connected. Only the organizational cleanup is missing — re-run \u002Farchive-batch manually.\n\n---\n\n## Resumability\n\nThe pipeline is designed to be interrupted and resumed at any point:\n\n| Interrupted At | How to Resume |\n|----------------|---------------|\n| Before seed | Run \u002Fpipeline again (starts fresh) |\n| After seed, before reduce | \u002Fralph 1 --batch {id} --type extract |\n| After reduce, during claims | \u002Fralph --batch {id} (picks up from failed phase) |\n| After all claims, before archive | \u002Farchive-batch {id} |\n\nState lives in the queue file. The pipeline reads queue state, not session state. This means you can interrupt, close the session, and resume later.\n\n---\n\n## Edge Cases\n\n**No target file:** List {DOMAIN:inbox}\u002F candidates, suggest the best one based on age and relevance.\n\n**Source already seeded:** \u002Fseed detects this and asks the user. If they decline, the pipeline stops cleanly.\n\n**Large source (2500+ lines):** \u002Freduce handles chunking automatically. The pipeline does not need special handling.\n\n**No ops\u002Fderivation-manifest.md:** Use universal vocabulary for all output.\n\n---\n\n## Critical Constraints\n\n**never:**\n- Skip the seed phase (duplicate detection is important)\n- Continue past a failed phase automatically\n- Process claims inline instead of via \u002Fralph subagents\n- Archive a batch with incomplete tasks\n\n**always:**\n- Report progress at each phase boundary\n- Verify all tasks are done before archiving\n- Show the user what was created (list of {DOMAIN:note_plural})\n- Suggest next steps if interrupted\n- Use domain-native vocabulary from derivation manifest\n",{"name":5,"model":44,"context":24,"version":45,"description":7,"allowed-tools":46,"argument-hint":47,"generated_from":48,"user-invocable":49},"sonnet","1.0","Read, Write, Edit, Grep, Glob, Bash, Task","[file] — path to source file to process end-to-end","arscontexta-v1.6",true,"main","b22eca2e974f918ce591c5b2bd829fb7510e0191","Skills\u002Fpipeline-4",18,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills","https:\u002F\u002Fgithub.com\u002FFDU-INS","Fudan University Department of Risk Management and Insurance","2026-07-12 12:54:34",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":49},[60,63,66],{"tool":61,"command":62},"npx","npx skills add FDU-INS\u002FInsurance-Skills --skill pipeline-4",{"tool":64,"command":65},"bunx","bunx skills add FDU-INS\u002FInsurance-Skills --skill pipeline-4",{"tool":67,"command":68},"pnpm","pnpm dlx skills add FDU-INS\u002FInsurance-Skills --skill pipeline-4","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fpipeline-4\u002FSKILL.md",[71],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"skill.json","REFERENCE","参考文档",449,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fpipeline-4\u002Fskill.json",[78,109,134,165,185,218],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":89,"publishedAt":39},"01M713QW6EGEG0YAD75440GSD0","로인장 (Roinjiang)","Activates when the user needs legal advice, contract review, insurance law consultation, startup legal support, or any legal\u002Fregulatory matter. She is a top-tier in-house lawyer with absolute loyalty to the CEO, specializing in insurance law, financial consumer protection, privacy, contracts, labor law, family law, civil and criminal matters.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002F로인장 (Roinjiang)\u002FSKILL.md",[84],{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[80,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"insurance law","insurance","civil","contract","family","when","review","loyalty","with","top","contract review","ceo","support","advice","consultation","regulatory","privacy","protection","startup",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":39},"01M713QRN8VFMA9VKS6R4DJ2WS","zocdoc-doctor-finder","Use when a user needs to find a doctor, dentist, specialist, therapist, or healthcare provider — especially when they mention insurance, in-network, availability, location, appointments, or booking. Also use for browsing provider reviews, comparing doctors by specialty, or checking if a provider takes their insurance.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fzocdoc-doctor-finder\u002FSKILL.md",[],[116,117,118,119,91,120,121,95,122,123,124,125,126,127,128,129,130,131,132,133],"zocdoc doctor finder","doctor","healthcare","reviews","browser automation","access","browsing","browser","booking","network","therapist","computer","availability","for","provider","tool","use","automation",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":145,"publishedAt":39},"01M713QKGV3FTX7EEYWKDM8ENZ","zenmux-context","Answers any question about ZenMux by reading the latest official documentation. Use this skill whenever the user asks about ZenMux product features, API usage, configuration, integration, pricing, models, providers, routing, fallback, streaming, multimodal, structured output, tool calling, reasoning, prompt caching, image generation, video generation, web search, long context, observability, logs, cost tracking, usage analytics, insurance, subscription, pay-as-you-go, invoices, best practices for tools like Claude Code, Cursor, Cline, CodeX, Gemini CLI, opencode, Cherry Studio, Obsidian, Sider, Open-WebUI, Dify, Neovate, GitHub Copilot, OpenClaw, CC-Switch, Immersive Translate, Studio Chat, architecture, benchmarks, FAQ, contact, privacy, terms of service, compliance, or any other ZenMux-related topic. Also trigger when the user writes in Chinese about ZenMux: 文档, 使用指南, 快速开始, API 参考, 最佳实践, 模型路由, 供应商路由, 订阅, 按量计费, 可观测性, 帮助, 常见问题, 接入指南, 配置. Trigger on phrases like \"how to use ZenMux\", \"ZenMux docs\", \"ZenMux API\", \"ZenMux integration\", \"ZenMux 怎么用\", \"ZenMux 接入\", \"ZenMux 配置\". Even if the user doesn't say \"ZenMux\" explicitly but asks about LLM API aggregation, model routing, provider fallback in a context where ZenMux is the project being worked on, this skill should activate.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fzenmux-context\u002FSKILL.md",[140],{"categoryNo":141,"categoryName":142,"taxonomyType":143,"taxonomyTypeDesc":144},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[146,147,148,149,91,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164],"context","zenmux context","Video","chinese","project","web search","translate","search","open","question","pay","image","you","activate","architecture","logs","streaming","cherry studio","how",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":39},"01M713QHWTBG634BCBV7NBJME1","workers-comp-guide","Guide workers compensation compliance and claims management.\nTRIGGERS - Use when user needs help with workers-comp-guide related tasks.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fworkers-comp-guide\u002FSKILL.md",[],[172,173,174,175,176,91,35,177,132,95,178,98,179,26,180,181,182,183,184],"workers","comp","workers comp","workers comp guide","guide","workers-comp","tasks","claims management","compliance","help","compensation","management","user",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":200,"publishedAt":39},"01M713QF45VMV1685AFNF1GPMA","weekly-kpi-report","Generate McKinsey-style board presentation PPTs from weekly auto insurance data. Automatically calculates 16+ KPIs, creates executive-level slides with actionable insights, and supports week-over-week comparisons. Use when user uploads insurance cost data (Excel\u002FCSV) and requests board report, weekly presentation, executive briefing, or mentions keywords like 董事会汇报, 周报PPT, 经营分析演示, McKinsey-style reports.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fweekly-kpi-report\u002FSKILL.md",[191,194,197],{"categoryNo":192,"categoryName":193,"taxonomyType":143,"taxonomyTypeDesc":144},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":195,"categoryName":196,"taxonomyType":143,"taxonomyTypeDesc":144},"01JBSEEDCAT000000000000004","电子表格",{"categoryNo":198,"categoryName":199,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000034","行政与办公人员",[201,202,203,204,205,91,206,207,208,209,95,210,211,212,213,214,215,216,132,217],"weekly","weekly kpi report","kpi","report","xlsx","actionable","insights","briefing","auto","board report","reports","generate","演示","data","presentation","slides","uploads",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":222,"categories":223,"keywords":227,"publishedAt":39},"01M713QA9WJDHMNVTTY1ENRKVB","wealth-advisory","Wealth management and financial planning for HNW and UHNW clients. Activate when the user\nmentions wealth management, financial planning, retirement, estate planning, tax planning,\nGRAT, IDGT, trust, asset allocation, withdrawal rate, Monte Carlo simulation, goals-based\ninvesting, tax-loss harvesting, Roth conversion, insurance, annuity, mortgage strategy,\nconcentrated stock, family office, direct indexing, 529 plan, charitable giving, donor-advised\nfund, private foundation, or asks about personal finance strategy, inheritance, long-term\nfinancial planning, or UHNW advisory.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fwealth-advisory\u002FSKILL.md",[224],{"categoryNo":225,"categoryName":226,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000040","财务",[228,229,91,230,231,95,159,232,233,234,235,236,237,238,239,240,241,242,243,244],"wealth advisory","advisory","stock","inheritance","conversion","indexing","plan","simulation","personal finance","rate","allocation","asset","direct","personal","investing","trust","planning"]