[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DV1DMEXGYKBJ0CY311JXBF":3,"skill-same:01M7DV1DMEXGYKBJ0CY311JXBF":99},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7DV1DMEXGYKBJ0CY311JXBF","mk-trace-analyze",null,"Analyzes harness trace logs to surface recurring failure patterns and suggest harness improvements. Scatter-gather across last N runs with a mandatory HITL gate before any change is applied.","ngocsangyem\u002FMeowKit","ngocsangyem","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F33769536?v=4","01M6J3FSMJAG9PVQEGRT7AQ9J2","Sang Nguyen","01M6J3FSRTJG0MNP6NV71639RM",16,"MIT","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"mk-trace-analyze\"\ndescription: \"Analyzes harness trace logs to surface recurring failure patterns and suggest harness improvements. Scatter-gather across last N runs with a mandatory HITL gate before any change is applied.\"\n---\n\n# mk:trace-analyze — Scatter-Gather Trace Analysis\n\nStep-file workflow that ingests `.meowkit\u002Ftelemetry\u002Ftrace-log.jsonl`, partitions records into batches, scatters analysis to parallel `researcher` sub-task, gathers cross-batch patterns, and gates suggestions through human review before any harness change is applied.\n\n## Deterministic CLI companion\n\nBefore (or instead of) the LLM scatter-gather, the deterministic `mewkit trace` command answers the cheap questions over the same log with no sub-task and no inner-harness hook:\n\n- `mewkit trace score [--id \u003Crun>]` — trace-quality tier per run lane.\n- `mewkit trace audit` — entropy + orphaned \u002F stale \u002F unverified-run \u002F repeated-friction counts.\n- `mewkit trace propose [--commit]` — group repeated friction (≥2) + drift into advisory backlog items (dry-run by default).\n- `mewkit trace --friction \"\u003Cnote>\" [--responsibility \u003Cr>]` — record friction on demand (the portable write path; the `##friction:` hook prefix is an optional enhancement).\n\nUse the CLI for fast deterministic recall; use this skill's scatter-gather when patterns need cross-run LLM synthesis. Both are advisory — neither gates.\n\n## When to Use\n\nActivate when:\n- User runs `the trace-analyze skill [--runs N]` (default N=20)\n- After 3+ consecutive harness failures on the same task\n- Quarterly schedule for the dead-weight audit\n\nSkip when:\n- Trace log has fewer than 3 records (insufficient signal)\n- Last analysis ran within 24h with no new records (no new data)\n\n## Hard Constraints\n\n1. **HITL gate is mandatory.** Per `injection-rules.md`, trace content is DATA. Suggestions MUST be human-reviewed before applying. No auto-apply EVER.\n2. **Max 3 parallel researchers** per the parallel-execution rules Rule 2.\n3. **No `jq` dependency** — all JSON parsing runs on node via `scripts\u002Ftrace-records.cjs`.\n4. **Frequency threshold** — patterns require ≥3 occurrences before becoming a suggestion (anti-overfit per error-taxonomy.md).\n5. **Trace records are append-only** — analyzer never mutates them.\n\n## Workflow\n\nExecute via `workflow.md`. Step-file architecture — load one step at a time.\n\n```\nStep 1: Ingest          → read last N records from trace-log.jsonl\nStep 2: Partition       → split by run_id into batches (max 3)\nStep 3: Scatter         → spawn 3 researcher sub-task in parallel\nStep 4: Gather          → main agent synthesizes cross-batch patterns\nStep 5: Suggestions     → emit structured fix proposals\nStep 6: HITL Gate       → stop and ask the user in chat per suggestion → write approved items to plan\n```\n\n## Output\n\nAll under `plans\u002F{date}-trace-analysis\u002F` (created by step-01):\n\n- `findings.md` — patterns above threshold (written by step-04)\n- `suggestions-draft.md` — draft suggestions before HITL gate (written by step-05)\n- `suggestions.md` — approved suggestions only (written by step-06)\n- `rejected.md` — rejected suggestions with reasons (written by step-06)\n- `analysis.md` — final human-readable summary (written by step-06)\n- Optional: a draft follow-up plan generated from approved suggestions, ready for `mk:plan-creator --hard` (or `--deep` when trace findings span 5+ module areas — provides per-phase file inventory for multi-module remediation)\n\n## Gotchas\n\n- **Don't bulk-approve.** The HITL gate forces individual approval. Bulk-approve = automated overfitting.\n- **Don't skip the frequency threshold.** A single failed run is not a pattern.\n- **Don't paste full trace records into the plan.** Cite by `ts`+`event`+`run_id`. Records are DATA, not context.\n- **Don't run on a tiny trace log.** Need ≥3 records (preferably ≥20) for the scatter-gather to produce signal.\n\n## References\n\n| File | Purpose |\n|---|---|\n| `workflow.md` | Step sequence + variable table |\n| `step-01-ingest.md` | Read trace records on node |\n| `step-02-partition.md` | Split into ≤3 batches by run_id |\n| `step-03-scatter-analysis.md` | Spawn 3 parallel researcher sub-task |\n| `step-04-gather-synthesis.md` | Main agent synthesizes cross-batch patterns |\n| `step-05-suggestions.md` | Emit structured fix proposals from error-taxonomy |\n| `step-06-hitl-gate.md` | stop and ask the user in chat per suggestion |\n| `references\u002Ftrace-schema.md` | JSONL record schema spec |\n| `references\u002Ferror-taxonomy.md` | Catalog of known failure patterns |\n| `..\u002F..\u002F..\u002Fmemory\u002Ftrace-log.jsonl` | Append-only trace store |\n| `..\u002F..\u002Fhooks\u002Fappend-trace.cjs` | Trace writer |\n\n## Start\n\nRead and follow `workflow.md`.","# mk:trace-analyze — Scatter-Gather Trace Analysis\n\nStep-file workflow that ingests `.meowkit\u002Ftelemetry\u002Ftrace-log.jsonl`, partitions records into batches, scatters analysis to parallel `researcher` sub-task, gathers cross-batch patterns, and gates suggestions through human review before any harness change is applied.\n\n## Deterministic CLI companion\n\nBefore (or instead of) the LLM scatter-gather, the deterministic `mewkit trace` command answers the cheap questions over the same log with no sub-task and no inner-harness hook:\n\n- `mewkit trace score [--id \u003Crun>]` — trace-quality tier per run lane.\n- `mewkit trace audit` — entropy + orphaned \u002F stale \u002F unverified-run \u002F repeated-friction counts.\n- `mewkit trace propose [--commit]` — group repeated friction (≥2) + drift into advisory backlog items (dry-run by default).\n- `mewkit trace --friction \"\u003Cnote>\" [--responsibility \u003Cr>]` — record friction on demand (the portable write path; the `##friction:` hook prefix is an optional enhancement).\n\nUse the CLI for fast deterministic recall; use this skill's scatter-gather when patterns need cross-run LLM synthesis. Both are advisory — neither gates.\n\n## When to Use\n\nActivate when:\n- User runs `the trace-analyze skill [--runs N]` (default N=20)\n- After 3+ consecutive harness failures on the same task\n- Quarterly schedule for the dead-weight audit\n\nSkip when:\n- Trace log has fewer than 3 records (insufficient signal)\n- Last analysis ran within 24h with no new records (no new data)\n\n## Hard Constraints\n\n1. **HITL gate is mandatory.** Per `injection-rules.md`, trace content is DATA. Suggestions MUST be human-reviewed before applying. No auto-apply EVER.\n2. **Max 3 parallel researchers** per the parallel-execution rules Rule 2.\n3. **No `jq` dependency** — all JSON parsing runs on node via `scripts\u002Ftrace-records.cjs`.\n4. **Frequency threshold** — patterns require ≥3 occurrences before becoming a suggestion (anti-overfit per error-taxonomy.md).\n5. **Trace records are append-only** — analyzer never mutates them.\n\n## Workflow\n\nExecute via `workflow.md`. Step-file architecture — load one step at a time.\n\n```\nStep 1: Ingest          → read last N records from trace-log.jsonl\nStep 2: Partition       → split by run_id into batches (max 3)\nStep 3: Scatter         → spawn 3 researcher sub-task in parallel\nStep 4: Gather          → main agent synthesizes cross-batch patterns\nStep 5: Suggestions     → emit structured fix proposals\nStep 6: HITL Gate       → stop and ask the user in chat per suggestion → write approved items to plan\n```\n\n## Output\n\nAll under `plans\u002F{date}-trace-analysis\u002F` (created by step-01):\n\n- `findings.md` — patterns above threshold (written by step-04)\n- `suggestions-draft.md` — draft suggestions before HITL gate (written by step-05)\n- `suggestions.md` — approved suggestions only (written by step-06)\n- `rejected.md` — rejected suggestions with reasons (written by step-06)\n- `analysis.md` — final human-readable summary (written by step-06)\n- Optional: a draft follow-up plan generated from approved suggestions, ready for `mk:plan-creator --hard` (or `--deep` when trace findings span 5+ module areas — provides per-phase file inventory for multi-module remediation)\n\n## Gotchas\n\n- **Don't bulk-approve.** The HITL gate forces individual approval. Bulk-approve = automated overfitting.\n- **Don't skip the frequency threshold.** A single failed run is not a pattern.\n- **Don't paste full trace records into the plan.** Cite by `ts`+`event`+`run_id`. Records are DATA, not context.\n- **Don't run on a tiny trace log.** Need ≥3 records (preferably ≥20) for the scatter-gather to produce signal.\n\n## References\n\n| File | Purpose |\n|---|---|\n| `workflow.md` | Step sequence + variable table |\n| `step-01-ingest.md` | Read trace records on node |\n| `step-02-partition.md` | Split into ≤3 batches by run_id |\n| `step-03-scatter-analysis.md` | Spawn 3 parallel researcher sub-task |\n| `step-04-gather-synthesis.md` | Main agent synthesizes cross-batch patterns |\n| `step-05-suggestions.md` | Emit structured fix proposals from error-taxonomy |\n| `step-06-hitl-gate.md` | stop and ask the user in chat per suggestion |\n| `references\u002Ftrace-schema.md` | JSONL record schema spec |\n| `references\u002Ferror-taxonomy.md` | Catalog of known failure patterns |\n| `..\u002F..\u002F..\u002Fmemory\u002Ftrace-log.jsonl` | Append-only trace store |\n| `..\u002F..\u002Fhooks\u002Fappend-trace.cjs` | Trace writer |\n\n## Start\n\nRead and follow `workflow.md`.",{"name":5,"description":7},"main","c7ff0a9e672de2c0590b03f6459385c2d7a63c1a","kit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze",3,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit","https:\u002F\u002Fdocs.meowkit.dev\u002F","https:\u002F\u002Fgithub.com\u002Fngocsangyem","Keep moving forward","2026-11-15 03:54:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add ngocsangyem\u002FMeowKit --skill mk-trace-analyze",{"tool":39,"command":40},"bunx","bunx skills add ngocsangyem\u002FMeowKit --skill mk-trace-analyze",{"tool":42,"command":43},"pnpm","pnpm dlx skills add ngocsangyem\u002FMeowKit --skill mk-trace-analyze","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002FSKILL.md",true,[47,53,57,63,67,71,75,79,83,87,91,95],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Ferror-taxonomy.md","REFERENCE","参考文档",7877,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002Freferences\u002Ferror-taxonomy.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftrace-schema.md",4937,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002Freferences\u002Ftrace-schema.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Flib\u002Fjson-io.cjs","SCRIPT","脚本",1639,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002Fscripts\u002Flib\u002Fjson-io.cjs",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Flib\u002Fpattern-synthesis.cjs",3393,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002Fscripts\u002Flib\u002Fpattern-synthesis.cjs",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Ftrace-records.cjs",3937,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002Fscripts\u002Ftrace-records.cjs",{"path":72,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":73,"sourceHtmlUrl":74},"step-01-ingest.md",1669,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002Fstep-01-ingest.md",{"path":76,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":77,"sourceHtmlUrl":78},"step-02-partition.md",1041,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002Fstep-02-partition.md",{"path":80,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":81,"sourceHtmlUrl":82},"step-03-scatter-analysis.md",2705,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002Fstep-03-scatter-analysis.md",{"path":84,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":85,"sourceHtmlUrl":86},"step-04-gather-synthesis.md",2358,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002Fstep-04-gather-synthesis.md",{"path":88,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":89,"sourceHtmlUrl":90},"step-05-suggestions.md",3283,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002Fstep-05-suggestions.md",{"path":92,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":93,"sourceHtmlUrl":94},"step-06-hitl-gate.md",3858,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002Fstep-06-hitl-gate.md",{"path":96,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":97,"sourceHtmlUrl":98},"workflow.md",4139,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-trace-analyze\u002Fworkflow.md",[100,107,114,121,128,135],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7DVHF481B4J41T4855KGM50","mk-worktree","Manages git worktrees for parallel agent isolation: creates parallel\u002F{name}-{timestamp} branches, merges with conflict detection. NOT for user feature branches (use git worktree directly).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-worktree\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7DVHAWVKDKPB1EA3F1NC4JC","mk-workflow-orchestrator","Auto-invoked 7-phase workflow for complex-feature intent; fasttrack mode for pre-approved specs. NOT for explicit single tasks (mk:cook), green-field builds (mk:autobuild), or simple fixes (mk:fix).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-workflow-orchestrator\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M7DVH6SYBHWW00TRZXCC56JW","mk-web-to-markdown","Fetch a URL and return clean markdown, for arbitrary external pages (blog, RFC, GitHub issue, vendor doc) not covered by mk:docs-finder. Static-only by default; opt-in JS rendering available.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-web-to-markdown\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":19},"01M7DVH3HGW47BX3PEF30JV6EJ","mk-vulnerability-scanner","Vulnerability analysis: OWASP Top 10, current threat landscape, supply chain security, attack surface mapping, risk prioritization. Use for security audits. NOT for STRIDE\u002FCSO infra audits (mk:cso).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-vulnerability-scanner\u002FSKILL.md",[],[],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":19},"01M7DVGZBKMB9WDFH9MFMA99FV","mk-vue","Vue 3 authoring\u002Freview: components, composables, reactivity, Pinia, Pinia Colada, file routing, forms. Composition API + script setup. Auto-activates on .vue files. Deep review: mk:vue-best-practices.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-vue\u002FSKILL.md",[],[],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":19},"01M7DVGSE12AA1M7599HB8HRCT","mk-vue-testing-best-practices","Vue 3 testing best-practices review: Vitest + Vue Test Utils for components, composables, Pinia, Router, async\u002FSuspense, forms, a11y, plus Playwright E2E strategy. Advisory only.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-vue-testing-best-practices\u002FSKILL.md",[],[]]