[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6EGP6VA3F6S21RSH4KDN147":3,"skill-same:01M6EGP6VA3F6S21RSH4KDN147":71},{"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":23,"publishedAt":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M6EGP6VA3F6S21RSH4KDN147","ln-811-algorithm-optimizer",null,"Optimizes algorithms via autoresearch loop: benchmark, research, hypothesize, keep\u002Fdiscard","levalencia\u002Fagent-god-mode","levalencia","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6962857?v=4","01M6EB0FZZ4BPQPC4HET4QY6NM","Luis Valencia ","01M6EB0G4HWHPWW0H9X7QKSAHP",3,"MIT","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-811-algorithm-optimizer\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32],"optimizer","ln 811 algorithm optimizer","research","benchmark","autoresearch","loop","algorithms","via","keep","2026-11-10 10:12:30",false,"---\nname: ln-811-algorithm-optimizer\ndescription: \"Optimizes algorithms via autoresearch loop: benchmark, research, hypothesize, keep\u002Fdiscard\"\nlicense: MIT\n---\n\n> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.\n\n# ln-811-algorithm-optimizer\n\n**Type:** L3 Worker\n**Category:** 8XX Optimization\n**Parent:** ln-810-performance-optimization-coordinator\n\nOptimizes target function performance via autoresearch loop: establish baseline benchmark, research best practices, generate 3-7 hypotheses, apply each with keep\u002Fdiscard verification.\n\n---\n\n## Overview\n\n| Aspect | Details |\n|--------|---------|\n| **Input** | `target_file` + `target_function` (or audit findings from ln-650) |\n| **Output** | Optimized function with benchmark proof, optimization report |\n| **Pattern** | Autoresearch: modify → benchmark → keep (≥10%) \u002F discard |\n\n---\n\n## Workflow\n\n**Phases:** Pre-flight → Baseline → Research → Hypothesize → Optimize Loop → Report\n\n---\n\n## Phase 0: Pre-flight Checks\n\n| Check | Required | Action if Missing |\n|-------|----------|-------------------|\n| Target file exists | Yes | Block optimization |\n| Target function identifiable | Yes | Block optimization |\n| Test infrastructure | Yes | Block optimization (see ci_tool_detection.md) |\n| Test coverage for target function | Yes | Block — no coverage = no safety net |\n| Git clean state | Yes | Block (need clean baseline for revert) |\n| Benchmark infrastructure | No | Generate benchmark (see references) |\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fci_tool_detection.md` — use Benchmarks + Test Frameworks sections.\n\n### Coverage Verification\n\nBefore starting optimization, verify target function has test coverage:\n\n| Step | Action |\n|------|--------|\n| 1 | Grep test files for target function name \u002F imports from target module |\n| 2 | If ≥1 test references target → PROCEED |\n| 3 | If 0 tests reference target → BLOCK with \"no test coverage for {function}\" |\n\n> Without test coverage, benchmark improvements are meaningless — the optimized function may produce wrong results faster.\n\n### Worktree & Branch Isolation\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fgit_worktree_fallback.md` — use ln-811 row.\n\nAll work (edits, benchmarks, KEEP commits) in worktree. Never modify main worktree.\n\n---\n\n## Phase 1: Establish Baseline\n\n### Step 1.1: Detect or Generate Benchmark\n\n| Situation | Action |\n|-----------|--------|\n| Existing benchmark found | Use as-is |\n| No benchmark exists | Generate minimal benchmark (see [benchmark_generation.md](references\u002Fbenchmark_generation.md)) |\n\n### Step 1.2: Run Baseline\n\n| Parameter | Value |\n|-----------|-------|\n| Runs | 5 |\n| Metric | Median execution time |\n| Warm-up | 1 discarded run |\n| Output | `baseline_median`, `baseline_p95` |\n\nSave baseline result — all improvements measured against this.\n\n---\n\n## Phase 2: Research Best Practices\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fresearch_tool_fallback.md` for MCP tool chain.\n\n### Research Strategy\n\n| Priority | Tool | Query Template |\n|----------|------|----------------|\n| 1 | mcp__context7__query-docs | `\"{language} {algorithm_type} optimization techniques\"` |\n| 2 | mcp__Ref__ref_search_documentation | `\"{language} {function_name} performance best practices\"` |\n| 3 | WebSearch | `\"{algorithm_type} optimization {language} benchmark {current_year}\"` |\n\n### Research Output\n\nCollect optimization techniques applicable to the target function. For each technique note:\n- Name and description\n- Expected improvement category (algorithmic complexity, memory, cache, parallelism)\n- Applicability conditions (data size, structure, language features)\n\n---\n\n## Phase 3: Generate Hypotheses (3-7)\n\n### Hypothesis Sources\n\n**MANDATORY READ:** Load [optimization_categories.md](references\u002Foptimization_categories.md) for category checklist.\n\n| Source | Priority |\n|--------|----------|\n| Research findings (Phase 2) | 1 |\n| Optimization categories checklist | 2 |\n| Code analysis (anti-patterns in target) | 3 |\n\n### Hypothesis Format\n\n| Field | Description |\n|-------|-------------|\n| id | H1, H2, ... H7 |\n| category | From optimization_categories.md |\n| description | What to change |\n| expected_impact | Estimated improvement % |\n| risk | Low \u002F Medium \u002F High |\n| dependencies | Other hypotheses this depends on |\n\n### Ordering\n\nSort by: `expected_impact DESC, risk ASC`. Independent hypotheses first (no dependencies).\n\n---\n\n## Phase 4: Optimize Loop (Keep\u002FDiscard)\n\n### Per-Hypothesis Cycle\n\n```\nFOR each hypothesis (H1..H7):\n  1. APPLY: Edit target function (surgical change, function body only)\n  2. VERIFY: Run tests\n     IF tests FAIL (assertion) → DISCARD (revert) → next hypothesis\n     IF tests CRASH (runtime error, OOM, import error):\n       IF fixable (typo, missing import) → fix & re-run ONCE\n       IF fundamental (design flaw, incompatible API) → DISCARD + log \"crash: {reason}\"\n  3. BENCHMARK: Run 5 times, take median\n  4. COMPARE: improvement = (baseline - new) \u002F baseline * 100\n     IF improvement >= 10% → KEEP:\n       git add {target_file}\n       git commit -m \"perf(H{N}): {description} (+{improvement}%)\"\n       new baseline = new median\n     IF improvement \u003C 10%  → DISCARD (revert edit)\n  5. LOG: Record result to experiment log + report\n```\n\n### Safety Rules\n\n| Rule | Description |\n|------|-------------|\n| Scope | Only target function body; no signature changes |\n| Dependencies | No new package installations |\n| Revert | `git checkout -- {target_file}` on discard |\n| Time budget | 30 minutes total for all hypotheses |\n| Compound | Each KEEP becomes new baseline for next hypothesis |\n| Traceability | Each KEEP = separate git commit with hypothesis ID in message |\n| Isolation | All work in isolated worktree; never modify main worktree |\n\n### Keep\u002FDiscard Decision\n\n| Condition | Decision | Action |\n|-----------|----------|--------|\n| Tests fail | DISCARD | Revert, log reason |\n| Improvement ≥ 10% | KEEP | Update baseline |\n| Improvement 10-20% BUT complexity increase | REVIEW | Log as \"marginal + complex\", prefer DISCARD |\n| Improvement \u003C 10% | DISCARD | Revert, log as \"insufficient gain\" |\n| Regression (slower) | DISCARD | Revert, log regression amount |\n\n> **Simplicity criterion (per autoresearch):** If improvement is marginal (10-20%) and change significantly increases code complexity (>50% more lines, deeply nested logic, hard-to-read constructs), prefer DISCARD. Simpler code at near-equal performance wins.\n\n---\n\n## Phase 5: Report Results\n\n### Report Schema\n\n| Field | Description |\n|-------|-------------|\n| target | File path + function name |\n| baseline | Original median benchmark |\n| final | Final median after all kept optimizations |\n| total_improvement | Percentage improvement |\n| hypotheses_tested | Total count |\n| hypotheses_kept | Count of kept optimizations |\n| hypotheses_discarded | Count + reasons |\n| optimizations[] | Per-kept: id, category, description, improvement% |\n\n### Experiment Log\n\nWrite to `{project_root}\u002F.optimization\u002Fln-811-log.tsv`:\n\n| Column | Description |\n|--------|-------------|\n| timestamp | ISO 8601 |\n| hypothesis_id | H1..H7 |\n| category | From optimization_categories.md |\n| description | What changed |\n| baseline_ms | Baseline median before this hypothesis |\n| result_ms | New median after change |\n| improvement_pct | Percentage change |\n| status | keep \u002F discard \u002F crash |\n| commit | Git commit hash (if kept) |\n\nAppend to existing file if present (enables tracking across multiple runs).\n\n### Cleanup\n\n| Action | When |\n|--------|------|\n| Remove generated benchmark | If benchmark was auto-generated AND no kept optimizations |\n| Keep generated benchmark | If any optimization was kept (proof of improvement) |\n\n---\n\n## Configuration\n\n```yaml\nOptions:\n  # Target\n  target_file: \"\"\n  target_function: \"\"\n\n  # Benchmark\n  benchmark_runs: 5\n  improvement_threshold: 10    # percent\n  warmup_runs: 1\n\n  # Hypotheses\n  max_hypotheses: 7\n  min_hypotheses: 3\n\n  # Safety\n  time_budget_minutes: 30\n  allow_new_deps: false\n  scope: \"function_body\"       # function_body | module\n\n  # Verification\n  run_tests: true\n  run_lint: false\n```\n\n---\n\n## Error Handling\n\n| Error | Cause | Solution |\n|-------|-------|----------|\n| No benchmark framework | Stack not in ci_tool_detection.md | Generate inline benchmark |\n| All hypotheses discarded | No effective optimization found | Report \"no improvements found\" |\n| Benchmark noise too high | Inconsistent timing | Increase runs to 10, use p50 |\n| Test flake | Non-deterministic test | Re-run once; if flakes again, skip hypothesis |\n\n---\n\n## References\n\n- [benchmark_generation.md](references\u002Fbenchmark_generation.md)\n- [optimization_categories.md](references\u002Foptimization_categories.md)\n- `shared\u002Freferences\u002Fci_tool_detection.md` (Benchmarks section)\n- `shared\u002Freferences\u002Fresearch_tool_fallback.md`\n\n---\n\n## Definition of Done\n\n- Test coverage for target function verified before optimization\n- Target function identified and baseline benchmark established (5 runs, median)\n- Research completed via MCP tool chain (Context7\u002FRef\u002FWebSearch)\n- 3-7 hypotheses generated, ordered by expected impact\n- Each hypothesis tested: apply → tests → benchmark → keep\u002Fdiscard\n- Each kept optimization = separate git commit with hypothesis ID\n- Kept optimizations compound (each becomes new baseline)\n- Marginal gains (10-20%) with complexity increase reviewed via simplicity criterion\n- Tests pass after all kept optimizations\n- Experiment log written to `.optimization\u002Fln-811-log.tsv`\n- Report returned with baseline, final, improvement%, per-hypothesis results\n- Generated benchmark cleaned up if no optimizations kept\n- All changes on isolated branch, pushed to remote\n\n---\n\n**Version:** 1.0.0\n**Last Updated:** 2026-03-08\n","> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.\n\n# ln-811-algorithm-optimizer\n\n**Type:** L3 Worker\n**Category:** 8XX Optimization\n**Parent:** ln-810-performance-optimization-coordinator\n\nOptimizes target function performance via autoresearch loop: establish baseline benchmark, research best practices, generate 3-7 hypotheses, apply each with keep\u002Fdiscard verification.\n\n---\n\n## Overview\n\n| Aspect | Details |\n|--------|---------|\n| **Input** | `target_file` + `target_function` (or audit findings from ln-650) |\n| **Output** | Optimized function with benchmark proof, optimization report |\n| **Pattern** | Autoresearch: modify → benchmark → keep (≥10%) \u002F discard |\n\n---\n\n## Workflow\n\n**Phases:** Pre-flight → Baseline → Research → Hypothesize → Optimize Loop → Report\n\n---\n\n## Phase 0: Pre-flight Checks\n\n| Check | Required | Action if Missing |\n|-------|----------|-------------------|\n| Target file exists | Yes | Block optimization |\n| Target function identifiable | Yes | Block optimization |\n| Test infrastructure | Yes | Block optimization (see ci_tool_detection.md) |\n| Test coverage for target function | Yes | Block — no coverage = no safety net |\n| Git clean state | Yes | Block (need clean baseline for revert) |\n| Benchmark infrastructure | No | Generate benchmark (see references) |\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fci_tool_detection.md` — use Benchmarks + Test Frameworks sections.\n\n### Coverage Verification\n\nBefore starting optimization, verify target function has test coverage:\n\n| Step | Action |\n|------|--------|\n| 1 | Grep test files for target function name \u002F imports from target module |\n| 2 | If ≥1 test references target → PROCEED |\n| 3 | If 0 tests reference target → BLOCK with \"no test coverage for {function}\" |\n\n> Without test coverage, benchmark improvements are meaningless — the optimized function may produce wrong results faster.\n\n### Worktree & Branch Isolation\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fgit_worktree_fallback.md` — use ln-811 row.\n\nAll work (edits, benchmarks, KEEP commits) in worktree. Never modify main worktree.\n\n---\n\n## Phase 1: Establish Baseline\n\n### Step 1.1: Detect or Generate Benchmark\n\n| Situation | Action |\n|-----------|--------|\n| Existing benchmark found | Use as-is |\n| No benchmark exists | Generate minimal benchmark (see [benchmark_generation.md](references\u002Fbenchmark_generation.md)) |\n\n### Step 1.2: Run Baseline\n\n| Parameter | Value |\n|-----------|-------|\n| Runs | 5 |\n| Metric | Median execution time |\n| Warm-up | 1 discarded run |\n| Output | `baseline_median`, `baseline_p95` |\n\nSave baseline result — all improvements measured against this.\n\n---\n\n## Phase 2: Research Best Practices\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fresearch_tool_fallback.md` for MCP tool chain.\n\n### Research Strategy\n\n| Priority | Tool | Query Template |\n|----------|------|----------------|\n| 1 | mcp__context7__query-docs | `\"{language} {algorithm_type} optimization techniques\"` |\n| 2 | mcp__Ref__ref_search_documentation | `\"{language} {function_name} performance best practices\"` |\n| 3 | WebSearch | `\"{algorithm_type} optimization {language} benchmark {current_year}\"` |\n\n### Research Output\n\nCollect optimization techniques applicable to the target function. For each technique note:\n- Name and description\n- Expected improvement category (algorithmic complexity, memory, cache, parallelism)\n- Applicability conditions (data size, structure, language features)\n\n---\n\n## Phase 3: Generate Hypotheses (3-7)\n\n### Hypothesis Sources\n\n**MANDATORY READ:** Load [optimization_categories.md](references\u002Foptimization_categories.md) for category checklist.\n\n| Source | Priority |\n|--------|----------|\n| Research findings (Phase 2) | 1 |\n| Optimization categories checklist | 2 |\n| Code analysis (anti-patterns in target) | 3 |\n\n### Hypothesis Format\n\n| Field | Description |\n|-------|-------------|\n| id | H1, H2, ... H7 |\n| category | From optimization_categories.md |\n| description | What to change |\n| expected_impact | Estimated improvement % |\n| risk | Low \u002F Medium \u002F High |\n| dependencies | Other hypotheses this depends on |\n\n### Ordering\n\nSort by: `expected_impact DESC, risk ASC`. Independent hypotheses first (no dependencies).\n\n---\n\n## Phase 4: Optimize Loop (Keep\u002FDiscard)\n\n### Per-Hypothesis Cycle\n\n```\nFOR each hypothesis (H1..H7):\n  1. APPLY: Edit target function (surgical change, function body only)\n  2. VERIFY: Run tests\n     IF tests FAIL (assertion) → DISCARD (revert) → next hypothesis\n     IF tests CRASH (runtime error, OOM, import error):\n       IF fixable (typo, missing import) → fix & re-run ONCE\n       IF fundamental (design flaw, incompatible API) → DISCARD + log \"crash: {reason}\"\n  3. BENCHMARK: Run 5 times, take median\n  4. COMPARE: improvement = (baseline - new) \u002F baseline * 100\n     IF improvement >= 10% → KEEP:\n       git add {target_file}\n       git commit -m \"perf(H{N}): {description} (+{improvement}%)\"\n       new baseline = new median\n     IF improvement \u003C 10%  → DISCARD (revert edit)\n  5. LOG: Record result to experiment log + report\n```\n\n### Safety Rules\n\n| Rule | Description |\n|------|-------------|\n| Scope | Only target function body; no signature changes |\n| Dependencies | No new package installations |\n| Revert | `git checkout -- {target_file}` on discard |\n| Time budget | 30 minutes total for all hypotheses |\n| Compound | Each KEEP becomes new baseline for next hypothesis |\n| Traceability | Each KEEP = separate git commit with hypothesis ID in message |\n| Isolation | All work in isolated worktree; never modify main worktree |\n\n### Keep\u002FDiscard Decision\n\n| Condition | Decision | Action |\n|-----------|----------|--------|\n| Tests fail | DISCARD | Revert, log reason |\n| Improvement ≥ 10% | KEEP | Update baseline |\n| Improvement 10-20% BUT complexity increase | REVIEW | Log as \"marginal + complex\", prefer DISCARD |\n| Improvement \u003C 10% | DISCARD | Revert, log as \"insufficient gain\" |\n| Regression (slower) | DISCARD | Revert, log regression amount |\n\n> **Simplicity criterion (per autoresearch):** If improvement is marginal (10-20%) and change significantly increases code complexity (>50% more lines, deeply nested logic, hard-to-read constructs), prefer DISCARD. Simpler code at near-equal performance wins.\n\n---\n\n## Phase 5: Report Results\n\n### Report Schema\n\n| Field | Description |\n|-------|-------------|\n| target | File path + function name |\n| baseline | Original median benchmark |\n| final | Final median after all kept optimizations |\n| total_improvement | Percentage improvement |\n| hypotheses_tested | Total count |\n| hypotheses_kept | Count of kept optimizations |\n| hypotheses_discarded | Count + reasons |\n| optimizations[] | Per-kept: id, category, description, improvement% |\n\n### Experiment Log\n\nWrite to `{project_root}\u002F.optimization\u002Fln-811-log.tsv`:\n\n| Column | Description |\n|--------|-------------|\n| timestamp | ISO 8601 |\n| hypothesis_id | H1..H7 |\n| category | From optimization_categories.md |\n| description | What changed |\n| baseline_ms | Baseline median before this hypothesis |\n| result_ms | New median after change |\n| improvement_pct | Percentage change |\n| status | keep \u002F discard \u002F crash |\n| commit | Git commit hash (if kept) |\n\nAppend to existing file if present (enables tracking across multiple runs).\n\n### Cleanup\n\n| Action | When |\n|--------|------|\n| Remove generated benchmark | If benchmark was auto-generated AND no kept optimizations |\n| Keep generated benchmark | If any optimization was kept (proof of improvement) |\n\n---\n\n## Configuration\n\n```yaml\nOptions:\n  # Target\n  target_file: \"\"\n  target_function: \"\"\n\n  # Benchmark\n  benchmark_runs: 5\n  improvement_threshold: 10    # percent\n  warmup_runs: 1\n\n  # Hypotheses\n  max_hypotheses: 7\n  min_hypotheses: 3\n\n  # Safety\n  time_budget_minutes: 30\n  allow_new_deps: false\n  scope: \"function_body\"       # function_body | module\n\n  # Verification\n  run_tests: true\n  run_lint: false\n```\n\n---\n\n## Error Handling\n\n| Error | Cause | Solution |\n|-------|-------|----------|\n| No benchmark framework | Stack not in ci_tool_detection.md | Generate inline benchmark |\n| All hypotheses discarded | No effective optimization found | Report \"no improvements found\" |\n| Benchmark noise too high | Inconsistent timing | Increase runs to 10, use p50 |\n| Test flake | Non-deterministic test | Re-run once; if flakes again, skip hypothesis |\n\n---\n\n## References\n\n- [benchmark_generation.md](references\u002Fbenchmark_generation.md)\n- [optimization_categories.md](references\u002Foptimization_categories.md)\n- `shared\u002Freferences\u002Fci_tool_detection.md` (Benchmarks section)\n- `shared\u002Freferences\u002Fresearch_tool_fallback.md`\n\n---\n\n## Definition of Done\n\n- Test coverage for target function verified before optimization\n- Target function identified and baseline benchmark established (5 runs, median)\n- Research completed via MCP tool chain (Context7\u002FRef\u002FWebSearch)\n- 3-7 hypotheses generated, ordered by expected impact\n- Each hypothesis tested: apply → tests → benchmark → keep\u002Fdiscard\n- Each kept optimization = separate git commit with hypothesis ID\n- Kept optimizations compound (each becomes new baseline)\n- Marginal gains (10-20%) with complexity increase reviewed via simplicity criterion\n- Tests pass after all kept optimizations\n- Experiment log written to `.optimization\u002Fln-811-log.tsv`\n- Report returned with baseline, final, improvement%, per-hypothesis results\n- Generated benchmark cleaned up if no optimizations kept\n- All changes on isolated branch, pushed to remote\n\n---\n\n**Version:** 1.0.0\n**Last Updated:** 2026-03-08\n",{"name":5,"license":15,"description":7},"main","fa638b97a18ff6d9f26cf0eaf3dfa123531bcc87","organized-skills\u002Fln-811-algorithm-optimizer",1,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode","https:\u002F\u002Fgithub.com\u002Flevalencia","https:\u002F\u002Fmedium.com\u002F@luisevalencia","Microsoft MVP - Artificial Intelligence\r\nMachine Learning Enthusiast\r\n","2026-05-02 06:55:36",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add levalencia\u002Fagent-god-mode --skill ln-811-algorithm-optimizer",{"tool":53,"command":54},"bunx","bunx skills add levalencia\u002Fagent-god-mode --skill ln-811-algorithm-optimizer",{"tool":56,"command":57},"pnpm","pnpm dlx skills add levalencia\u002Fagent-god-mode --skill ln-811-algorithm-optimizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-811-algorithm-optimizer\u002FSKILL.md",true,[61,67],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fbenchmark_generation.md","REFERENCE","参考文档",3566,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-811-algorithm-optimizer\u002Freferences\u002Fbenchmark_generation.md",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Foptimization_categories.md",3496,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-811-algorithm-optimizer\u002Freferences\u002Foptimization_categories.md",[72,94,129,156,182,210],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":33},"01M6EM8ES5M9J4S8N78NJST0YC","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fzarr-python\u002FSKILL.md",[],[79,80,81,82,83,84,85,86,87,88,89,90,91,92,93],"python","zarr python","storage","integration","s3","gcs","cloud","dask","parallel","pipelines","arrays","numpy","scientific computing","scale","scientific",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":111,"publishedAt":33},"01M6EM8AR6ZFKZ9YVW8TTG850Z","zabbix","Zabbix monitoring system automation via API and Python. Use when: (1) Managing hosts, templates, items, triggers, or host groups, (2) Automating monitoring configuration, (3) Sending data via Zabbix trapper\u002Fsender, (4) Querying historical data or events, (5) Bulk operations on Zabbix objects, (6) Maintenance window management, (7) User\u002Fpermission management","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fzabbix-api-skill\u002FSKILL.md",[100,103,106],{"categoryNo":101,"categoryName":102,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":104,"categoryName":105,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":107,"categoryName":108,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[96,79,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,31,128],"automation","window management","monitoring","data","templates","api","system","operations","use","maintenance","objects","permission","bulk operations","triggers","host","events","bulk",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":33},"01M6EM6Q9JG846ECQY9A210A26","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fx-twitter-growth\u002FSKILL.md",[],[136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155],"twitter","x twitter growth","growth","competitive intelligence","search","analyzing","plan","marketing","web search","competitors","analyze","write","optimize","social","intelligence","viral","growth engine","mechanics","grow","competitive",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":33},"01M6EM3FQNPYNKPC4CV9TCVNGD","what-if-oracle","Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like \"what if...\", \"what would happen if...\", \"what are the possibilities\", \"explore scenarios\", \"scenario analysis\", \"possibility space\", \"what could go wrong\", \"best case \u002F worst case\", \"risk analysis\", \"contingency planning\", \"strategic options\", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fwhat-if-oracle\u002FSKILL.md",[],[163,164,165,166,167,168,169,170,171,172,173,174,120,175,176,177,178,179,180,181],"oracle","what if oracle","test","planning","ux","futures","risk","analysis","explore","decision","branch","question","exploration","options","stress-test","strategies","trigger","case","multi",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":191,"publishedAt":33},"01M6EM08C06RGDYCJ86HAPK0FF","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fvercel-react-best-practices\u002FSKILL.md",[188],{"categoryNo":189,"categoryName":190,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[192,193,194,195,196,197,198,199,200,201,202,203,204,115,205,206,207,208,209,125],"react","vercel react best practices","best practices","react best practices","vercel","writing","performance","components","react components","guidelines","tasks","code","Optimization","Next.js","refactoring","performance optimization","next","pages",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":224,"publishedAt":33},"01M6EM00S13326QM08DTM94J6Z","venue-templates","Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fvenue-templates\u002FSKILL.md",[216,219,220,221],{"categoryNo":217,"categoryName":218,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":104,"categoryName":105,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":222,"categoryName":223,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000036","内容创作者",[116,225,26,201,226,227,228,229,230,231,232,147,233,234,235,236,237,238,93,239],"venue templates","NeurIPS","ICML","LaTeX","science","Bash","access","read","edit","proposals","Academic","requirements","formatting","journal","chi"]