[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71NJ5XEPV7M21RHJA5J2FSS":3,"skill-same:01M71NJ5XEPV7M21RHJA5J2FSS":132},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":49,"updatedAt":50,"install":51,"resources":63},"01M71NJ5XEPV7M21RHJA5J2FSS","ln-810-performance-optimizer",null,"Multi-cycle performance optimization with profiling and bottleneck analysis. Use when optimizing application performance.","vitalikpestov\u002FSkills-Catalog","vitalikpestov","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F13882997?v=4","01M71N4QG0CWRXX4R24JQZXDDQ","Vitalik Pestov","01M71N4QGMSYRW607DDSE0CQMM",2,"MIT","https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"optimizer","ln 810 performance optimizer","ln","performance optimizer","performance","application","profiling","performance optimization","multi","with","bottleneck analysis","use","true","Optimization","analysis","when","bottleneck","cycle","2026-11-10 10:56:23",false,"---\nname: ln-810-performance-optimizer\ndescription: \"Multi-cycle performance optimization with profiling and bottleneck analysis. Use when optimizing application performance.\"\ndisable-model-invocation: true\nlicense: MIT\n---\n\n> **Paths:** File paths (`references\u002F`, `..\u002Fln-*`) are relative to this skill directory.\n\n**Type:** L2 Domain Coordinator\n**Category:** 8XX Optimization\n\n# Performance Optimizer\n\nRuntime-backed multi-cycle optimization coordinator. Profiles, researches, validates, and executes optimization hypotheses until target reached, plateau detected, or budget exhausted.\n\n## Inputs\n\n| Input | Required | Description |\n|-------|----------|-------------|\n| `target` | Yes | endpoint, function, or pipeline to optimize |\n| `observed_metric` | Yes | current performance problem |\n| `target_metric` | No | user or research-derived target |\n| `max_cycles` | No | default `3` |\n\n## Purpose & Scope\n\n- Detect whether optimization is the right tool\n- Run iterative cycles: `profile -> gate -> research -> target -> context -> validate -> execute`\n- Preserve optimization artifacts under `.hex-skills\u002Foptimization\u002F{slug}\u002F` and runtime state under `.hex-skills\u002Foptimization\u002Fruntime\u002Fruns\u002F{run_id}\u002F`\n- Resume deterministically from the last checkpointed phase\n- Keep cycle summaries machine-readable\n\n## Runtime Contract\n\n**MANDATORY READ:** Load `references\u002Fci_tool_detection.md`\n**MANDATORY READ:** Load `references\u002Fcoordinator_runtime_contract.md`, `references\u002Foptimization_runtime_contract.md`, `references\u002Fcoordinator_summary_contract.md`\n\nRuntime CLI:\n\n```bash\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs start --slug {slug} --manifest-file .hex-skills\u002Foptimization\u002F{slug}\u002Fmanifest.json\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs status --slug {slug}\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs record-worker-result --payload '{...}'\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs record-summary --payload '{...}'\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs record-cycle --payload '{...}'\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs checkpoint --phase PHASE_8_EXECUTE --payload '{...}'\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs advance --to PHASE_9_CYCLE_BOUNDARY\n```\n\n## Runtime Layout\n\nRuntime state is run-scoped, while optimization artifacts stay slug-scoped:\n\n```text\n.hex-skills\u002Foptimization\u002F\n  runtime\u002Factive\u002Fln-810\u002F{slug}.json\n  runtime\u002Fruns\u002F{run_id}\u002Fmanifest.json\n  runtime\u002Fruns\u002F{run_id}\u002Fstate.json\n  runtime\u002Fruns\u002F{run_id}\u002Fcheckpoints.json\n  runtime\u002Fruns\u002F{run_id}\u002Fhistory.jsonl\n  runtime-artifacts\u002Fruns\u002F{run_id}\u002Foptimization-coordinator\u002Fln-810--{slug}.json\n  runtime-artifacts\u002Fruns\u002F{run_id}\u002Foptimization-worker\u002F{worker}--{child_identifier}.json\n  {slug}\u002Fcontext.md\n  {slug}\u002Fln-814-log.tsv\n```\n\n## Workflow\n\n### Phase 0: Preflight\n\n1. Validate:\n   - target identifiable\n   - observed metric provided\n   - git clean state\n   - test infrastructure exists\n2. Detect stack and optional service topology.\n3. Derive slug.\n4. Build manifest with:\n   - `slug`\n   - `target`\n   - `observed_metric`\n   - `target_metric`\n   - `execution_mode`\n   - `cycle_config`\n5. Start runtime and checkpoint `PHASE_0_PREFLIGHT`.\n\n### Phase 1: Parse Input\n\n1. Normalize the problem statement.\n2. Set or defer `target_metric`.\n3. Checkpoint `PHASE_1_PARSE_INPUT`.\n\n### Phase 2: Profile\n\n1. Compute deterministic child metadata:\n   - `identifier=ln-811--{slug}--cycle-{current_cycle}`\n   - child `run_id`\n   - exact `summaryArtifactPath=.hex-skills\u002Fruntime-artifacts\u002Fruns\u002F{parent_run_id}\u002Foptimization-worker\u002Fln-811--{slug}--cycle-{current_cycle}.json`\n2. Checkpoint `PHASE_2_PROFILE` with `child_run`.\n3. Invoke `ln-811-performance-profiler` with the child `runId` and exact `summaryArtifactPath`.\n4. Read the emitted `optimization-worker` summary envelope from the exact artifact path.\n5. Record the worker summary with `record-worker-result`.\n\n### Phase 3: Wrong Tool Gate\n\nEvaluate profiler output:\n\n| Gate | Meaning | Action |\n|------|---------|--------|\n| `PROCEED` | optimization work is justified | continue |\n| `CONCERNS` | measurements usable but imperfect | continue with warning |\n| `BLOCK` | wrong tool, already optimized, or infrastructure-bound | aggregate and exit |\n| `WAIVED` | user overrides `BLOCK` | continue with explicit waiver |\n\nRules:\n- cycle 1 `BLOCK` -> finish as diagnostic result\n- cycle 2+ `BLOCK` due to `already_optimized` or `within_industry_norm` -> finish as successful stop\n\nCheckpoint `PHASE_3_WRONG_TOOL_GATE` with:\n- `gate_verdict`\n- `stop_reason` when blocked\n- `final_result` when terminal\n\n### Phase 4: Research\n\n1. Compute deterministic child metadata for `ln-812`.\n2. Checkpoint `PHASE_4_RESEARCH` with `child_run`.\n3. Invoke `ln-812-optimization-researcher` with the child `runId` and exact `summaryArtifactPath`.\n4. Read and record the emitted `optimization-worker` summary envelope.\n5. If no hypotheses remain, stop after aggregate\u002Freport.\n\n### Phase 5: Set Target\n\n1. Resolve target metric:\n   - user-specified target wins\n   - otherwise use research target with confidence\n   - otherwise default to 50% improvement\n2. Checkpoint `PHASE_5_SET_TARGET` with `target_metric`.\n\n### Phase 6: Write Context\n\n1. Build `.hex-skills\u002Foptimization\u002F{slug}\u002Fcontext.md`.\n2. Include:\n   - problem statement\n   - performance map\n   - target metrics\n   - hypotheses and conflicts\n   - local codebase findings\n   - previous cycles\n3. Checkpoint `PHASE_6_WRITE_CONTEXT` with `context_file`.\n\n### Phase 7: Validate Plan\n\n1. Compute deterministic child metadata for `ln-813`.\n2. Checkpoint `PHASE_7_VALIDATE_PLAN` with `validation_verdict` and `child_run`.\n3. Invoke `ln-813-optimization-plan-validator` with the child `runId` and exact `summaryArtifactPath`.\n4. Read and record the emitted `evaluation-coordinator` summary envelope.\n5. If verdict is `NO_GO`, pause runtime until user resolves or waives.\n\n### Phase 8: Execute\n\n`execution_mode=execute`:\n\n1. Compute deterministic child metadata for `ln-814`.\n2. Checkpoint `PHASE_8_EXECUTE` with `child_run`.\n3. Invoke `ln-814-optimization-executor` with the child `runId` and exact `summaryArtifactPath`.\n4. Read and record the emitted `optimization-worker` summary envelope.\n\n`execution_mode=plan_only`:\n\n1. Do not run `ln-814`.\n2. Checkpoint `PHASE_8_EXECUTE` as `skipped_by_mode`.\n\n### Phase 9: Cycle Boundary\n\n1. Record the cycle summary with `record-cycle`.\n2. Evaluate stop conditions:\n   - target met\n   - plateau\n   - max cycles reached\n   - no new hypotheses\n3. If continuing:\n   - merge previous branch when needed\n   - increment `current_cycle`\n   - checkpoint `PHASE_9_CYCLE_BOUNDARY`\n   - advance back to `PHASE_2_PROFILE`\n4. If stopping:\n   - checkpoint `PHASE_9_CYCLE_BOUNDARY` with `stop_reason`\n   - advance to `PHASE_10_AGGREGATE`\n\n### Phase 10: Aggregate\n\n1. Aggregate all cycle summaries from runtime state.\n2. Compute cumulative improvement.\n3. Checkpoint `PHASE_10_AGGREGATE`.\n\n### Phase 11: Report\n\n1. Produce final report with:\n   - per-cycle summary\n   - cumulative improvement\n   - final result\n   - gap analysis when target not met\n2. Checkpoint `PHASE_11_REPORT` with:\n   - `report_ready=true`\n   - `final_result`\n3. Record the `optimization-coordinator` summary envelope with `record-summary`.\n4. Complete runtime only after the report checkpoint and coordinator summary exist.\n\n## Worker Invocation (MANDATORY)\n\n**Host Skill Invocation:** `Skill(skill: \"...\", args: \"...\")` is mandatory delegation.\n- Claude: call the Skill tool exactly as shown.\n- Codex: if no Skill tool exists, locate the named skill in available skills, read its `SKILL.md`, treat `args` as `$ARGUMENTS`, execute that skill workflow, then return here with its result\u002Fartifact.\n- Do not inline worker logic or mark the worker complete without executing the target skill.\n\n| Phase | Skill | Purpose |\n|-------|--------|---------|\n| 2 | `ln-811-performance-profiler` | Build measured performance map |\n| 4 | `ln-812-optimization-researcher` | Research hypotheses and targets |\n| 7 | `ln-813-optimization-plan-validator` | Validate feasibility via evaluation-platform review (L2 Coordinator) |\n| 8 | `ln-814-optimization-executor` | Execute optimization strike and bisect |\n\n```javascript\nSkill(skill: \"ln-811-performance-profiler\")\nSkill(skill: \"ln-812-optimization-researcher\")\nAgent(... Skill(skill: \"ln-813-optimization-plan-validator\"))\nAgent(... Skill(skill: \"ln-814-optimization-executor\"))\n```\n\n## TodoWrite format (mandatory)\n\n```\n- Start ln-810 runtime (pending)\n- Run profiler and record summary (pending)\n- Apply Wrong Tool Gate (pending)\n- Run researcher and record summary (pending)\n- Set target metric (pending)\n- Write optimization context (pending)\n- Validate plan and record summary (pending)\n- Execute or skip by mode (pending)\n- Record cycle boundary (pending)\n- Aggregate results and write final report (pending)\n```\n\n## Critical Rules\n\n- Runtime state is the optimization orchestration SSOT.\n- Worker outputs are consumed only through summary JSON artifacts.\n- `plan_only` is a first-class execution mode, not an informal branch.\n- `NO_GO` from `ln-813` must pause runtime until explicitly resolved.\n- Cycle history lives in runtime state, not in chat memory.\n- A terminal diagnostic result is still a valid `DONE` orchestration outcome.\n\n## Definition of Done\n\n- [ ] Runtime started and preflight\u002Finput checkpoints recorded\n- [ ] Profiler and researcher summaries recorded deterministically\n- [ ] Wrong Tool Gate result checkpointed\n- [ ] Target metric and context file checkpointed\n- [ ] Validator summary recorded; `NO_GO` handled via `PAUSED` when needed\n- [ ] Executor summary recorded or `skipped_by_mode` checkpointed\n- [ ] Cycle boundary recorded for every completed cycle\n- [ ] Aggregate and final report checkpoints recorded\n- [ ] Runtime completed with final result and resume-free terminal state\n\n## Phase 12: Meta-Analysis\n\nOptional reference: load `references\u002Fmeta_analysis_protocol.md` only when the user asks for post-run meta-analysis or protocol-formatted run reflection.\n\nSkill type: `optimization-coordinator`. When requested, run after phases complete. Output to chat using the `optimization-coordinator` format.\n\n## Reference Files\n\n- `references\u002Fcoordinator_runtime_contract.md`\n- `references\u002Foptimization_runtime_contract.md`\n- `references\u002Fcoordinator_summary_contract.md`\n- `..\u002Fln-811-performance-profiler\u002FSKILL.md`\n- `..\u002Fln-812-optimization-researcher\u002FSKILL.md`\n- `..\u002Fln-813-optimization-plan-validator\u002FSKILL.md`\n- `..\u002Fln-814-optimization-executor\u002FSKILL.md`\n\n---\n**Version:** 3.0.0\n**Last Updated:** 2026-03-15\n","> **Paths:** File paths (`references\u002F`, `..\u002Fln-*`) are relative to this skill directory.\n\n**Type:** L2 Domain Coordinator\n**Category:** 8XX Optimization\n\n# Performance Optimizer\n\nRuntime-backed multi-cycle optimization coordinator. Profiles, researches, validates, and executes optimization hypotheses until target reached, plateau detected, or budget exhausted.\n\n## Inputs\n\n| Input | Required | Description |\n|-------|----------|-------------|\n| `target` | Yes | endpoint, function, or pipeline to optimize |\n| `observed_metric` | Yes | current performance problem |\n| `target_metric` | No | user or research-derived target |\n| `max_cycles` | No | default `3` |\n\n## Purpose & Scope\n\n- Detect whether optimization is the right tool\n- Run iterative cycles: `profile -> gate -> research -> target -> context -> validate -> execute`\n- Preserve optimization artifacts under `.hex-skills\u002Foptimization\u002F{slug}\u002F` and runtime state under `.hex-skills\u002Foptimization\u002Fruntime\u002Fruns\u002F{run_id}\u002F`\n- Resume deterministically from the last checkpointed phase\n- Keep cycle summaries machine-readable\n\n## Runtime Contract\n\n**MANDATORY READ:** Load `references\u002Fci_tool_detection.md`\n**MANDATORY READ:** Load `references\u002Fcoordinator_runtime_contract.md`, `references\u002Foptimization_runtime_contract.md`, `references\u002Fcoordinator_summary_contract.md`\n\nRuntime CLI:\n\n```bash\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs start --slug {slug} --manifest-file .hex-skills\u002Foptimization\u002F{slug}\u002Fmanifest.json\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs status --slug {slug}\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs record-worker-result --payload '{...}'\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs record-summary --payload '{...}'\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs record-cycle --payload '{...}'\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs checkpoint --phase PHASE_8_EXECUTE --payload '{...}'\nnode references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs advance --to PHASE_9_CYCLE_BOUNDARY\n```\n\n## Runtime Layout\n\nRuntime state is run-scoped, while optimization artifacts stay slug-scoped:\n\n```text\n.hex-skills\u002Foptimization\u002F\n  runtime\u002Factive\u002Fln-810\u002F{slug}.json\n  runtime\u002Fruns\u002F{run_id}\u002Fmanifest.json\n  runtime\u002Fruns\u002F{run_id}\u002Fstate.json\n  runtime\u002Fruns\u002F{run_id}\u002Fcheckpoints.json\n  runtime\u002Fruns\u002F{run_id}\u002Fhistory.jsonl\n  runtime-artifacts\u002Fruns\u002F{run_id}\u002Foptimization-coordinator\u002Fln-810--{slug}.json\n  runtime-artifacts\u002Fruns\u002F{run_id}\u002Foptimization-worker\u002F{worker}--{child_identifier}.json\n  {slug}\u002Fcontext.md\n  {slug}\u002Fln-814-log.tsv\n```\n\n## Workflow\n\n### Phase 0: Preflight\n\n1. Validate:\n   - target identifiable\n   - observed metric provided\n   - git clean state\n   - test infrastructure exists\n2. Detect stack and optional service topology.\n3. Derive slug.\n4. Build manifest with:\n   - `slug`\n   - `target`\n   - `observed_metric`\n   - `target_metric`\n   - `execution_mode`\n   - `cycle_config`\n5. Start runtime and checkpoint `PHASE_0_PREFLIGHT`.\n\n### Phase 1: Parse Input\n\n1. Normalize the problem statement.\n2. Set or defer `target_metric`.\n3. Checkpoint `PHASE_1_PARSE_INPUT`.\n\n### Phase 2: Profile\n\n1. Compute deterministic child metadata:\n   - `identifier=ln-811--{slug}--cycle-{current_cycle}`\n   - child `run_id`\n   - exact `summaryArtifactPath=.hex-skills\u002Fruntime-artifacts\u002Fruns\u002F{parent_run_id}\u002Foptimization-worker\u002Fln-811--{slug}--cycle-{current_cycle}.json`\n2. Checkpoint `PHASE_2_PROFILE` with `child_run`.\n3. Invoke `ln-811-performance-profiler` with the child `runId` and exact `summaryArtifactPath`.\n4. Read the emitted `optimization-worker` summary envelope from the exact artifact path.\n5. Record the worker summary with `record-worker-result`.\n\n### Phase 3: Wrong Tool Gate\n\nEvaluate profiler output:\n\n| Gate | Meaning | Action |\n|------|---------|--------|\n| `PROCEED` | optimization work is justified | continue |\n| `CONCERNS` | measurements usable but imperfect | continue with warning |\n| `BLOCK` | wrong tool, already optimized, or infrastructure-bound | aggregate and exit |\n| `WAIVED` | user overrides `BLOCK` | continue with explicit waiver |\n\nRules:\n- cycle 1 `BLOCK` -> finish as diagnostic result\n- cycle 2+ `BLOCK` due to `already_optimized` or `within_industry_norm` -> finish as successful stop\n\nCheckpoint `PHASE_3_WRONG_TOOL_GATE` with:\n- `gate_verdict`\n- `stop_reason` when blocked\n- `final_result` when terminal\n\n### Phase 4: Research\n\n1. Compute deterministic child metadata for `ln-812`.\n2. Checkpoint `PHASE_4_RESEARCH` with `child_run`.\n3. Invoke `ln-812-optimization-researcher` with the child `runId` and exact `summaryArtifactPath`.\n4. Read and record the emitted `optimization-worker` summary envelope.\n5. If no hypotheses remain, stop after aggregate\u002Freport.\n\n### Phase 5: Set Target\n\n1. Resolve target metric:\n   - user-specified target wins\n   - otherwise use research target with confidence\n   - otherwise default to 50% improvement\n2. Checkpoint `PHASE_5_SET_TARGET` with `target_metric`.\n\n### Phase 6: Write Context\n\n1. Build `.hex-skills\u002Foptimization\u002F{slug}\u002Fcontext.md`.\n2. Include:\n   - problem statement\n   - performance map\n   - target metrics\n   - hypotheses and conflicts\n   - local codebase findings\n   - previous cycles\n3. Checkpoint `PHASE_6_WRITE_CONTEXT` with `context_file`.\n\n### Phase 7: Validate Plan\n\n1. Compute deterministic child metadata for `ln-813`.\n2. Checkpoint `PHASE_7_VALIDATE_PLAN` with `validation_verdict` and `child_run`.\n3. Invoke `ln-813-optimization-plan-validator` with the child `runId` and exact `summaryArtifactPath`.\n4. Read and record the emitted `evaluation-coordinator` summary envelope.\n5. If verdict is `NO_GO`, pause runtime until user resolves or waives.\n\n### Phase 8: Execute\n\n`execution_mode=execute`:\n\n1. Compute deterministic child metadata for `ln-814`.\n2. Checkpoint `PHASE_8_EXECUTE` with `child_run`.\n3. Invoke `ln-814-optimization-executor` with the child `runId` and exact `summaryArtifactPath`.\n4. Read and record the emitted `optimization-worker` summary envelope.\n\n`execution_mode=plan_only`:\n\n1. Do not run `ln-814`.\n2. Checkpoint `PHASE_8_EXECUTE` as `skipped_by_mode`.\n\n### Phase 9: Cycle Boundary\n\n1. Record the cycle summary with `record-cycle`.\n2. Evaluate stop conditions:\n   - target met\n   - plateau\n   - max cycles reached\n   - no new hypotheses\n3. If continuing:\n   - merge previous branch when needed\n   - increment `current_cycle`\n   - checkpoint `PHASE_9_CYCLE_BOUNDARY`\n   - advance back to `PHASE_2_PROFILE`\n4. If stopping:\n   - checkpoint `PHASE_9_CYCLE_BOUNDARY` with `stop_reason`\n   - advance to `PHASE_10_AGGREGATE`\n\n### Phase 10: Aggregate\n\n1. Aggregate all cycle summaries from runtime state.\n2. Compute cumulative improvement.\n3. Checkpoint `PHASE_10_AGGREGATE`.\n\n### Phase 11: Report\n\n1. Produce final report with:\n   - per-cycle summary\n   - cumulative improvement\n   - final result\n   - gap analysis when target not met\n2. Checkpoint `PHASE_11_REPORT` with:\n   - `report_ready=true`\n   - `final_result`\n3. Record the `optimization-coordinator` summary envelope with `record-summary`.\n4. Complete runtime only after the report checkpoint and coordinator summary exist.\n\n## Worker Invocation (MANDATORY)\n\n**Host Skill Invocation:** `Skill(skill: \"...\", args: \"...\")` is mandatory delegation.\n- Claude: call the Skill tool exactly as shown.\n- Codex: if no Skill tool exists, locate the named skill in available skills, read its `SKILL.md`, treat `args` as `$ARGUMENTS`, execute that skill workflow, then return here with its result\u002Fartifact.\n- Do not inline worker logic or mark the worker complete without executing the target skill.\n\n| Phase | Skill | Purpose |\n|-------|--------|---------|\n| 2 | `ln-811-performance-profiler` | Build measured performance map |\n| 4 | `ln-812-optimization-researcher` | Research hypotheses and targets |\n| 7 | `ln-813-optimization-plan-validator` | Validate feasibility via evaluation-platform review (L2 Coordinator) |\n| 8 | `ln-814-optimization-executor` | Execute optimization strike and bisect |\n\n```javascript\nSkill(skill: \"ln-811-performance-profiler\")\nSkill(skill: \"ln-812-optimization-researcher\")\nAgent(... Skill(skill: \"ln-813-optimization-plan-validator\"))\nAgent(... Skill(skill: \"ln-814-optimization-executor\"))\n```\n\n## TodoWrite format (mandatory)\n\n```\n- Start ln-810 runtime (pending)\n- Run profiler and record summary (pending)\n- Apply Wrong Tool Gate (pending)\n- Run researcher and record summary (pending)\n- Set target metric (pending)\n- Write optimization context (pending)\n- Validate plan and record summary (pending)\n- Execute or skip by mode (pending)\n- Record cycle boundary (pending)\n- Aggregate results and write final report (pending)\n```\n\n## Critical Rules\n\n- Runtime state is the optimization orchestration SSOT.\n- Worker outputs are consumed only through summary JSON artifacts.\n- `plan_only` is a first-class execution mode, not an informal branch.\n- `NO_GO` from `ln-813` must pause runtime until explicitly resolved.\n- Cycle history lives in runtime state, not in chat memory.\n- A terminal diagnostic result is still a valid `DONE` orchestration outcome.\n\n## Definition of Done\n\n- [ ] Runtime started and preflight\u002Finput checkpoints recorded\n- [ ] Profiler and researcher summaries recorded deterministically\n- [ ] Wrong Tool Gate result checkpointed\n- [ ] Target metric and context file checkpointed\n- [ ] Validator summary recorded; `NO_GO` handled via `PAUSED` when needed\n- [ ] Executor summary recorded or `skipped_by_mode` checkpointed\n- [ ] Cycle boundary recorded for every completed cycle\n- [ ] Aggregate and final report checkpoints recorded\n- [ ] Runtime completed with final result and resume-free terminal state\n\n## Phase 12: Meta-Analysis\n\nOptional reference: load `references\u002Fmeta_analysis_protocol.md` only when the user asks for post-run meta-analysis or protocol-formatted run reflection.\n\nSkill type: `optimization-coordinator`. When requested, run after phases complete. Output to chat using the `optimization-coordinator` format.\n\n## Reference Files\n\n- `references\u002Fcoordinator_runtime_contract.md`\n- `references\u002Foptimization_runtime_contract.md`\n- `references\u002Fcoordinator_summary_contract.md`\n- `..\u002Fln-811-performance-profiler\u002FSKILL.md`\n- `..\u002Fln-812-optimization-researcher\u002FSKILL.md`\n- `..\u002Fln-813-optimization-plan-validator\u002FSKILL.md`\n- `..\u002Fln-814-optimization-executor\u002FSKILL.md`\n\n---\n**Version:** 3.0.0\n**Last Updated:** 2026-03-15\n",{"name":5,"license":15,"description":7,"disable-model-invocation":42},true,"main","fbfb242f793fdf040f3a1a6b100896c188c228c8","_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer",1,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog","https:\u002F\u002Fgithub.com\u002Fvitalikpestov","Listing on crypto exchanges","2026-06-15 22:12:56",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":42},[53,56,59],{"tool":54,"command":55},"npx","npx skills add vitalikpestov\u002FSkills-Catalog --skill ln-810-performance-optimizer",{"tool":57,"command":58},"bunx","bunx skills add vitalikpestov\u002FSkills-Catalog --skill ln-810-performance-optimizer",{"tool":60,"command":61},"pnpm","pnpm dlx skills add vitalikpestov\u002FSkills-Catalog --skill ln-810-performance-optimizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002FSKILL.md",[64,70,74,78,82,86,92,96,100,104,108,112,116,120,124,128],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fci_tool_detection.md","REFERENCE","参考文档",1986,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fci_tool_detection.md",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fcoordinator_runtime_contract.md",2707,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fcoordinator_runtime_contract.md",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fcoordinator_summary_contract.md",1009,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fcoordinator_summary_contract.md",{"path":79,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fmeta_analysis_protocol.md",1509,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fmeta_analysis_protocol.md",{"path":83,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Foptimization_runtime_contract.md",3747,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Foptimization_runtime_contract.md",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Fartifacts.mjs","SCRIPT","脚本",2463,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Fartifacts.mjs",{"path":93,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Fcli-helpers.mjs",3569,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Fcli-helpers.mjs",{"path":97,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Fcore.mjs",19048,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Fcore.mjs",{"path":101,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Floop-health.mjs",7667,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Floop-health.mjs",{"path":105,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Fruntime-constants.mjs",3880,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Fruntime-constants.mjs",{"path":109,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Fschemas.mjs",38117,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Fschemas.mjs",{"path":113,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Fvalidate.mjs",4943,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fscripts\u002Fcoordinator-runtime\u002Flib\u002Fvalidate.mjs",{"path":117,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs",10435,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fscripts\u002Foptimization-runtime\u002Fcli.mjs",{"path":121,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Fscripts\u002Foptimization-runtime\u002Flib\u002Fguards.mjs",10831,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fscripts\u002Foptimization-runtime\u002Flib\u002Fguards.mjs",{"path":125,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Fscripts\u002Foptimization-runtime\u002Flib\u002Fphases.mjs",818,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fscripts\u002Foptimization-runtime\u002Flib\u002Fphases.mjs",{"path":129,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":130,"sourceHtmlUrl":131},"references\u002Fscripts\u002Foptimization-runtime\u002Flib\u002Fstore.mjs",8536,"https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_AI-Automation\u002Fclaude-code-skills-levnikolaevich\u002Fplugins\u002Foptimization-suite\u002Fskills\u002Fln-810-performance-optimizer\u002Freferences\u002Fscripts\u002Foptimization-runtime\u002Flib\u002Fstore.mjs",[133,177,201,218,241,274],{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":155,"publishedAt":176},"01M71V1MC994P553631JZSWVYD","solana-dev","Use when user asks to \"build a Solana dapp\", \"write an Anchor program\", \"create a token\", \"debug Solana errors\", \"set up wallet connection\", \"test my Solana program\", \"deploy to devnet\", or \"explain Solana concepts\" (rent, accounts, PDAs, CPIs, etc.). End-to-end Solana development playbook covering wallet connection, Anchor\u002FPinocchio programs, Codama client generation, LiteSVM\u002FMollusk\u002FSurfpool testing, and security checklists. Integrates with the Solana MCP server for live documentation search. Prefers framework-kit (@solana\u002Fclient + @solana\u002Freact-hooks) for UI, wallet-standard-first connection (incl. ConnectorKit), @solana\u002Fkit for client\u002FRPC code, and @solana\u002Fweb3-compat for legacy boundaries.","https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_Web3\u002Fsolana-dev\u002Fskill\u002FSKILL.md",[139,144,147,150],{"categoryNo":140,"categoryName":141,"taxonomyType":142,"taxonomyTypeDesc":143},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":145,"categoryName":146,"taxonomyType":142,"taxonomyTypeDesc":143},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":148,"categoryName":149,"taxonomyType":142,"taxonomyTypeDesc":143},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":151,"categoryName":152,"taxonomyType":153,"taxonomyTypeDesc":154},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175],"dev","solana dev","solana","Wallet","search","testing","solana cli","kit","MCP","web3","react","create","server","write","playbook","live","security","ui","concepts","toolchain","2026-11-10 13:02:02",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":176},"01M71TYQPHE2YGKTT7DG9QCW3K","generating-trading-signals","Generate trading signals using technical indicators (RSI, MACD, Bollinger Bands, etc.).\nCombines multiple indicators into composite signals with confidence scores.\nUse when analyzing assets for trading opportunities or checking technical indicators.\nTrigger with phrases like \"get trading signals\", \"check indicators\", \"analyze for entry\",\n\"scan for opportunities\", \"generate buy\u002Fsell signals\", or \"technical analysis\".","https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_Trading-Finance\u002Fgenerating-trading-signals\u002FSKILL.md",[],[184,185,186,187,188,189,190,191,192,193,194,195,30,34,196,33,197,198,199,200],"generating trading signals","signals","trading signals","trading","get","technical indicators","for","scan","rsi","trigger","python","technical","Bash","code","io","check","analyze",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":207,"publishedAt":176},"01M71TY4CR3GKGQ3M12X9WN95Y","prediction-monitor","Prediction Monitor - Auto-activating skill for ML Deployment.\nTriggers on: prediction monitor, prediction monitor\nPart of the ML Deployment skill category.","https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_Trading-Finance\u002FAI Predictions\u002Fprediction-monitor\u002FSKILL.md",[],[208,209,210,190,211,212,169,213,214,215,216,217,196],"prediction","monitor","prediction monitor","deployment","read","edit","triggers","grep","auto","ml",{"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":224,"publishedAt":176},"01M71TXD9MYXZC39HCPP909HTZ","strategy-advisor","High-level strategic thinking and business decision guidance for planning and direction-setting.\nUse when: making strategic decisions, evaluating business options, setting direction, analyzing\ntrade-offs, or when user mentions strategy, business planning, competitive analysis, or long-term planning.","https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_Product-Apps\u002Fstrategy-advisor\u002FSKILL.md",[],[225,226,227,228,229,230,231,232,233,190,234,235,236,30,237,238,34,239,33,240],"strategy advisor","strategy","advisor","competitive","setting","thinking","planning","direction","trade-offs","long","decision","strategic","business","apps","decisions","trade",{"skillNo":242,"name":243,"nameZh":6,"description":244,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":245,"sourceHtmlUrl":246,"categories":247,"keywords":254,"publishedAt":176},"01M71TWHBT2R1P1FNWTW67ZREP","app-paywall-pilot","Design, audit, debug, and implement App Store-compliant mobile paywalls, subscription flows, pricing screens, trials, offers, feature gates, and subscription lifecycle UX. Use when the user asks to audit my paywall, fix App Store 3.1.2 rejection, improve trial-to-paid, choose plans\u002Fprices\u002Ftrials, review RevenueCat\u002FAdapty\u002FApphud\u002FSuperwall setup, calculate LTV\u002FROAS, or build paywall implementation.","https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_Product-Apps\u002Ffrom-dosesync\u002Fapp-paywall-pilot\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_Product-Apps\u002Ffrom-dosesync\u002Fapp-paywall-pilot\u002FSKILL.md",[248,251],{"categoryNo":249,"categoryName":250,"taxonomyType":142,"taxonomyTypeDesc":143},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":252,"categoryName":253,"taxonomyType":153,"taxonomyTypeDesc":154},"01JBSEEDCAT000000000000032","设计师",[255,256,257,258,259,260,261,262,263,264,265,266,34,267,268,269,270,271,272,273],"app","paywall","app paywall pilot","paid","paywalls","prices","choose","flows","fix","improve","design","app store","review","audit","ux","subscription","mobile","my","calculate",{"skillNo":275,"name":276,"nameZh":6,"description":277,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":278,"licenseFileUrl":279,"sourceHtmlUrl":280,"categories":281,"keywords":284,"publishedAt":176},"01M71TWET8GFKEB7ZHJPMQX29V","figma","Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_Product-Apps\u002Ffigma\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fvitalikpestov\u002FSkills-Catalog\u002Fblob\u002Fmain\u002F_Product-Apps\u002Ffigma\u002FSKILL.md",[282,283],{"categoryNo":148,"categoryName":149,"taxonomyType":142,"taxonomyTypeDesc":143},{"categoryNo":252,"categoryName":253,"taxonomyType":153,"taxonomyTypeDesc":154},[276,285,286,287,288,193,265,164,30,34,289,290,197,291,168,292,293,294,295,296],"fetch","ids","mcp setup","translate","mcp server","Variables","task","Nodes","figma mcp","code implementation","node","assets"]