Token导航 LogoToken导航

Agent Skill · 研究检索

ln-810-performance-optimizer(ln 810 性能优化器)

ln-810-performance-optimizer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

ln-810-performance-optimizer 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 33,574。

总安装 2,328周安装 98GitHub Stars 441下载 815核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ln-810-performance-optimizer(ln 810 性能优化器)
来源仓库:https://github.com/levnikolaevich/claude-code-skills
仓库路径:skills/ln-810-performance-optimizer
安装命令:
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-810-performance-optimizer
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-810-performance-optimizer

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息。ln-810-performance-optimizer 属于研究检索类 Skill,可作为该场景下的辅助能力补充。适合根据关键词或任务场景快速定位候选结果。可结合来源仓库和原始 README 核验具体用法。安装前建议确认权限范围和维护状态。注意是否会触发联网、命令执行或文件读写操作。

来源仓库内路径:skills/ln-810-performance-optimizer

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-8…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

ln-810-performance-optimizer 怎么安装?

在终端执行 npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-810-perform…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ln-810-performance-optimizer 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ln-810-performance-optimizer 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-810-performance-optimizer 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

ln-810-performance-optimizer 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

ln-810-performance-optimizer 用的人多吗?

公开数据是累计安装 2,328 次,近一周安装 98 次,下载 815 次,GitHub 441 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ln-810-performance-optimizer 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
ln-810-performance-optimizer

ln 810 性能优化器 · 本页

2,328441执行命令未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. If shared/ is missing, fetch files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}.

Type: L2 Domain Coordinator Category: 8XX Optimization

Performance Optimizer

Runtime-backed multi-cycle optimization coordinator. Profiles, researches, validates, and executes optimization hypotheses until target reached, plateau detected, or budget exhausted.

Inputs

InputRequiredDescription
targetYesendpoint, function, or pipeline to optimize
observed_metricYescurrent performance problem
target_metricNouser or research-derived target
max_cyclesNodefault 3

Purpose & Scope

  • Detect whether optimization is the right tool
  • Run iterative cycles: profile -> gate -> research -> target -> context -> validate -> execute
  • Preserve optimization artifacts under .hex-skills/optimization/{slug}/ and runtime state under .hex-skills/optimization/runtime/runs/{run_id}/
  • Resume deterministically from the last checkpointed phase
  • Keep cycle summaries machine-readable

Runtime Contract

MANDATORY READ: Load shared/references/ci_tool_detection.md MANDATORY READ: Load shared/references/coordinator_runtime_contract.md, shared/references/optimization_runtime_contract.md, shared/references/coordinator_summary_contract.md

Runtime CLI:

node shared/scripts/optimization-runtime/cli.mjs start --slug {slug} --manifest-file .hex-skills/optimization/{slug}/manifest.json
node shared/scripts/optimization-runtime/cli.mjs status --slug {slug}
node shared/scripts/optimization-runtime/cli.mjs record-worker-result --payload '{...}'
node shared/scripts/optimization-runtime/cli.mjs record-summary --payload '{...}'
node shared/scripts/optimization-runtime/cli.mjs record-cycle --payload '{...}'
node shared/scripts/optimization-runtime/cli.mjs checkpoint --phase PHASE_8_EXECUTE --payload '{...}'
node shared/scripts/optimization-runtime/cli.mjs advance --to PHASE_9_CYCLE_BOUNDARY

Runtime Layout

Runtime state is run-scoped, while optimization artifacts stay slug-scoped:

.hex-skills/optimization/
  runtime/active/ln-810/{slug}.json
  runtime/runs/{run_id}/manifest.json
  runtime/runs/{run_id}/state.json
  runtime/runs/{run_id}/checkpoints.json
  runtime/runs/{run_id}/history.jsonl
  runtime-artifacts/runs/{run_id}/optimization-coordinator/ln-810--{slug}.json
  runtime-artifacts/runs/{run_id}/optimization-worker/{worker}--{child_identifier}.json
  {slug}/context.md
  {slug}/ln-814-log.tsv

Workflow

Phase 0: Preflight

  1. Validate:

- target identifiable - observed metric provided - git clean state - test infrastructure exists

  1. Detect stack and optional service topology.
  2. Derive slug.
  3. Build manifest with:

- slug - target - observed_metric - target_metric - execution_mode - cycle_config

  1. Start runtime and checkpoint PHASE_0_PREFLIGHT.

Phase 1: Parse Input

  1. Normalize the problem statement.
  2. Set or defer target_metric.
  3. Checkpoint PHASE_1_PARSE_INPUT.

Phase 2: Profile

  1. Compute deterministic child metadata:

- identifier=ln-811--{slug}--cycle-{current_cycle} - child run_id - exact summaryArtifactPath=.hex-skills/runtime-artifacts/runs/{parent_run_id}/optimization-worker/ln-811--{slug}--cycle-{current_cycle}.json

  1. Checkpoint PHASE_2_PROFILE with child_run.
  2. Invoke ln-811-performance-profiler with the child runId and exact summaryArtifactPath.
  3. Read the emitted optimization-worker summary envelope from the exact artifact path.
  4. Record the worker summary with record-worker-result.

Phase 3: Wrong Tool Gate

Evaluate profiler output:

GateMeaningAction
PROCEEDoptimization work is justifiedcontinue
CONCERNSmeasurements usable but imperfectcontinue with warning
BLOCKwrong tool, already optimized, or infrastructure-boundaggregate and exit
WAIVEDuser overrides BLOCKcontinue with explicit waiver

Rules:

  • cycle 1 BLOCK -> finish as diagnostic result
  • cycle 2+ BLOCK due to already_optimized or within_industry_norm -> finish as successful stop

Checkpoint PHASE_3_WRONG_TOOL_GATE with:

  • gate_verdict
  • stop_reason when blocked
  • final_result when terminal

Phase 4: Research

  1. Compute deterministic child metadata for ln-812.
  2. Checkpoint PHASE_4_RESEARCH with child_run.
  3. Invoke ln-812-optimization-researcher with the child runId and exact summaryArtifactPath.
  4. Read and record the emitted optimization-worker summary envelope.
  5. If no hypotheses remain, stop after aggregate/report.

Phase 5: Set Target

  1. Resolve target metric:

- user-specified target wins - otherwise use research target with confidence - otherwise default to 50% improvement

  1. Checkpoint PHASE_5_SET_TARGET with target_metric.

Phase 6: Write Context

  1. Build .hex-skills/optimization/{slug}/context.md.
  2. Include:

- problem statement - performance map - target metrics - hypotheses and conflicts - local codebase findings - previous cycles

  1. Checkpoint PHASE_6_WRITE_CONTEXT with context_file.

Phase 7: Validate Plan

  1. Compute deterministic child metadata for ln-813.
  2. Checkpoint PHASE_7_VALIDATE_PLAN with validation_verdict and child_run.
  3. Invoke ln-813-optimization-plan-validator with the child runId and exact summaryArtifactPath.
  4. Read and record the emitted evaluation-coordinator summary envelope.
  5. If verdict is NO_GO, pause runtime until user resolves or waives.

Phase 8: Execute

execution_mode=execute:

  1. Compute deterministic child metadata for ln-814.
  2. Checkpoint PHASE_8_EXECUTE with child_run.
  3. Invoke ln-814-optimization-executor with the child runId and exact summaryArtifactPath.
  4. Read and record the emitted optimization-worker summary envelope.

execution_mode=plan_only:

  1. Do not run ln-814.
  2. Checkpoint PHASE_8_EXECUTE as skipped_by_mode.

Phase 9: Cycle Boundary

  1. Record the cycle summary with record-cycle.
  2. Evaluate stop conditions:

- target met - plateau - max cycles reached - no new hypotheses

  1. If continuing:

- merge previous branch when needed - increment current_cycle - checkpoint PHASE_9_CYCLE_BOUNDARY - advance back to PHASE_2_PROFILE

  1. If stopping:

- checkpoint PHASE_9_CYCLE_BOUNDARY with stop_reason - advance to PHASE_10_AGGREGATE

Phase 10: Aggregate

  1. Aggregate all cycle summaries from runtime state.
  2. Compute cumulative improvement.
  3. Checkpoint PHASE_10_AGGREGATE.

Phase 11: Report

  1. Produce final report with:

- per-cycle summary - cumulative improvement - final result - gap analysis when target not met

  1. Checkpoint PHASE_11_REPORT with:

- report_ready=true - final_result

  1. Record the optimization-coordinator summary envelope with record-summary.
  2. Complete runtime only after the report checkpoint and coordinator summary exist.

Worker Invocation (MANDATORY)

PhaseSkillPurpose
2ln-811-performance-profilerBuild measured performance map
4ln-812-optimization-researcherResearch hypotheses and targets
7ln-813-optimization-plan-validatorValidate feasibility via evaluation-platform review (L2 Coordinator)
8ln-814-optimization-executorExecute optimization strike and bisect
Skill(skill: "ln-811-performance-profiler")
Skill(skill: "ln-812-optimization-researcher")
Agent(... Skill(skill: "ln-813-optimization-plan-validator"))
Agent(... Skill(skill: "ln-814-optimization-executor"))

TodoWrite format (mandatory)

- Start ln-810 runtime (pending)
- Run profiler and record summary (pending)
- Apply Wrong Tool Gate (pending)
- Run researcher and record summary (pending)
- Set target metric (pending)
- Write optimization context (pending)
- Validate plan and record summary (pending)
- Execute or skip by mode (pending)
- Record cycle boundary (pending)
- Aggregate results and write final report (pending)

Critical Rules

  • Runtime state is the optimization orchestration SSOT.
  • Worker outputs are consumed only through summary JSON artifacts.
  • plan_only is a first-class execution mode, not an informal branch.
  • NO_GO from ln-813 must pause runtime until explicitly resolved.
  • Cycle history lives in runtime state, not in chat memory.
  • A terminal diagnostic result is still a valid DONE orchestration outcome.

Definition of Done

  • Runtime started and preflight/input checkpoints recorded
  • Profiler and researcher summaries recorded deterministically
  • Wrong Tool Gate result checkpointed
  • Target metric and context file checkpointed
  • Validator summary recorded; NO_GO handled via PAUSED when needed
  • Executor summary recorded or skipped_by_mode checkpointed
  • Cycle boundary recorded for every completed cycle
  • Aggregate and final report checkpoints recorded
  • Runtime completed with final result and resume-free terminal state

Phase 12: Meta-Analysis

MANDATORY READ: Load shared/references/meta_analysis_protocol.md

Skill type: optimization-coordinator. Run after phases complete. Output to chat using the optimization-coordinator format.

Reference Files

  • shared/references/coordinator_runtime_contract.md
  • shared/references/optimization_runtime_contract.md
  • shared/references/coordinator_summary_contract.md
  • ../ln-811-performance-profiler/SKILL.md
  • ../ln-812-optimization-researcher/SKILL.md
  • ../ln-813-optimization-plan-validator/SKILL.md
  • ../ln-814-optimization-executor/SKILL.md

Version: 3.0.0 Last Updated: 2026-03-15

平台分布

Codex

38.35%
按下载量换算313

Claude

28.21%
按下载量换算230

Cursor

19.02%
按下载量换算155

Gemini CLI

9.5%
按下载量换算77

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-810-performance-optimizer 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills