Token导航 LogoToken导航

Agent Skill · 研究检索

ln-830-code-modernization-coordinator(ln 830 代码现代化协调员)

ln-830-code-modernization-coordinator 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-830-code-modernization-coordinator 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,权限为需要联网;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 29,170。

总安装 3,096周安装 133GitHub Stars 437下载 1,085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-830-code-modernization-coordinator(ln 830 代码现代化协调员)
来源仓库:https://github.com/levnikolaevich/claude-code-skills
仓库路径:skills/ln-830-code-modernization-coordinator
安装命令:
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-830-code-modernization-coordinator
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-830-code-modernization-coordinator

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。

用于代码现代化改造,支持 JS/TS 和 .NET 等项目类型。根据审计报告选择合适工人执行具体现代化任务。确保变更经过验证且不影响现有功能稳定性。安装前建议确认权限范围、维护状态及是否触发代码修改操作。

ln-830-code-modernization-coordinator 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/ln-830-code-modernization-coordinator

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

    它需要需要联网,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-830-code-modernization-coordinator 怎么安装?

在终端执行 npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-830-code-mo…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ln-830-code-modernization-coordinator 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-830-code-modernization-coordinator 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

ln-830-code-modernization-coordinator 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-830-code-modernization-coordinator 用的人多吗?

公开数据是累计安装 3,096 次,近一周安装 133 次,下载 1,085 次,GitHub 437 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-830-code-modernization-coordinator 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

  • 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

  • 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-830-code-modernization-coordinator

ln 830 代码现代化协调员 · 本页

3,096437需要联网未明确有提醒

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}.

ln-830-code-modernization-coordinator

Type: L2 Domain Coordinator Category: 8XX Optimization

Runtime-backed coordinator for code modernization. Delegates OSS replacement and bundle-size work to isolated child runs, records machine-readable worker summaries, and emits a final coordinator summary.


Overview

AspectDetails
InputAudit report, target module, or modernization scope
OutputAggregated modernization report with durable worker artifacts
Workersln-831 (OSS replacer), ln-832 (bundle optimizer)
Runtime.hex-skills/modernization/runtime/runs/{run_id}/

Workflow

Phases: Pre-flight -> Analyze Input -> Delegate Workers -> Collect Results -> Verify Summary -> Report


Runtime Contract

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

Runtime CLI:

node shared/scripts/modernization-runtime/cli.mjs start --identifier repo-modernization --manifest-file <file>
node shared/scripts/modernization-runtime/cli.mjs status --identifier repo-modernization
node shared/scripts/modernization-runtime/cli.mjs checkpoint --phase PHASE_2_DELEGATE_WORKERS --payload '{...}'
node shared/scripts/modernization-runtime/cli.mjs record-worker-result --payload '{...}'
node shared/scripts/modernization-runtime/cli.mjs record-summary --payload '{...}'
node shared/scripts/modernization-runtime/cli.mjs advance --to PHASE_3_COLLECT_RESULTS
node shared/scripts/modernization-runtime/cli.mjs complete

Required state fields:

  • worker_plan
  • worker_results
  • child_runs
  • verification_passed
  • report_ready
  • summary_recorded

Domain checkpoints:

  • PHASE_1_ANALYZE_INPUT: target modules, worker selection, stack detection
  • PHASE_2_DELEGATE_WORKERS: one child_run per delegated worker with worker name, runId, and summaryArtifactPath
  • PHASE_3_COLLECT_RESULTS: recorded worker summaries and unresolved failures
  • PHASE_4_VERIFY_SUMMARY: final report path, verification verdict, summary readiness

Guard rules:

  • do not advance from PHASE_2_DELEGATE_WORKERS until every planned worker emitted a valid modernization-worker summary
  • do not complete until the final report checkpoint exists and the modernization-coordinator summary was recorded
  • consume worker JSON summaries only; never infer worker status from prose output

Phase 0: Pre-flight

Confirm the modernization request has a valid scope and a deterministic runtime target.

CheckRequiredAction if Missing
Audit report or target moduleYesBlock modernization
Project pathYesBlock modernization
Verification command availableYesBlock if workers cannot verify changes
Existing active run for identifierNoPause if conflicting run exists

Phase 1: Analyze Input

Select workers based on project type and findings.

Worker selection:

Conditionln-831ln-832
Audit findings include OSS candidatesYesNo
JS/TS project with package.jsonNoYes
Both conditions trueYesYes
Explicit target module onlyYesOptional if bundle impact exists

Stack detection:

IndicatorStackln-832 Eligible
package.json + JS/TS filesJS/TSYes
*.csproj.NETNo
requirements.txt or pyproject.tomlPythonNo
go.modGoNo

Checkpoint payload must include:

  • input_source
  • worker_plan
  • stack_detection
  • skipped_reasons

Phase 2: Delegate Workers

Delegate one child run per selected worker. Child runs are deterministic and artifact-driven.

Delegate using the concrete worker identities selected by the routing rules below. Do not synthesize family placeholders or guessed skill IDs in prompts.

Delegation context:

FieldTypeDescription
projectPathstringAbsolute path to the target project
auditReportstringPath to audit output when applicable
targetModulestringOptional focused module path
identifierstringStable worker identifier
runIdstringDeterministic child run id
summaryArtifactPathstringExact JSON path for the worker summary
optionsobjectVerification flags and worker-specific settings

Delegation rules:

  • launch ln-831 before ln-832 when both are selected
  • ln-832 consumes the project state produced by accepted modernization changes, not a guessed baseline
  • checkpoint every child run before waiting on its result
  • record every emitted worker summary with record-worker-result

Phase 3: Collect Results

Aggregate validated worker summaries only.

Worker summary fields consumed by the coordinator:

FieldDescription
producer_skillworker identity (ln-831 or ln-832)
summary_kindmust be modernization-worker
identifierstable worker identifier
payload.statuscompleted, partial, or failed
payload.changes_appliedkept changes
payload.changes_discardeddiscarded experiments
payload.verificationbuild/test verification result
payload.artifact_pathworker-owned durable report path
payload.warningsnon-blocking issues

Collection output:

  • worker_results
  • success_count
  • partial_count
  • failed_count
  • warnings

Phase 4: Verify Summary

Prepare the final modernization report and verify the coordinator can finish deterministically.

Verification checklist:

  • every planned worker produced one valid summary envelope
  • aggregate counts match recorded worker results
  • final report path exists or is ready to be written
  • report_ready and verification_passed are true before completion

Failure handling:

  1. Keep successful worker results intact.
  2. Mark failed workers explicitly in the coordinator report.
  3. Do not invent rollback actions beyond what workers already verified.

Phase 5: Report

Coordinator report schema:

FieldDescription
input_sourceaudit report or target module
workers_activateddelegated workers
modules_replacedOSS replacements applied
loc_removedcustom code removed
bundle_reductionfinal bundle reduction summary
verification_passedaggregate verification verdict
per_worker[]machine-readable worker result summaries
warnings[]cross-worker warnings

Completion sequence:

  1. Write the durable report.
  2. Checkpoint the report path and verification verdict.
  3. Record the modernization-coordinator summary envelope with record-summary.
  4. Complete runtime only after the report checkpoint and coordinator summary exist.

Configuration

Options:
  audit_report: "docs/project/codebase_audit.md"
  target_module: ""
  enable_oss_replacer: true
  enable_bundle_optimizer: true
  run_tests: true
  run_build: true

Error Handling

Recoverable:

ErrorRecovery
ln-831 partial resultContinue with ln-832 if still applicable
ln-832 failurePreserve ln-831 result and report partial modernization
Build failure in one workerKeep failure in coordinator report, continue collection

Fatal:

ErrorAction
No workers activatedFinish with empty-result report
Runtime validation failurePause run and require intervention
Missing worker summary for planned child runDo not advance from collection

References

  • ../ln-831-oss-replacer/SKILL.md
  • ../ln-832-bundle-optimizer/SKILL.md
  • ../ln-645-open-source-replacer/SKILL.md
  • shared/references/ci_tool_detection.md

TodoWrite format (mandatory):

- Analyze modernization input (in_progress)
- Delegate ln-831-oss-replacer child run (pending)
- Delegate ln-832-bundle-optimizer child run (pending)
- Aggregate modernization-worker summaries (pending)

Worker Invocation (MANDATORY)

PhaseWorkerContext
2ln-831-oss-replacerIsolated child run with runId and exact summaryArtifactPath
2ln-832-bundle-optimizerIsolated child run with runId and exact summaryArtifactPath

All workers: start the child runtime, checkpoint the child_run metadata, then invoke the worker skill explicitly and consume the emitted modernization-worker summary envelope via record-worker-result.

# Sequential per selected worker (ln-831 before ln-832 when both selected):
node shared/scripts/modernization-runtime/cli.mjs start --skill {worker} --identifier {identifier} --manifest-file {workerManifestPath} --run-id {childRunId} --summary-artifact-path {childSummaryArtifactPath}
node shared/scripts/optimization-runtime/cli.mjs checkpoint --phase PHASE_2_DELEGATE --payload '{"child_run":{"worker":"{worker}","run_id":"{childRunId}","summary_artifact_path":"{childSummaryArtifactPath}"}}'
Skill(skill: "{worker}", args: "{identifier} --run-id {childRunId} --summary-artifact-path {childSummaryArtifactPath}")
Read {childSummaryArtifactPath}
node shared/scripts/optimization-runtime/cli.mjs record-worker-result --payload-file {childSummaryArtifactPath}

Worker token substitution: {worker} is ln-831-oss-replacer or ln-832-bundle-optimizer.


Definition of Done

  • Runtime started with a validated manifest and stable identifier
  • Modernization scope analyzed and workers selected from real input
  • One child run delegated per selected worker
  • Every child run emitted a valid modernization-worker summary
  • Coordinator report aggregates replacements, bundle changes, warnings, and verification results
  • Final modernization-coordinator summary recorded before completion

Phase 6: Meta-Analysis

MANDATORY READ: Load shared/references/meta_analysis_protocol.md

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


Version: 1.0.0 Last Updated: 2026-03-08

平台分布

Codex

36.94%
按下载量换算401

Claude

29.03%
按下载量换算315

Cursor

16.72%
按下载量换算181

Gemini CLI

9.38%
按下载量换算102

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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