Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计通过

lifecyclemodel-automated-builder生命周期模型自动构建器

Agent Skill

lifecyclemodel-automated-builder 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。

总安装

190

周安装

8

GitHub Stars

4

下载量

67
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:lifecyclemodel-automated-builder(生命周期模型自动构建器)
来源仓库:https://github.com/tiangong-lca/skills
仓库路径:skills/lifecyclemodel-automated-builder
安装命令:
npx skills add https://github.com/tiangong-lca/skills --skill lifecyclemodel-automated-builder
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/tiangong-lca/skills --skill lifecyclemodel-automated-builder

简介

lifecyclemodel-automated-builder 用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词快速定位候选结果。
  • 通过 npx skills add 命令从指定仓库安装,需确认权限和维护状态。
  • 使用前建议核验是否会触发联网、命令执行或文件读写操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Lifecycle Model Automated Builder

Use this skill when the source of truth is a set of existing local process-automated-builder run directories and the next step is to assemble a native lifecyclemodel artifact locally.

Read First

  1. references/workflow.md
  2. references/model-contract.md
  3. references/source-analysis.md

Guardrails

  • The canonical runtime path is skill -> Node wrapper -> tiangong CLI.
  • Persistent build outputs must use an explicit --out-dir; this skill does not choose a default output root.
  • For repeatable runs, use an explicit output directory such as /abs/path/artifacts/<case_slug>/....
  • The current canonical slices are:

- tiangong lifecyclemodel auto-build - tiangong lifecyclemodel validate-build - tiangong lifecyclemodel publish-build

  • The supported workflow is CLI-based and local to your build inputs:

- no Python workflow - no MCP transport - no remote lifecyclemodel CRUD - no reference-model discovery against KB / LLM services

  • The skill produces native json_ordered only. It does not emit json_tg, rule_verification, or resulting-process artifacts.
  • validate-build and publish-build now exist as dedicated CLI follow-up commands; do not reintroduce those stages inside the skill.
  • Only local_runs[] is executable today. Discovery hints may be recorded as deferred notes, but they are not executed inside this skill.

Workflow

  1. Prepare a manifest whose core input is local_runs[].
  2. Pick an output directory, typically under a path such as /abs/path/artifacts/<case_slug>/....
  3. Run node scripts/run-lifecyclemodel-automated-builder.mjs build --input <manifest> --out-dir <dir>.
  4. During assembly, preserve TianGong native model conventions from tiangong-lca-next:

- lifeCycleModelInformation.quantitativeReference.referenceToReferenceProcess - technology.processes.processInstance[*].referenceToProcess - technology.processes.processInstance[*].connections.outputExchange - computed @multiplicationFactor - a valid referenceToResultingProcess reference inside json_ordered

  1. Review the local outputs:

- run-plan.json - resolved-manifest.json - selection/selection-brief.md - discovery/reference-model-summary.json - models/**/tidas_bundle/lifecyclemodels/*.json - models/**/summary.json - models/**/connections.json - models/**/process-catalog.json - reports/lifecyclemodel-auto-build-report.json

  1. If the workflow later needs validation or publish handoff, call the dedicated CLI follow-up commands instead of rebuilding those paths inside the skill:

- node scripts/run-lifecyclemodel-automated-builder.mjs validate --run-dir <dir> - node scripts/run-lifecyclemodel-automated-builder.mjs publish --run-dir <dir>

  1. If someone asks for remote discovery or AI-assisted model selection, add it as a native tiangong lifecyclemodel... capability first.

Commands

node lifecyclemodel-automated-builder/scripts/run-lifecyclemodel-automated-builder.mjs build \
  --input lifecyclemodel-automated-builder/assets/example-request.json \
  --out-dir /abs/path/artifacts/<case_slug>/lifecyclemodel-auto-build \
  --dry-run

node lifecyclemodel-automated-builder/scripts/run-lifecyclemodel-automated-builder.mjs build \
  --input /abs/path/request.json \
  --out-dir /abs/path/artifacts/<case_slug>/lifecyclemodel-auto-build

node lifecyclemodel-automated-builder/scripts/run-lifecyclemodel-automated-builder.mjs build \
  --input lifecyclemodel-automated-builder/assets/example-local-runs.json \
  --out-dir /abs/path/artifacts/<case_slug>/lifecyclemodel-auto-build

node lifecyclemodel-automated-builder/scripts/run-lifecyclemodel-automated-builder.mjs validate \
  --run-dir /abs/path/artifacts/<case_slug>/lifecyclemodel-auto-build

node lifecyclemodel-automated-builder/scripts/run-lifecyclemodel-automated-builder.mjs publish \
  --run-dir /abs/path/artifacts/<case_slug>/lifecyclemodel-auto-build

Troubleshooting

  • Local CLI override issues: set TIANGONG_LCA_CLI_DIR or pass --cli-dir only when you intentionally need an unpublished working tree.
  • Missing --out-dir: the wrapper requires an explicit output path such as /abs/path/artifacts/<case_slug>/....
  • Missing local_runs[]: the current canonical slice only accepts local process-build runs.
  • Validation/publish follow-up: use the dedicated CLI subcommands against one existing auto-build run; they work from local build outputs and do not perform remote writes.
  • Validation failures on required model fields: inspect references/model-contract.md.
  • Topology disagreements: inspect references/source-analysis.md for native lifecycle model conventions.
  • If you need remote discovery or writes, add that capability to the native CLI instead of extending this skill with a separate runtime.

Bundled Resources

  • scripts/run-lifecyclemodel-automated-builder.mjs: native Node wrapper that delegates to tiangong lifecyclemodel....
  • assets/example-request.json: minimal current-slice manifest using local_runs[].
  • assets/example-local-runs.json: multi-run local assembly manifest example.
  • references/workflow.md: current CLI-backed workflow and deferred slices.
  • references/source-analysis.md: extracted conventions from tiangong-lca-next, tidas-sdk, and tidas-tools.
  • references/model-contract.md: native json_ordered fields required before validation or publish.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.16%
按下载量换算22

Claude

29%
按下载量换算19

Cursor

18.76%
按下载量换算13

Gemini CLI

9.87%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills