Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问clear审计通过

ln-222-story-replanner222 故事重新规划器

Agent Skill

ln-222-story-replanner 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

6,261

周安装

267

GitHub Stars

437

下载量

2,072
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

3

许可证

MIT

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:ln-222-story-replanner(222 故事重新规划器)
来源仓库:https://github.com/levnikolaevich/claude-code-skills
仓库路径:skills/ln-222-story-replanner
安装命令:
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-222-story-replanner
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-222-story-replanner

简介

ln-222-story-replanner 用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 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

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.

Story Replanner

Type: L3 Worker Category: 2XX Planning

Standalone-first worker for Story replanning. It compares ideal Story intent with existing Stories and applies the resulting operations.

MANDATORY READ

Load these before execution:

  • shared/references/planning_worker_runtime_contract.md
  • shared/references/coordinator_summary_contract.md
  • shared/references/environment_state_contract.md
  • shared/references/storage_mode_detection.md
  • shared/references/template_loading_pattern.md
  • references/replan_algorithm_stories.md

Inputs

Core inputs:

  • epicData
  • idealPlan
  • existingStoryIds
  • standardsResearch
  • teamId
  • autoApprove

Optional transport inputs:

  • runId
  • summaryArtifactPath

The worker must remain fully usable without caller-provided runId and without summaryArtifactPath. In standalone mode it generates its own run_id before emitting the summary envelope.

Runtime

Runtime family: planning-worker-runtime

Identifier:

  • epic-{epicId}

Phases:

  1. PHASE_0_CONFIG
  2. PHASE_1_RESOLVE_CONTEXT
  3. PHASE_2_LOAD_EXISTING_STORIES
  4. PHASE_3_CLASSIFY_REPLAN
  5. PHASE_4_CONFIRM_OR_AUTOAPPROVE
  6. PHASE_5_APPLY_REPLAN
  7. PHASE_6_UPDATE_KANBAN
  8. PHASE_7_WRITE_SUMMARY
  9. PHASE_8_SELF_CHECK

Managed child-run mode:

  • caller starts the runtime with --run-id and --summary-artifact-path
  • runtime writes the final summary artifact directly to the caller-provided path
  • parent coordinator records the resulting story-plan-worker artifact

Standalone mode:

  • runtime generates its own run_id
  • runtime still returns the same structured summary envelope
  • artifact writing is optional unless summaryArtifactPath is provided

Output Contract

Always build a structured summary envelope:

  • schema_version
  • summary_kind=story-plan-worker
  • run_id
  • identifier
  • producer_skill=ln-222
  • produced_at
  • payload

Payload fields:

  • mode
  • epic_id
  • stories_planned
  • stories_created
  • stories_updated
  • stories_canceled
  • story_urls
  • warnings
  • kanban_updated
  • research_path_used

If summaryArtifactPath is provided:

  • write the same JSON summary to that path

If summaryArtifactPath is not provided:

  • return the same summary in structured output only

Managed artifact path pattern:

  • .hex-skills/runtime-artifacts/runs/{parent_run_id}/story-plan-worker/ln-222--{identifier}.json

Workflow

  1. Resolve Epic context if not already provided.
  2. Load existing Stories one by one.
  3. Normalize ideal vs existing Story structures.
  4. Run the replan algorithm to classify KEEP, UPDATE, OBSOLETE, CREATE.
  5. Show operations summary unless autoApprove=true.
  6. Execute provider-specific updates.
  7. Update kanban.
  8. Return structured summary.

Critical Rules

  • Prefer conservative updates when matching is ambiguous.
  • Preserve finished work when replanning conflicts with completed Stories.
  • Keep the worker standalone-capable.
  • Never require coordinator runtime state to operate.
  • Return machine-readable results, not prose-only outcomes.
  • STOP before save_issue: verify all 9 sections present in body: Story, Context, Acceptance Criteria, Implementation Tasks, Test Strategy, Technical Notes, Definition of Done, Dependencies, Assumptions. PreToolUse hook will BLOCK creation without them.

Definition of Done

  • Existing Stories loaded and normalized
  • Replan algorithm applied
  • Required updates, cancellations, and creations executed
  • kanban updated
  • Structured summary returned
  • Summary artifact written when summaryArtifactPath is provided

Version: 3.0.0 Last Updated: 2025-12-23

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

Claude Code

25.59%
按下载量换算530

Gemini CLI

22.42%
按下载量换算465

Codex

17.79%
按下载量换算369

OpenCode

13.18%
按下载量换算273

Antigravity

7.32%
按下载量换算152

windsurf

3.41%
按下载量换算71

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。

来源信息

继续浏览同类 Skills