Token导航 LogoToken导航

Agent Skill · 研究检索

plot-sprint(情节冲刺)

用于处理 Jira 项目、任务、缺陷、Sprint、负责人和状态流转。它适合让 Agent 辅助查询工单、汇总迭代进展、创建任务或整理需求和缺陷信息。使用时要确认项目权限、字段配置和工作流规则,不同团队的 Issue 类型、状态和必填字段可能不同;涉及批量改状态、改负责人或创建工单时,应先预览变更内容再执行。

plot-sprint 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,权限为只读;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 58,594。

总安装 412周安装 17GitHub Stars 2下载 135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:plot-sprint(情节冲刺)
来源仓库:https://github.com/eins78/skills
仓库路径:skills/plot-sprint
安装命令:
npx skills add https://github.com/eins78/skills --skill plot-sprint
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/eins78/skills --skill plot-sprint

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。

plot-sprint 用于处理 Jira 项目中的任务、缺陷、Sprint 和状态流转,适合辅助查询工单、汇总迭代进展或创建新任务。它适用于敏捷开发环境,可帮助 Agent 整理需求和缺陷信息,跟踪负责人变更和工作流规则。使用时需结合具体项目的 Issue 类型、字段配置和权限设置,支持预览变更后再执行批量操作。

安装命令为 npx skills add https://github.com/eins78/skills --skill plot-sprint,需确保有对应 Jira 项目的读写权限。涉及敏感操作时应先脱敏并确认最小权限,避免误改生产环境数据或触发不必要的审批流程。

来源仓库内路径:skills/plot-sprint

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/eins78/skills --skill plot-sprint;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

plot-sprint 怎么安装?

在终端执行 npx skills add https://github.com/eins78/skills --skill plot-sprint。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

plot-sprint 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。

plot-sprint 需要什么权限?

权限级别是只读。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。

plot-sprint 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。

plot-sprint 用的人多吗?

公开数据是累计安装 412 次,近一周安装 17 次,下载 135 次,GitHub 2 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。

plot-sprint 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。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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。
  • 只想先试试效果、不希望它改动本地文件的人。

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
plot-sprint

情节冲刺 · 本页

4122只读未明确有提醒

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

Plot: Sprint

Sprints are not plans. Plans track *what* to build; sprints track *when* to ship it. Sprint files live in docs/sprints/, committed directly to main — no PR, no review gate. Principle 2 ("Plans merge before implementation") does not apply to sprints.

Input: $ARGUMENTS determines the subcommand.

FormAction
/plot-sprintStatus (infer slug or list all)
/plot-sprint <slug>Status of slug (or create if not found)
/plot-sprint <slug> commitLock sprint contents
/plot-sprint <slug> startBegin the sprint
/plot-sprint <slug> closeEnd timebox, capture retro
/plot-sprint <slug> add/remove/reprioChange sprint scope (see Scope Change)
/plot-sprint <slug>: <goal>Create slug with goal

Argument parsing: $ARGUMENTS = [<slug>] [<subcommand>] [<args>]

  • $ARGUMENTS[0] → slug (first word, if present)
  • $ARGUMENTS[1] → subcommand: commit, start, close
  • Create detected by : in slug token (e.g. week-1: Ship auth)
  • If no slug given: discover from docs/sprints/active/ — one active sprint → use it, multiple → list and ask, none → offer to create

Setup

Add a ## Plot Config section to the adopting project's CLAUDE.md:

## Plot Config
- **Project board:** <your-project-name> (#<number>)  <!-- optional, for `gh pr edit --add-project` -->
- **Branch prefixes:** idea/, feature/, bug/, docs/, infra/
- **Plan directory:** docs/plans/
- **Active index:** docs/plans/active/
- **Delivered index:** docs/plans/delivered/
- **Sprint directory:** docs/sprints/

Model Guidance

StepsMin. TierNotes
Create, commit, start, statusSmallGit commands, templates, file ops
CloseMidCheckbox parsing + reading plan files to check delivery status of [slug] refs

All sprint operations are structural (Small or Mid). No Frontier needed.

Sprint Lifecycle

flowchart LR
    A["/plot-sprint<br/><slug>: <goal>"] -->|"⏸ drafting"| B["Planning"]
    B -->|"⏳ /plot-sprint commit"| C["Committed"]
    C -->|"⚡ /plot-sprint start"| D["Active"]
    D -->|"⏳ /plot-sprint close"| E["Closed"]

Legend: ⚡ automate ASAP · ⏸ natural pause · ⏳ human-paced

Guardrail

Sprint files must not contain ## Design or ## Approach sections. If detected, warn: "This looks like a plan, not a sprint. Use /plot-idea for plans."

Subcommands

Create: /plot-sprint <slug>: <goal>

Create a new sprint in Planning phase.

Pacing: ⏸ natural pause (drafting)

1. Parse Input

Extract <slug> (before the colon) and <goal> (after the colon). Both are required.

  • Slug: trimmed, lowercase, hyphens only
  • Goal: the sprint goal as a sentence

If no colon or missing parts: "Usage: /plot-sprint <slug>: <goal>"

2. Determine ISO Week Prefix

Derive the ISO week prefix from today's date for the filename:

WEEK_PREFIX=$(date -u +%Y-W%V)

The sprint file will be named docs/sprints/${WEEK_PREFIX}-<slug>.md.

3. Pre-flight Checks
ls docs/sprints/${WEEK_PREFIX}-<slug>.md 2>/dev/null

If file exists: "Sprint <slug> already exists for week ${WEEK_PREFIX}."

4. Discover Active Plans

List active plans so the user can add them to the sprint:

ls docs/plans/active/ 2>/dev/null

If plans exist, present: "Found N active plans. Add any to this sprint?" List them and let the user select which to include (or none). Selected plans are added as [slug] items under the appropriate MoSCoW tier.

5. Create Sprint File
mkdir -p docs/sprints

Write docs/sprints/${WEEK_PREFIX}-<slug>.md using the template from skills/plot/templates/sprint.md, substituting <title> and <sprint goal>.

Item format: - [] [slug] description (plan reference) or - [] description (lightweight task).

Item Annotations

Plan-backed items carry HTML comment annotations for automation tracking:

- [ ] [slug] description <!-- pr: #N, status: draft, branch: feature/slug -->
FieldSet byValues
pr/plot-approvePR number (#N) or none
status/plot-approve, /plot-delivernot-started, draft, open, merged
branch/plot-approveImplementation branch name
reviewed_atReview trackingISO 8601 timestamp
review_shaReview trackingHEAD SHA at time of review

Annotations are created by /plot-approve and updated by /plot-deliver. The status subcommand reads them for enriched output.

Review Tracking

The review_sha annotation enables skip-if-unchanged review:

  1. Compare current HEAD SHA of the PR branch to the review_sha in the annotation
  2. If same → no new commits since last review, skip
  3. If different → new commits, needs re-review
  4. If status is merged → never needs review

Use skills/plot/scripts/plot-review-status.sh <sprint-slug> to get review freshness for all sprint items as JSON.

Leave Start/End dates as placeholders — the user fills them during the Planning phase.

6. Update Plan Files

For each plan-backed item ([slug]) added in step 4, update the referenced plan file to record sprint membership:

  • Resolve the plan file via docs/plans/active/<slug>.md
  • Add - **Sprint:** <sprint-slug> to its ## Status section (after the Phase line)

This enables sprint awareness in /plot-approve and /plot-deliver.

7. Commit to Main

Sprint files are committed directly to main (include any updated plan files):

git add docs/sprints/${WEEK_PREFIX}-<slug>.md docs/plans/
git commit -m "sprint: create <slug>"
git push
8. Summary

Print:

  • Created: docs/sprints/${WEEK_PREFIX}-<slug>.md
  • Sprint: [*] Planning > [] Committed > [] Active > [] Closed
  • Plan files updated: N (if any)
  • Next: add items, set dates, then /plot-sprint <slug> commit when ready

Commit: /plot-sprint <slug> commit

Lock sprint contents. Team has agreed on what's in scope.

Pacing: ⏳ human-paced (team agreement)

1. Find Sprint File
ls docs/sprints/*-<slug>.md 2>/dev/null

If not found: "No sprint found for <slug>."

Read the sprint file. Check Phase field:

  • If not Planning: "Sprint is in <phase> phase, not Planning. Cannot commit."
2. Validate End Date

Check that the **End:** field has a real date (not the placeholder YYYY-MM-DD).

If missing or placeholder: "Set an end date before committing. Edit the sprint file directly."

3. Update Phase

Change **Phase:** Planning → **Phase:** Committed

4. Commit
git add docs/sprints/*-<slug>.md
git commit -m "sprint: commit <slug>"
git push
5. Summary

Print:

  • Committed: <slug>
  • Sprint: [] Planning > [x] Committed > [] Active > [] Closed
  • End date: <end date>
  • Items: N must-haves, N should-haves, N could-haves
  • Next: /plot-sprint <slug> start when the sprint begins

Start: /plot-sprint <slug> start

Begin the sprint. Creates the active symlink.

Pacing: ⚡ automate ASAP (mechanical transition)

1. Find and Validate Sprint File

Find sprint file, check Phase is Committed.

2. Create Active Symlink
mkdir -p docs/sprints/active
ln -s ../${WEEK_PREFIX}-<slug>.md docs/sprints/active/<slug>.md
3. Update Phase

Change **Phase:** Committed → **Phase:** Active

4. Commit
git add docs/sprints/*-<slug>.md docs/sprints/active/<slug>.md
git commit -m "sprint: start <slug>"
git push
5. Summary

Print:

  • Started: <slug>
  • Sprint: [] Planning > [] Committed > [x] Active > [] Closed
  • End date: <end date>
  • Active symlink: docs/sprints/active/<slug>.md
  • Next: work on sprint items. When timebox ends, /plot-sprint <slug> close

Close: /plot-sprint <slug> close

End the timebox. Check MoSCoW completeness and capture retrospective.

Pacing: ⏳ human-paced (retrospective)

1. Find and Validate Sprint File

Find sprint file, check Phase is Active.

2. MoSCoW Completeness Check

Parse the sprint file for checkbox items in each tier:

  • Count checked - [x] vs unchecked - [] items per tier
  • For plan-backed items ([slug]), check if the referenced plan is delivered (exists in docs/plans/delivered/)

Present results:

Must Have:  2/4 complete
Should Have: 1/2 complete
Could Have:  0/1 complete

If must-haves are incomplete, present three options:

  1. Close anyway (must-haves stay unchecked in place)
  2. Move incomplete must-haves to Deferred — move each unchecked - [] line from ### Must Have to ### Deferred, preserving the original text
  3. Hold off (don't close yet)
3. Capture Retrospective

Ask the user: "Add a retrospective? (optional)"

If yes, prompt for:

  • What went well?
  • What could improve?
  • Action items for next sprint?

Fill the ## Retrospective section using the template from skills/plot/templates/retrospective.md. Include the Metrics subsection with actual counts from step 2.

4. Update Phase and Remove Symlink

Change **Phase:** Active → **Phase:** Closed

git rm docs/sprints/active/<slug>.md
git add docs/sprints/*-<slug>.md
git commit -m "sprint: close <slug>"
git push
5. Summary

Print:

  • Closed: <slug>
  • Sprint: [] Planning > [] Committed > [] Active > [x] Closed
  • Must-haves: N/M complete
  • Deferred: N items (if any moved)
  • Retrospective: captured / skipped
  • Suggested next actions:

1. Review the retrospective action items 2. Carry deferred items to the next sprint: /plot-sprint <new-slug>: <goal> 3. If all planned work is delivered: /plot-release to cut a release


Scope Change

Scope changes are allowed during Active (or Committed) sprints. All changes are logged in the sprint file's ## Notes > ### Scope Changes section for traceability.

Adding items mid-sprint:

  • Add the new - [] item to the appropriate MoSCoW tier
  • Log: - YYYY-MM-DD: Added [slug] to Must/Should/Could — <reason>
  • If plan-backed ([slug]), update the plan's Sprint field

Removing or deferring items:

  • Move the item to the ### Deferred section (do not delete — preserve history)
  • Log: - YYYY-MM-DD: Deferred [slug] from Must — <reason>

Changing MoSCoW tier:

  • Move the item between tier sections (e.g., Must → Should)
  • Log: - YYYY-MM-DD: Reprioritized [slug] Must → Should — <reason>

Commit scope changes directly to main with message: sprint: scope change <slug>.


Status: /plot-sprint or /plot-sprint <slug>

Show sprint status.

1. Resolve Slug

If slug provided ($ARGUMENTS[0] present, no subcommand):

  • Find sprint file: ls docs/sprints/*-<slug>.md 2>/dev/null
  • Found → show status for that sprint (step 2)
  • Not found → "No sprint <slug> found. Create it with /plot-sprint <slug>: <goal>"

If no arguments:

  • List active sprints: ls docs/sprints/active/ 2>/dev/null
  • One active sprint → use it, show status (step 2)
  • Multiple → list all active sprints with summary
  • None → "No active sprints. Create one with /plot-sprint <slug>: <goal>"
2. For Each Sprint

Read the sprint file and display:

  • Sprint name and goal
  • Phase
  • Time remaining (days until end date; "ended N days ago" if past)
  • MoSCoW progress: Must N/M, Should N/M, Could N/M
  • For plan-backed items with annotations: show PR number, status, and branch
3. Summary
## Active Sprints

- `<slug>` — "<goal>" | [*] Active | 3 days remaining | Must: 2/4 | Should: 1/2 | Could: 0/1

平台分布

Codex

36.54%
按下载量换算49

Claude

31.98%
按下载量换算43

Cursor

18.09%
按下载量换算24

Gemini CLI

10.27%
按下载量换算14

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

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