create-plan

GitHub

将用户提示转化为单一、可执行的编程任务计划。通过只读模式扫描上下文,仅在最必要时提问,并严格遵循模板输出包含目标、范围、原子化行动项及待办问题的计划,不生成代码或元解释。

bundled/skills/create-plan/SKILL.md foryourhealth111-pixel/Vibe-Skills

Trigger Scenarios

用户明确要求创建计划 涉及编码任务的规划需求

Install

npx skills add foryourhealth111-pixel/Vibe-Skills --skill create-plan -g -y
More Options

Non-standard path

npx skills add https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/main/bundled/skills/create-plan -g -y

Use without installing

npx skills use foryourhealth111-pixel/Vibe-Skills@create-plan

指定 Agent (Claude Code)

npx skills add foryourhealth111-pixel/Vibe-Skills --skill create-plan -a claude-code -g -y

安装 repo 全部 skill

npx skills add foryourhealth111-pixel/Vibe-Skills --all -g -y

预览 repo 内 skill

npx skills add foryourhealth111-pixel/Vibe-Skills --list

SKILL.md

Frontmatter
{
    "name": "create-plan",
    "metadata": {
        "short-description": "Create a plan"
    },
    "description": "Create a concise plan. Use when a user explicitly asks for a plan related to a coding task."
}

Create Plan

Goal

Turn a user prompt into a single, actionable plan delivered in the final assistant message.

Minimal workflow

Throughout the entire workflow, operate in read-only mode. Do not write or update files.

  1. Scan context quickly

    • Read README.md and any obvious docs (docs/, CONTRIBUTING.md, ARCHITECTURE.md).
    • Skim relevant files (the ones most likely touched).
    • Identify constraints (language, frameworks, CI/test commands, deployment shape).
  2. Ask follow-ups only if blocking

    • Ask at most 1–2 questions.
    • Only ask if you cannot responsibly plan without the answer; prefer multiple-choice.
    • If unsure but not blocked, make a reasonable assumption and proceed.
  3. Create a plan using the template below

    • Start with 1 short paragraph describing the intent and approach.
    • Clearly call out what is in scope and what is not in scope in short.
    • Then provide a small checklist of action items (default 6–10 items).
      • Each checklist item should be a concrete action and, when helpful, mention files/commands.
      • Make items atomic and ordered: discovery → changes → tests → rollout.
      • Verb-first: "Add…", "Refactor…", "Verify…", "Ship…".
    • Include at least one item for tests/validation and one for edge cases/risk when applicable.
    • If there are unknowns, include a tiny Open questions section (max 3).
  4. Do not preface the plan with meta explanations; output only the plan as per template

Plan template (follow exactly)

# Plan

<1–3 sentences: what we're doing, why, and the high-level approach.>

## Scope
- In:
- Out:

## Action items
[ ] <Step 1>
[ ] <Step 2>
[ ] <Step 3>
[ ] <Step 4>
[ ] <Step 5>
[ ] <Step 6>

## Open questions
- <Question 1>
- <Question 2>
- <Question 3>

Checklist item guidance

Good checklist items:

  • Point to likely files/modules: src/..., app/..., services/...
  • Name concrete validation: "Run npm test", "Add unit tests for X"
  • Include safe rollout when relevant: feature flag, migration plan, rollback note

Avoid:

  • Vague steps ("handle backend", "do auth")
  • Too many micro-steps
  • Writing code snippets (keep the plan implementation-agnostic)

Version History

  • f627ab5 Current 2026-07-25 04:40

Same Skill Collection

bundled/skills/.system/skill-creator/SKILL.md
bundled/skills/.system/skill-installer/SKILL.md
bundled/skills/aeon/SKILL.md
bundled/skills/algorithmic-art/SKILL.md
bundled/skills/architecture-patterns/SKILL.md
bundled/skills/astropy/SKILL.md
bundled/skills/autonomous-builder/SKILL.md
bundled/skills/brainstorming/SKILL.md
bundled/skills/cancel-ralph/SKILL.md
bundled/skills/chembl-database/SKILL.md
bundled/skills/citation-management/SKILL.md
bundled/skills/claude-skills/SKILL.md
bundled/skills/clinical-reports/SKILL.md
bundled/skills/clinicaltrials-database/SKILL.md
bundled/skills/clinpgx-database/SKILL.md
bundled/skills/code-reviewer/SKILL.md
bundled/skills/coding-tutor/SKILL.md
bundled/skills/commit-with-reflection/SKILL.md
bundled/skills/comprehensive-research-agent/SKILL.md
bundled/skills/content-research-writer/SKILL.md
bundled/skills/context-fundamentals/SKILL.md
bundled/skills/context-hunter/SKILL.md
bundled/skills/creating-data-visualizations/SKILL.md
bundled/skills/cs-foundations/SKILL.md
bundled/skills/dask/SKILL.md
bundled/skills/data-artist/SKILL.md
bundled/skills/data-quality-frameworks/SKILL.md
bundled/skills/data-storytelling/SKILL.md
bundled/skills/datacommons-client/SKILL.md
bundled/skills/datavis/SKILL.md
bundled/skills/denario/SKILL.md
bundled/skills/designing-experiments/SKILL.md
bundled/skills/detecting-data-anomalies/SKILL.md
bundled/skills/detecting-performance-regressions/SKILL.md
bundled/skills/dialectic/SKILL.md
bundled/skills/digital-brain/SKILL.md
bundled/skills/dnanexus-integration/SKILL.md
bundled/skills/doc/SKILL.md
bundled/skills/docs-review/SKILL.md
bundled/skills/docs-write/SKILL.md
bundled/skills/document-skills/docx/SKILL.md
bundled/skills/document-skills/pdf/SKILL.md
bundled/skills/document-skills/pptx/SKILL.md
bundled/skills/document-skills/SKILL.md
bundled/skills/documentation-lookup/SKILL.md
bundled/skills/docx-comment-reply/SKILL.md
bundled/skills/docx/SKILL.md
bundled/skills/edgartools/SKILL.md
bundled/skills/embedding-strategies/SKILL.md

Metadata

Files
0
Version
f627ab5
Hash
bcccc37b
Indexed
2026-07-25 04:40

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-07 16:35
浙ICP备14020137号-1 $방문자$