standard_plan_core
Standardizes project intake by converting casual requests into formal specs and task lists.
Install
mkdir -p .claude/skills/standard-plan-core && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12598" && unzip -o skill.zip -d .claude/skills/standard-plan-core && rm skill.zipInstalls to .claude/skills/standard-plan-core
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
将口语化/不完整需求转化为可执行“规划包”，并给出 `PLAN_READY/BLOCKED` 裁决。 本 Skill 是默认规划入口。Key capabilities
- →Clarify spoken or incomplete requirements into a decidable description.
- →Define standard requirements documents with goals, scope, constraints, and acceptance criteria.
- →Design prototypes including business processes, API drafts, and data changes.
- →Plan tasks, assign ownership, and identify risks and preconditions.
- →Decide if a plan is ready for development or blocked.
- →Output a summary of the standard requirements document, prototype design, and task assignments.
How it works
The skill guides the user through five planning stages: intake, requirement definition, prototyping, task assignment, and final readiness decision. It produces required artifacts at each stage and applies gates to ensure quality before proceeding.
Inputs & outputs
When to use standard_plan_core
- →Clarifying a new project request
- →Defining project scope and constraints
- →Creating a plan for a new feature
About this skill
Skill: standard_plan_core
Purpose
将口语化/不完整需求转化为可执行“规划包”，并给出 PLAN_READY/BLOCKED 裁决。
本 Skill 是默认规划入口。
When To Use
- 默认使用本 Skill（未显式要求简易流程时）
- 需求跨模块、跨团队、跨服务
- 涉及 API/数据结构/依赖关系变更
- 需求歧义较多或风险较高
Boundary
- 允许：需求澄清、标准需求文档、原型设计、任务拆分、责任划分、风险评估
- 禁止：直接修改业务代码、执行发布动作
Workflow (Planning Stages)
- 口语化需求澄清（INTAKE）
- 标准需求定义（REQUIREMENT_SPEC）
- 原型设计（PROTOTYPE_DESIGN）
- 任务规划与责任划分（PLANNING_OWNERSHIP）
- 规划就绪裁决（PLAN_READY_DECISION）
Stage 1: INTAKE
目标：将口语化输入转化为可裁决需求描述。
必产物：
- 背景与目标
- 范围与排除项
- 依赖与约束
- 歧义与待确认清单
门禁：
- 关键歧义未裁决不得进入下一阶段
Stage 2: REQUIREMENT_SPEC
目标：形成标准需求文档。
必产物：
- 需求文档（目标、范围、约束、验收标准）
门禁：
- 验收标准不可验证则 BLOCKED
Stage 3: PROTOTYPE_DESIGN
目标：将需求转换为实现导向原型。
必产物：
- 业务流程说明
- API 草案
- 数据与状态变化说明
- 异常场景说明
门禁：
- 原型与需求不一致不得进入下一阶段
Stage 4: PLANNING_OWNERSHIP
目标：形成可执行任务清单和责任划分。
必产物：
- Task/Sub Task 清单
- depends_on 依赖关系
- owner 责任划分
- 风险与前置条件清单
门禁：
- owner 缺失、依赖不清、循环依赖时 BLOCKED
Stage 5: PLAN_READY_DECISION
目标：给出规划是否可进入开发执行。
必产物：
- 规划结论（PLAN_READY/BLOCKED）
- 缺失项与补齐建议（如 BLOCKED）
Output Contract (Mandatory)
每次执行必须输出：
- 标准需求文档摘要
- 原型设计摘要
- 任务与责任划分摘要
- 风险与前置条件摘要
- 规划结论（PLAN_READY/BLOCKED）
DSL Alignment
- 开发流程规范：
.codex/DSL/flows/standard-dev-flow.adoc - 门禁规则：
.codex/DSL/rules/06-standard-dev-flow-rules.adoc - Task 定义：
.codex/DSL/rules/01-task-rules.adoc
When not to use it
- →When a simplified process is explicitly requested.
- →When requirements are clear and low risk.
- →When the task involves directly modifying business code or executing release actions.
Limitations
- →It cannot directly modify business code.
- →It cannot execute release actions.
- →Acceptance criteria must be verifiable, otherwise the plan is blocked.
How it compares
This skill formalizes the planning process into distinct stages with mandatory outputs and gates, unlike an ad-hoc approach that might skip critical verification steps.
Compared to similar skills
standard_plan_core side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| standard_plan_core (this skill) | 0 | 2mo | No flags | Intermediate |
| writing-plans | 15 | 3mo | Review | Intermediate |
| feature-design-assistant | 6 | 7mo | No flags | Intermediate |
| task-coordination-strategies | 3 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
writing-plans
obra
Use when you have a spec or requirements for a multi-step task, before touching code
feature-design-assistant
davila7
Turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when planning new features, designing architecture, or making significant changes to the codebase.
task-coordination-strategies
wshobson
Decompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.
swarm-planner
am-will
[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.
plan
indexedlabs
Plan work using Mighty (mt) by creating/updating specs and recording decisions, then spawning/structuring implementation tasks. Use when asked to plan/outline/break down a change, draft a spec (feature/rule/invariant/bug), record an ADR-style decision, or turn a fuzzy request into a structured Might
planning
hdtinh57
>