Trigger Condition: User requests to continue discussion or modify planning
Execution Actions:
Retrieve and analyze previously generated planning files
Identify user feedback and confirmation content
Enable Planner Agent
Generate detailed markdown planning document
Create a new document, for example, if the last one was plan/xxx.md, then this time it's plan/xxx-1.md, if the last one was plan/xxx-1.md, then this time it's plan/xxx-2.md, and so on
Reorganize pending implementation task priorities
C. Execution Implementation Processing
Trigger Condition: User confirms planning is complete and requests to start execution
Execution Actions:
Start task execution in the order of planning documents
Perform task type identification before each subtask begins
Frontend Task Special Processing:
Check if available UI design exists
If no design solution exists, must use UI-UX-Designer Agent
Complete UI design before proceeding with development implementation
3. Key Execution Principles
Mandatory Response Requirements
Must first state in every interaction: "I determine this operation type as: [specific type]"
Type determination must be accurate and clearly communicated to users
Task Execution Standards
Strictly execute according to documented planning
Must clarify task nature and dependencies before subtask startup
Frontend tasks must ensure UI design completeness
State Management Mechanism
Maintain task completion status tracking
Timely update planning document status
Ensure user visibility of progress
Quality Assurance Points
Type Determination Accuracy: Type identification at the beginning of each interaction must be accurate
Document Consistency: Planning documents and actual execution remain synchronized
Dependency Management: Pay special attention to UI design dependencies of frontend tasks
Transparent User Communication: All judgments and actions must be clearly communicated to users
1---
2name: feat
3description: Add New Feature
4disable-model-invocation: true
5---
67$ARGUMENTS
89## Core Workflow
1011### 1. Input Analysis and Type Determination
1213When receiving user input, first perform type determination and clearly inform the user:
1415**Determination Criteria:**
1617- **Requirement Planning Type**: User proposes new feature requirements, project ideas, or needs to formulate plans
1819- **Discussion Iteration Type**: User requests to continue discussion, modify, or refine existing planning
2021- **Execution Implementation Type**: User confirms planning is complete and requests to start specific implementation work
2223### 2. Classification Processing Mechanism
2425#### A. Requirement Planning Processing
2627**Trigger Condition**: Identified as functional requirement input
2829**Execution Actions**:
3031- Enable Planner Agent
3233- Generate detailed markdown planning document
3435- Store document in `./.claude/plan` directory, named in plan/xxx.md format
3637- Include: objective definition, feature breakdown, implementation steps, acceptance criteria
3839#### B. Discussion Iteration Processing
4041**Trigger Condition**: User requests to continue discussion or modify planning
4243**Execution Actions**:
4445- Retrieve and analyze previously generated planning files
4647- Identify user feedback and confirmation content
4849- Enable Planner Agent
5051- Generate detailed markdown planning document
5253- Create a new document, for example, if the last one was plan/xxx.md, then this time it's plan/xxx-1.md, if the last one was plan/xxx-1.md, then this time it's plan/xxx-2.md, and so on
5455- Reorganize pending implementation task priorities
5657#### C. Execution Implementation Processing
5859**Trigger Condition**: User confirms planning is complete and requests to start execution
6061**Execution Actions**:
6263- Start task execution in the order of planning documents
6465- Perform task type identification before each subtask begins
6667- **Frontend Task Special Processing**:
6869- Check if available UI design exists
7071- If no design solution exists, must use UI-UX-Designer Agent
7273- Complete UI design before proceeding with development implementation
7475### 3. Key Execution Principles
7677#### Mandatory Response Requirements
7879- **Must first state in every interaction**: "I determine this operation type as: [specific type]"
8081- Type determination must be accurate and clearly communicated to users
8283#### Task Execution Standards
8485- Strictly execute according to documented planning
8687- Must clarify task nature and dependencies before subtask startup
8889- Frontend tasks must ensure UI design completeness
9091#### State Management Mechanism
9293- Maintain task completion status tracking
9495- Timely update planning document status
9697- Ensure user visibility of progress
9899## Quality Assurance Points
1001011. **Type Determination Accuracy**: Type identification at the beginning of each interaction must be accurate
1021032. **Document Consistency**: Planning documents and actual execution remain synchronized
1041053. **Dependency Management**: Pay special attention to UI design dependencies of frontend tasks
1061074. **Transparent User Communication**: All judgments and actions must be clearly communicated to users
Run npx skillmds@latest add ufomiao/feat in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Add New Feature It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
UfoMiao (@ufomiao) published this skill. Their other Agent Skills are listed on their SkillMD profile.