feature-planning
Skill2 starsChanged 4 months agoMITView on GitHub
Plan features by breaking them down into tickets with subtasks. Use when: planning complex features, creating task breakdowns, defining feature scope, or generating ticket structures with acceptance criteria.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- SWEStash/swe-workflow-skillstheir own version, first seen Nov 8, 2026
- OpenxIntelligence/Coding-Agent-Skillstheir own version, first seen Nov 1, 2026
- I-Onlabs/claude-code-skillstheir own version, first seen Oct 25, 2026
- HybridAIOne/hybridclawtheir own version, first seen Oct 13, 2026
- SoftBlack42/StarPietheir own version, first seen Oct 9, 2026
- OneDro1d/onedroid-docstheir own version, first seen Sep 18, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- SoftBlack42/StarPie★ 1.3ksame name
- HybridAIOne/hybridclaw★ 162same name
- I-Onlabs/claude-code-skills★ 4same name
- OpenxIntelligence/Coding-Agent-Skills★ 4same name
- rm2thaddeus/Aitor_Skills★ 4same name
- thejordanleopold/claude-code-skills-distilled★ 4same name
- apinstein/skills★ 2same name
- SWEStash/swe-workflow-skills★ 1same name
- OneDro1d/onedroid-docs★ 0same name
- spelbreker/agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- design-taste-frontendSkill
- frontend-designSkill
- task-execution-orchestrationSkill
- web-design-guidelinesSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 59
Create a structured JSON manifest that can be consumed by the task-execution-orchestration skill:
- Distinctive: line 94
No conversational text or explanations outside the JSON
- Distinctive: line 101
Sub-tickets: When a task has distinct, separable work that requires independent validation or involves multiple components
- Distinctive: line 102
Single ticket: When the work is cohesive and can be completed as a unit
“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Feature Planning Skill
Overview
This skill guides the planning of complex features by breaking them down into manageable tickets with subtasks, defining scope, dependencies, and acceptance criteria.
CRITICAL OUTPUT FORMAT: The skill MUST return a JSON manifest that can be directly consumed by the task-execution-orchestration skill. The response should be succinct - only providing the points that need to be done for validation, without unnecessary explanations or conversational text.
Step-by-Step Process
1. Feature Analysis & Scope Definition
Input: Feature description or user request
Actions:
- Understand the feature requirements and constraints
- Identify the main components or modules involved
- Determine the technology stack and dependencies
- Define success criteria and acceptance conditions
Output: Feature summary with clear boundaries
2. Task Breakdown into Tickets
For each major component, create a ticket structure with:
Ticket: [TICKET-ID] - [Brief Description]
Type: [Feature | Bugfix | Refactor | Chore | Infrastructure]
Priority: [High | Medium | Low]
Description:
[Detailed description of what needs to be done]
Subtasks:
- [ ] Subtask 1: [Description]
- [ ] Subtask 2: [Description]
- [ ] Subtask 3: [Description]
Dependencies:
- [List of tickets or subtasks that must be completed first]
Acceptance Criteria:
- [ ] Criterion 1
- [ ] Criterion 2
Validation Required: [Yes/No]
Validation Criteria: [What the validation should check]3. Generate Planning Manifest (JSON OUTPUT)
Create a structured JSON manifest that can be consumed by the task-execution-orchestration skill:
{
"feature": "<Feature Name>",
"description": "<Feature Description>",
"tickets": [
{
"id": "TICKET-001",
"title": "<Ticket Title>",
"type": "<Type>",
"priority": "<Priority>",
"description": "<Description>",
"subtasks": [
{
"id": "SUB-001-1",
"title": "<Subtask Title>",
"status": "not-started",
"acceptanceCriteria": ["<criterion 1>", "<criterion 2>"]
}
],
"dependencies": ["<ticket-id or subtask-id>"],
"status": "not-started",
"validationRequired": true,
"validationCriteria": ["<validation criterion 1>", "<validation criterion 2>"]
}
]
}Output Format Requirements
CRITICAL: The response MUST be:
- Succinct - only provide the points that need to be done for validation
- JSON format - the planning manifest JSON should be the primary output
- No conversational text or explanations outside the JSON
- Include all acceptance criteria and validation requirements in the JSON structure
Decision Points & Branching Logic
When to Create Sub-Tickets vs Single Tickets
- Sub-tickets: When a task has distinct, separable work that requires independent validation or involves multiple components
- Single ticket: When the work is cohesive and can be completed as a unit
When to Require Validation
- Required: For code quality, security, accessibility, and integration points
- Optional: For simple refactors or documentation updates
Quality Criteria & Completion Checks
For Planning Phase
- All feature requirements are captured and understood
- Tickets cover all necessary components
- Dependencies between tickets are correctly identified
- Subtasks are atomic and clearly defined
- Acceptance criteria are specific and testable
- JSON manifest is properly formatted and consumable by task-execution-orchestration
Example Prompts to Try This Skill
- "Plan the implementation of a new face swap feature with GIF upload and preview"
- "Create a task breakdown for adding queue/batch processing support"
- "Break down the MCP server integration into tickets with subtasks and validation requirements"
Related Skills
- task-execution-orchestration: For executing the planned tickets using sub-agents and validating the work
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

