spec-propose
Skill9 starsChanged 4 months agoMITView on GitHub
Propose a new feature or change. Creates a structured spec folder with proposal, requirements, design, and tasks before any code is written. Use when starting new work.
In this repository8 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- auth-implementationSkill
- incident-responseSkill
- kiro-railsSkill
- review-guideSkill
- spec-archiveSkill
- spec-implementSkill
- spec-verifySkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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
- Distinctive: line 8
When the user wants to propose a new feature or change, create a structured spec folder BEFORE writing any code.
- Very specific: line 96
Use the TDD template from .kiro/templates/tasks-template-tdd.md if available.
- Distinctive: line 119
Requirements must be testable: - every requirement needs acceptance criteria
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Spec Propose Workflow
When the user wants to propose a new feature or change, create a structured spec folder BEFORE writing any code.
Steps
- Ask clarifying questions - understand scope, constraints, affected areas
- Create the spec folder at
.kiro/specs/<feature-name>/ - Generate all artifacts in order:
Folder Structure
.kiro/specs/<feature-name>/
├── proposal.md # Why this change exists
├── requirements.md # What the system should do
├── design.md # How to implement it
└── tasks.md # Checkbox-tracked implementation stepsproposal.md Template
# Proposal: <Feature Name>
## Problem Statement
What problem does this solve? Who is affected?
## Proposed Solution
High-level description of the approach.
## Scope
- **In scope:** what this change includes
- **Out of scope:** what this change explicitly excludes
## Success Criteria
How do we know this is done and working?
## Risks & Open Questions
- Risk 1: ...
- Question 1: ...requirements.md Template
# Requirements: <Feature Name>
## Functional Requirements
### REQ-1: <Requirement Name>
**Description:** What the system must do.
**Acceptance Criteria:**
- [ ] Criterion 1
- [ ] Criterion 2
### REQ-2: <Requirement Name>
...
## Non-Functional Requirements
- Performance: ...
- Security: ...
- Accessibility: ...design.md Template
# Design: <Feature Name>
## Architecture
How this fits into the existing system.
## Key Decisions
| Decision | Rationale | Alternatives Considered |
|----------|-----------|------------------------|
| ... | ... | ... |
## Data Model Changes
Describe any schema/model changes.
## API Changes
Describe any endpoint additions/modifications.
## Dependencies
What this depends on, what depends on this.tasks.md Template
Use the TDD template from .kiro/templates/tasks-template-tdd.md if available. Otherwise:
# Tasks: <Feature Name>
## Implementation Checklist
- [ ] Task 1: ...
- [ ] Task 2: ...
- [ ] Task 3: ...
## Testing
- [ ] Unit tests for ...
- [ ] Integration tests for ...
## Documentation
- [ ] Update relevant docs
- [ ] Add ADR if architectural decision was madeRules
- Never skip the proposal - even for "small" changes, write at minimum a 3-sentence proposal
- Requirements must be testable - every requirement needs acceptance criteria
- Design must reference requirements - trace each design decision to a requirement
- Tasks must be atomic - each task should be completable in one session
- Get user confirmation on the proposal before proceeding to requirements
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.

