create-feature-spec
Skill8 starsChanged 8 months agoMITView on GitHub
Create Feature Specs for Stage E of the VibeFlow docs-first workflow
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analyze-codebaseSkill
- clarify-demandSkill
- define-prdSkill
- define-tech-specSkill
- manage-workSkill
- prepare-releaseSkill
- record-decisionSkill
- run-tddSkill
- validate-checkpointSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
Create Feature Specs for Stage E of the VibeFlow docs-first workflow.
- Very specific: line 24
Document design changes (UI/API/schema)
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
create-feature-spec
Create Feature Specs for Stage E of the VibeFlow docs-first workflow.
Purpose
This skill creates Feature Spec documents that:
- Define the API design contract (exact function/class signatures)
- Specify testable acceptance criteria
- Document design changes (UI/API/schema)
- Include test and evaluation plan
- Reference discovery findings and specs
Workflow
Stage E: Feature Spec
│
├── Define API Design (exact signatures)
├── Write testable acceptance criteria
├── Document design changes (UI/API/schema)
├── Create test and evaluation plan
├── Map telemetry and metrics
└── Reference discovery findings and specsUsage
Create Feature Spec
/create-feature-spec <ID> <slug>Creates docs/features/ft-<ID>-<slug>.md with required sections.
Example:
/create-feature-spec 030 anti-hallucinationValidate Feature Spec
/create-feature-spec validate <ID>Validates that the feature spec has all required sections.
Update Schedule
/create-feature-spec scheduleUpdates docs/features/schedule.md with feature status.
Document Requirements
Required Sections
For All Features:
- Header (ID, File, Owner, TECH-SPECs with versions)
- Architecture Conformance
- API Design (exact signatures)
- Acceptance Criteria
- Design Changes
- Test & Eval Plan
- Telemetry & Metrics
- Edge Cases & Risks
For Medium/Large Features (Additional):
- Stage B Discovery Findings
- Test Impact Analysis
- Existing Implementation Analysis
- Dependency & Side Effect Mapping
API Design Section (Critical)
The API Design section defines the contract for Stage F (test writing):
## API Design
### ServiceName.method_name()
- **Signature:** `method_name(param: Type, param2: Type = default) -> ReturnType`
- **Purpose:** [Brief description]
- **Parameters:**
- `param`: [Description]
- `param2`: [Description, default value]
- **Returns:** [Description of return type and structure]
### API Endpoint: POST /api/v1/endpoint
- **Method:** POST
- **Path:** `/api/v1/endpoint`
- **Request Body:**
```json
{
"field": "type"
}- Response Body:
{ "result": "type" }
Why This Matters:
- Stage F creates implementation stubs from these signatures
- Tests are written using these exact function names
- Any changes require updating specs first (Stage G.1)
Acceptance Criteria
Format as testable checklist or Gherkin:
## Acceptance Criteria
- [ ] User can [action] with [condition] resulting in [outcome]
- [ ] System returns [response] when [condition]
- [ ] Error [X] is shown when [condition]
Or Gherkin:
Given [context]
When [action]
Then [expected outcome]Validation
scripts/validate_feature.py— Validate feature spec structure and API Design
References
See assets/:
feature-template.md— Complete feature spec template
See references/:
api-design-guide.md— API Design section guidance
Context7 Library Research
Follow the workflow in .claude/rules/context7-research.md to fetch current library documentation.
What to look for: exact method signatures, error types, configuration options, parameter defaults.
Where to incorporate findings:
- API Design — use verified signatures and types from library docs, not assumed ones
- Acceptance Criteria — reference actual error types and edge cases from docs
- Edge Cases & Risks — document known limitations and version-specific behaviors
Manifest Update
After completing Stage E, update docs/workflow-state.yaml:
- Set
stage: E - Set
docs.feature: docs/features/ft-<ID>-<slug>.md
Checkpoint #2 (after Stage E):
- Set
checkpoint: 2after passing validation - Criteria: Feature spec exists with all required sections, API Design section has exact signatures, acceptance criteria are testable
Git Commit
After completing this stage, ask the user for permission before committing:
git add docs/features/ft-<ID>-<slug>.md docs/workflow-state.yaml
git commit -m "feat(feature): define <slug> feature spec (#ft-<ID>)"Replace <ID> and <slug> with actual values.
Auto-Advance
After the commit is complete, directly run /manage-work advance <ID> to advance to the next stage.
The advance command will automatically validate Checkpoint #2 at the E→F boundary.
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.

