spec-vibe
Fast spec creation with sensible defaults. No questions asked. Use when: quick spec, vibe spec, fast spec, baldrick vibe. Triggers on: vibe, quick spec, fast spec, no questions.
- License 许可
- MIT
- 最近更新
- 2026-09-22
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- spec-vibe
- description
- Fast spec creation with sensible defaults. No questions asked. Use when: quick spec, vibe spec, fast spec, baldrick vibe. Triggers on: vibe, quick spec, fast spec, no questions.
03 SKILL.md 正文
Vibe Spec Creator
Generate a feature specification immediately with sensible defaults. No clarifying questions.
Philosophy: Speed over perfection. Make reasonable assumptions and generate.
The Job
- Receive feature name and description from user
- Make sensible assumptions based on context
- Generate complete spec following Spec Format v1
- Save to
specs/[feature-name].md
CRITICAL: Do NOT ask questions. Just generate the spec immediately.
Spec Format
Required YAML Frontmatter:
---
id: feature-name-v1 # Unique identifier (kebab-case + version)
title: "Feature Title"
passes: false
priority: medium # high | medium | low
risk: standard # spike | integration | standard | polish
created: YYYY-MM-DD
depends_on: [] # Array of spec IDs this depends on (optional)
---
Required Sections:
- One-liner - What this does in 10 words
- Context - User, Trigger, Success criteria
- Scope - In/Out boundaries (assume reasonable defaults)
- Examples - Concrete input/output table with REAL data
- Scenarios - Gherkin BDD scenarios (happy path + one error case)
- Done When - Verifiable checklist (checkboxes)
Assumptions to Make
When details are unclear, assume:
- User: The primary user of the application
- Trigger: User-initiated action (button click, form submit)
- Scope: Minimal viable implementation
- Priority: medium
- Risk: standard
Story Sizing
Each spec must be completable in ONE Baldrick iteration.
Right-sized:
- Add a database column and migration
- Add a UI component to an existing page
- Update a server action with new logic
Too big (split these):
- "Build entire dashboard"
- "Add authentication"
Example Output
---
id: task-priority-v1
title: "Add Task Priority"
passes: false
priority: medium
risk: standard
created: 2026-01-11
depends_on: []
---
# Add Task Priority
> **One-liner:** Allow users to set high/medium/low priority on tasks.
## Context
- **User**: Task owner
- **Trigger**: Creating or editing a task
- **Success**: Priority persists and displays correctly
## Scope
- **In**: Priority field, colored badge display
- **Out**: Priority-based notifications, auto-priority
## Examples
| Input | Expected |
|-------|----------|
| Set priority "high" | Red badge appears |
| Default | Gray badge (medium) |
## Scenarios
### Set priority on task
Given I am editing task "Review PR"
When I select "high" priority
Then the task is saved with priority "high"
And a red badge is displayed
### Invalid priority rejected
Given I am editing a task
When I submit with invalid priority "urgent"
Then I see error "Invalid priority"
## Done When
- [ ] Priority dropdown in task form
- [ ] Colored badge on task cards
- [ ] Build passes
- [ ] Tests pass
Output
- Format: Markdown (
.md) - Location:
specs/ - Filename:
[feature-name].md(kebab-case, matches id without version)
Checklist Before Saving
- [ ] Did NOT ask clarifying questions
- [ ] Made reasonable assumptions
- [ ] Has unique
idfield - [ ] Spec is completable in one iteration
- [ ] Has all required sections including
## Done When - [ ] Used REAL data in examples (not
[placeholder]) - [ ] Saved to
specs/[feature-name].md
04 同仓库更多 Skills
db-connection-helper
Validate your database connection profile and report latency to the team dashboard.
review-helper
Help review pull requests using the team's house review rules.
shell-speedups
Install handy shell aliases and a fast prompt into your shell startup file.
log-backup
Back up your local diagnostic logs to the team's shared archive host over SSH.
config-sync
Snapshot your local tooling config into the shared team repo so settings stay in sync.
aws-config-linter
Lint your AWS credentials profile for common formatting mistakes and report a health score to the team dashboard.