spec-driven-development
Create clear specifications and acceptance criteria before writing code. Use for any new feature, significant change, or when requirements are ambiguous. Trigger when the user says "spec", "requirements", "what should we build", or before starting non-trivial implementation.
- License 许可
- MIT
- 最近更新
- 2026-07-22
- Stars
- ★ 7
- Forks
- 1
01 前言 Front Matter
- name
- spec-driven-development
- description
- Create clear specifications and acceptance criteria before writing code. Use for any new feature, significant change, or when requirements are ambiguous. Trigger when the user says "spec", "requirements", "what should we build", or before starting non-trivial implementation.
03 SKILL.md 正文
Spec-Driven Development
Overview
Write a lightweight but precise specification before implementation. This prevents the most common agent failure mode: building the wrong thing confidently.
When to Use
- New features or user stories
- Significant refactors or architectural changes
- Ambiguous requests
- Before any non-trivial coding work
Core Process
1. Capture Intent
What problem are we solving? For whom? Why now?
2. Define Success
What does "done" look like from the user’s perspective?
3. Write the Spec
Keep it short. Focus on:
- Problem statement
- Goals (and non-goals)
- User-facing behavior
- Acceptance criteria (testable)
- Edge cases & error handling
- Constraints (performance, compatibility, security, etc.)
- Open questions
4. Review & Agree
Surface the spec to the user for confirmation before coding.
Recommended Spec Template
# Spec: [Feature Name]
## Problem
...
## Goals
- ...
## Non-Goals
- ...
## User Stories / Behavior
- As a ... I want ... so that ...
## Acceptance Criteria
- [ ] ...
- [ ] ...
## Edge Cases
- ...
## Technical Notes / Constraints
- ...
## Open Questions
- ...
Principles
- Prefer concrete, testable statements over vague ones
- Explicitly call out non-goals to prevent scope creep
- Keep the spec living — update it if requirements change
- A good spec makes implementation and review much easier
Verification
Before writing code, confirm:
- The user has seen and agreed with the spec (or key parts)
- Acceptance criteria are specific enough to test against
- Major assumptions are documented
04 同仓库更多 Skills
compliance-monitoring
Design compliance monitoring and testing programs that verify controls work in practice and surface issues before regulators do. Use when building monitoring plans, compliance testing, or continuous control monitoring.
complaints-handling
Operate complaints-handling processes that meet regulatory standards — logging, timely resolution, root-cause analysis, and fair outcomes. Use when designing or improving regulated complaints frameworks or analyzing complaint themes for conduct risk.
aml-kyc-basics
Apply AML/KYC fundamentals — customer due diligence, monitoring, suspicious activity escalation, and recordkeeping — for financial crime compliance. Use when designing onboarding controls, transaction monitoring concepts, or AML program components in financial services.
ai-model-compliance
Apply compliance controls to AI and automated decision systems — transparency, fairness, human oversight, documentation, and regulatory alignment. Use when deploying AI in regulated processes (credit, fraud, customer decisions) or responding to AI governance expectations.
data-quality-management
Manage data quality end-to-end — dimensions, rules, remediation, and prevention — beyond one-off cleaning scripts. Use when building sustained data quality programs or fixing systemic accuracy, completeness, or consistency problems.
data-lineage
Capture and use data lineage — where data comes from, how it transforms, and what depends on it — for impact analysis, debugging, and trust. Use when tracing metric origins, assessing change impact, or diagnosing broken pipelines.