.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/agent-skills/spec-driven-development
home/skills/addyosmani/agent-skills/spec-driven-development
addyosmani avatar

spec-driven-development

byaddyosmani· 31 skills

Installs

17k

Stars

80k

Forks

8.7k

Category

Product & Project Management

View on GitHub

TL;DR

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.

How to install spec-driven-development?

addyosmani/agent-skills/spec-driven-development
$npx -y skills add addyosmani/agent-skills --skill spec-driven-development

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Use this skill

Run `npx skills use "https://github.com/addyosmani/agent-skills" --skill "addyosmani/agent-skills/spec-driven-development"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the whole pack

Use the skills in "https://github.com/addyosmani/agent-skills" that are relevant to the current task. Run `npx skills add "https://github.com/addyosmani/agent-skills"` and select the relevant skills, then follow their instructions.

Files · 1

View on GitHub
SKILL.md
1# Spec-Driven Development
2 
3## Overview
4 
5Write a structured specification before writing any code. The spec is the shared source of truth between you and the human engineer — it defines what we're building, why, and how we'll know it's done. Code without a spec is guessing.
6 
7## When to Use
8 
9- Starting a new project or feature
10- Requirements are ambiguous or incomplete
11- The change touches multiple files or modules
12- You're about to make an architectural decision
13- The task would take more than 30 minutes to implement
14 
15**When NOT to use:** Single-line fixes, typo corrections, or changes where requirements are unambiguous and self-contained.
16 
17## The Gated Workflow
18 
19Spec-driven development has four phases. Do not advance to the next phase until the current one is validated.
20 
21```
22SPECIFY ──→ PLAN ──→ TASKS ──→ IMPLEMENT
23 │ │ │ │
24 ▼ ▼ ▼ ▼
25 Human Human Human Human
26 reviews reviews reviews reviews
27```
28 
29### Phase 1: Specify
30 
31Start with a high-level vision. Ask the human clarifying questions until requirements are concrete.
32 
33**Surface assumptions immediately.** Before writing any spec content, list what you're assuming:
34 
35```
36ASSUMPTIONS I'M MAKING:
371. This is a web application (not native mobile)
382. Authentication uses session-based cookies (not JWT)
393. The database is PostgreSQL (based on existing Prisma schema)
404. We're targeting modern browsers only (no IE11)
41→ Correct me now or I'll proceed with these.
42```
43 
44Don't silently fill in ambiguous requirements. The spec's entire purpose is to surface misunderstandings *before* code gets written — assumptions are the most dangerous form of misunderstanding.
45 
46**Write a spec document covering these six core areas:**
47 
481. **Objective** — What are we building and why? Who is the user? What does success look like?
49 
502. **Commands** — Full executable commands with flags, not just tool names.
51 ```
52 Build: npm run build
53 Test: npm test -- --coverage
54 Lint: npm run lint --fix
55 Dev: npm run dev
56 ```
57 
583. **Project Structure** — Where source code lives, where tests go, where docs belong.
59 ```
60 src/ → Application source code
61 src/components → React components
62 src/lib → Shared utilities
63 tests/ → Unit and integration tests
64 e2e/ → End-to-end tests
65 docs/ → Documentation
66 ```
67 
684. **Code Style** — One real code snippet showing your style beats three paragraphs describing it. Include naming conventions, formatting rules, and examples of good output.
69 
705. **Testing Strategy** — What framework, where tests live, coverage expectations, which test levels for which concerns.
71 
726. **Boundaries** — Three-tier system:
73 - **Always do:** Run tests before commits, follow naming conventions, validate inputs
74 - **Ask first:** Database schema changes, adding dependencies, changing CI config
75 - **Never do:** Commit secrets, edit vendor directories, remove failing tests without approval
76 
77**Spec template:**
78 
79```markdown
80# Spec: [Project/Feature Name]
81 
82## Objective
83[What we're building and why. User stories or acceptance criteria.]
84 
85## Tech Stack
86[Framework, language, key dependencies with versions]
87 
88## Commands
89[Build, test, lint, dev — full commands]
90 
91## Project Structure
92[Directory layout with descriptions]
93 
94## Code Style
95[Example snippet + key conventions]
96 
97## Testing Strategy
98[Framework, test locations, coverage requirements, test levels]
99 
100## Boundaries
101- Always: [...]
102- Ask first: [...]
103- Never: [...]
104 
105## Success Criteria
106[How we'll know this is done — specific, testable conditions]
107 
108## Open Questions
109[Anything unresolved that needs human input]
110```
111 
112**Reframe instructions as success criteria.** When receiving vague requirements, translate them into concrete conditions:
113 
114```
115REQUIREMENT: "Make the dashboard faster"
116 
117REFRAMED SUCCESS CRITERIA:
118- Dashboard LCP < 2.5s on 4G connection
119- Initial data load completes in < 500ms
120- No layout shift during load (CLS < 0.1)
121→ Are these the right targets?
122```
123 
124This lets you loop, retry, and problem-solve toward a clear goal rather than guessing what "faster" means.
125 
126### Phase 2: Plan
127 
128With the validated spec, generate a technical implementation plan:
129 
1301. Identify the major components and their dependencies
1312. Determine the implementation order (what must be built first)
1323. Note risks and mitigation strategies
1334. Identify what can be built in parallel vs. what must be sequential
1345. Define verification checkpoints between phases
135 
136> Follow `planning-and-task-breakdown` for the dependency-graph mapping and vertical-slicing mechanics behind these steps; it is the canonical source. The bullets above are a lightweight summary; if they ever diverge, `planning-and-task-breakdown` takes precedence.
137>
138> **Output convention:** Save the plan to `tasks/plan.md` and the task list to `tasks/todo.md`, per the `/plan` command convention. Create `tasks/` if it does not exist. Downstream commands (`/build`, etc.) expect these paths.
139 
140The plan should be reviewable: the human should be able to read it and say "yes, that's the right approach" or "no, change X."
141 
142### Phase 3: Tasks
143 
144Break the plan into discrete, implementable tasks:
145 
146- Each task should be completable in a single focused session
147- Each task has explicit acceptance criteria
148- Each task includes a verification step (test, build, manual check)
149- Tasks are ordered by dependency, not by perceived importance
150- No task should require changing more than ~5 files
151 
152> Follow `planning-and-task-breakdown` for the full task-sizing and dependency-ordering mechanics; it is the canonical source. The template below is a lightweight inline form; if they ever diverge, `planning-and-task-breakdown` takes precedence.
153 
154**Task template:**
155```markdown
156- [ ] Task: [Description]
157 - Acceptance: [What must be true when done]
158 - Verify: [How to confirm — test command, build, manual check]
159 - Files: [Which files will be touched]
160```
161 
162### Phase 4: Implement
163 
164Execute tasks one at a time following `skills/incremental-implementation/SKILL.md` (`incremental-implementation`) and `skills/test-driven-development/SKILL.md` (`test-driven-development`). Use `skills/context-engineering/SKILL.md` (`context-engineering`) to load the right spec sections and source files at each step rather than flooding the agent with the entire spec.
165 
166## Keeping the Spec Alive
167 
168The spec is a living document, not a one-time artifact:
169 
170- **Update when decisions change** — If you discover the data model needs to change, update the spec first, then implement.
171- **Update when scope changes** — Features added or cut should be reflected in the spec.
172- **Commit the spec** — The spec belongs in version control alongside the code.
173- **Reference the spec in PRs** — Link back to the spec section that each PR implements.
174 
175## Common Rationalizations
176 
177| Rationalization | Reality |
178|---|---|
179| "This is simple, I don't need a spec" | Simple tasks don't need *long* specs, but they still need acceptance criteria. A two-line spec is fine. |
180| "I'll write the spec after I code it" | That's documentation, not specification. The spec's value is in forcing clarity *before* code. |
181| "The spec will slow us down" | A 15-minute spec prevents hours of rework. Waterfall in 15 minutes beats debugging in 15 hours. |
182| "Requirements will change anyway" | That's why the spec is a living document. An outdated spec is still better than no spec. |
183| "The user knows what they want" | Even clear requests have implicit assumptions. The spec surfaces those assumptions. |
184 
185## Red Flags
186 
187- Starting to write code without any written requirements
188- Asking "should I just start building?" before clarifying what "done" means
189- Implementing features not mentioned in any spec or task list
190- Making architectural decisions without documenting them
191- Skipping the spec because "it's obvious what to build"
192 
193## Verification
194 
195Before proceeding to implementation, confirm:
196 
197- [ ] The spec covers all six core areas
198- [ ] The human has reviewed and approved the spec
199- [ ] Success criteria are specific and testable
200- [ ] Boundaries (Always/Ask First/Never) are defined
201- [ ] The spec is saved to a file in the repository

Security

Review

  • Gen Agent Trust Hubpass
  • Socketpass
  • Snykpass
  • Runlayerwarn
  • ZeroLeakspass

Preview

addyosmani/agent-skillsaddyosmani/agent-skills

$ npx -y skills add addyosmani/agent-skills --skill spec-driven-development

▸ installing to .claude/skills…

✓ spec-driven-development ready

Repoaddyosmani/agent-skills
TypeSkills
CategoryProduct & Project Management
ForArchitectProduct Manager
UpdatedJul 2026
License—
First seenJul 26, 2026

Tags

Skill

Related

6 picks
Type
  1. mattpocock avatargrill-meA relentless interview to sharpen a plan or design.SkillsJul 2026690k189k
  2. mattpocock avatartriageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026463k189k
  3. larksuite avatarlark-task飞书任务:管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更…SkillsJul 2026388k16k
  4. larksuite avatarlark-okr飞书 OKR:管理目标与关键结果。查看和编辑 OKR 周期、目标、关键结果、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。不负责:待办任务管理(lark-task)、日程/会议安排(lark-calendar)、绩效评估SkillsJul 2026324k16k
  5. obra avatarbrainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.SkillsJul 2026301k261k
  6. mattpocock avatargrillingGrill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.SkillsJul 2026295k189k