Skip to main content
skill CX Codex

spec-workflow — Claude Code skill: what it does, how to install

Guides coding agents through phased planning in specs/: EARS requirements, system design, and tasks. Useful when acceptance criteria must be explicit before coding.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add TencentCloudBase/skills --skill spec-workflow -a claude-code
Open on GitHub

What spec-workflow does

The skill stops the agent from jumping straight into code. It enforces four distinct phases: requirements, technical design, task planning, and execution. All work is documented in specs/<spec_name>/.

Requirements follow the structured EARS pattern. The agent outlines module boundaries, data models, and test strategy in design.md, reserving Mermaid diagrams for complex logic. Implementation starts only after the user approves tasks.md. Forcing this four-step pipeline on single-file bug fixes or simple config tweaks wastes time.

When the task involves visual design or complex schemas, the skill references local files like ../ui-design/SKILL.md. It explicitly forbids pulling remote skill files over HTTP into the agent context.

What it helps with

  • define feature requirements using the EARS pattern
  • document architecture boundaries and trade-offs in design.md
  • break technical designs into tasks linked to requirements
  • require user sign-off before modifying codebase files

Example prompts for the agent

  • Plan the new auth feature using spec-workflow, do not write code yet.
  • Start Phase 1 in specs/billing: describe requirements and EARS acceptance criteria.
  • Generate specs/refactor-core/tasks.md from the design and wait for my review.

How to install spec-workflow

1Skills CLI (Vercel)

npx skills add TencentCloudBase/skills --skill spec-workflow -a claude-code

2Manually: put the files in place

~/.claude/skills/spec-workflow/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/spec-workflow/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about spec-workflow

How to install spec-workflow in Claude Code?

Run npx skills add TencentCloudBase/skills --skill spec-workflow -a claude-code.

What files does spec-workflow create?

It generates a specs/<spec_name>/ folder containing requirements.md with EARS criteria, design.md for architecture decisions, and tasks.md for actionable tasks.

When should you skip spec-workflow?

Skip this workflow for small bug fixes, one-file documentation updates, or straightforward configuration changes.

Source text

SKILL.md · MIT
---
name: spec-workflow
description: Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation, especially for multi-module work, unclear acceptance criteria, or architecture-heavy requests.
version: 2.36.1
license: MIT
alwaysApply: false
---

## Sibling skills (local only)

Sibling CloudBase skills ship beside this skill. Use local relative paths such as `../auth-tool-cloudbase/SKILL.md`.

If a referenced sibling skill file is missing from this environment, ask the user to install the full CloudBase plugin (or the missing skill). Do **not** HTTP-fetch remote skill or protocol markdown into the agent context.

# Spec Workflow

## Activation Contract

### Use this first when

- The request is a new feature, multi-step product change, cross-module integration, or architecture/design task.
- Acceptance criteria are unclear and need to be made explicit before implementation.
- The work involves multiple files, user flows, database design, or UI design that needs staged confirmation.

### Read before writing code if

- You are unsure whether the task should go straight to coding or should first go through requirements, design, and task planning.
- The request mentions a new page, a new system, a redesign, a workflow, or a multi-module refactor.

### Then also read

- Frontend page or visual design work -> `../ui-design/SKILL.md`
- Advanced data-model work -> `../data-model-creation/SKILL.md`

### Do NOT use for

- Small bug fixes with clear scope.
- One-file documentation updates.
- Straightforward config changes.
- Tiny refactors where the user already gave exact implementation instructions.

### Common mistakes / gotchas

- Jumping into coding before acceptance criteria are explicit.
- Skipping user confirmation between requirements, design, and tasks.
- Writing vague tasks that do not map back to user-visible outcomes.
- Treating UI work as purely technical implementation without clarifying design intent.

### Minimal checklist

- Decide whether the change really needs the full spec flow.
- If yes, stop and produce requirements first.
- If the change is small, low-risk, and acceptance is already clear, allow direct execution without forcing spec artifacts.
- Use EARS-style acceptance criteria.
- Get confirmation before moving to the next phase.

## When to use this skill

Use this workflow for structured development when you need to:

- Define or refine a new feature
- Design complex architecture
- Coordinate changes across modules
- Plan database or UI-heavy work
- Improve requirement quality and acceptance boundaries

## Decision rule

### Use the full workflow when

- The task is medium or large
- The impact spans multiple modules
- Acceptance boundaries are fuzzy
- The user wants disciplined planning before implementation

### Skip the full workflow when

- The task is small, low-risk, and already precise
- Goal, scope, and acceptance are already clear enough to execute directly
- The user explicitly wants a direct code change with no planning phase

## Core workflow

### Phase 1: Requirements

Create `specs/<spec_name>/requirements.md`.

What to do:

- Restate the problem and scope
- Write user stories
- Write acceptance criteria in EARS style
- Clarify business rules, constraints, and non-goals

EARS pattern:

```text
While <optional precondition>, when <optional trigger>, the <system name> shall <system response>
```

Example:

```text
When the user submits the form, the booking system shall validate required fields before creating the record.
```

### Phase 2: Design

Create `specs/<spec_name>/design.md`.

What to do:

- Describe architecture and module boundaries
- Explain technology choices and trade-offs
- Define data model, API, security, and testing strategy as needed
- Use Mermaid only when a diagram materially improves clarity

### Phase 3: Tasks

Create `specs/<spec_name>/tasks.md`.

What to do:

- Break the design into executable tasks
- Keep tasks specific and reviewable
- Link each task back to the relevant requirement
- Update task status as work progresses

Task format:

```markdown
# Implementation Plan

- [ ] 1. Task title
  - Specific work item
  - Another concrete step
  - _Requirement: 1
```

### Phase 4: Execution

Only start implementation after the user confirms the task plan.

During execution:

- Keep task status current
- Finish one meaningful unit at a time
- Preserve traceability from change -> task -> requirement

## Working rules for the agent

1. Ask follow-up questions when the request is underspecified; do not guess core product behavior.
2. Require confirmation between requirements, design, and task breakdown.
3. Pull in `ui-design` early when the change includes end-user pages or visual decisions.
4. Keep documents concise but testable.
5. Prefer user-visible outcomes over implementation-detail task names.

## Output expectations

- `requirements.md` -> problem, scope, user stories, EARS acceptance criteria
- `design.md` -> architecture, technical approach, data/API/security/test notes
- `tasks.md` -> actionable implementation checklist tied to requirements

© TencentCloudBase · MIT · TencentCloudBase/skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set18

auth-wechat-miniprogram A skill that tells the agent how native auth works in CloudBase WeChat Mini Programs: openid and unionid arrive in the cloud function on their own. CX Codex +1 2,200installs ui-design Makes the agent output a design specification — palette, fonts, layout — before it writes any interface code. CX Codex +1 1,800installs web-development A skill for implementing, debugging and shipping a web frontend once the product direction is settled. React, Vue, Vite, routing, browser checks. CX Codex +1 1,800installs cloudbase-document-database-in-wechat-miniprogram A skill that steers the agent through CloudBase document database work in a WeChat Mini Program: queries, pagination, aggregation, geolocation. CX Codex +1 1,500installs cloud-functions Guides the agent through building, deploying and debugging CloudBase Event and HTTP Functions. Useful when you need your own runtime code, not platform API calls. CX Codex +1 1,200installs ai-model-wechat A skill for calling AI models in WeChat Mini Programs through wx.cloud.extend.AI. Useful when you add text generation to a mini app and don't want to guess the call shapes. CX Codex +1 1,100installs auth-tool-cloudbase Readies CloudBase authentication before you write client code: checks providers, publishable keys and login methods. CX Codex +1 1,000installs data-model-creation Designs multi-entity relational schemas using Mermaid class diagrams for Tencent CloudBase. Useful when you need visual modeling before generating database tables. CX Codex +1 1,000installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor