Skip to content
Skill Authoring
Skill

/feature-spec

Use this skill when the user says 'feature spec', 'spec this feature', 'write a spec', 'functional requirements', or needs a detailed specification for one feature with user flows, edge cases, API definitions, and acceptance criteria. Do NOT use for full PRDs or user story

BOOST
From plugin
memstack
42587 skills2 commands4 hooks
Install
$ npx -y skills add cwinvestments/memstack --skill feature-spec --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/feature-spec

Context preview

The summary Claude sees to decide when to auto-load this skill.

Use this skill when the user says 'feature spec', 'spec this feature', 'write a spec', 'functional requirements', or needs a detailed specification for one feature with user flows, edge cases, API definitions, and acceptance criteria. Do NOT use for full PRDs or user story

SKILL.md

feature-spec.SKILL.md
name: memstack-product-feature-spec
description: "Use this skill when the user says 'feature spec', 'spec this feature', 'write a spec', 'functional requirements', or needs a detailed specification for one feature with user flows, edge cases, API definitions, and acceptance criteria. Do NOT use for full PRDs or user story generation."
version: 1.0.0
license: "Proprietary, MemStack™ Pro by CW Affiliate Investments LLC. See LICENSE.txt"

Feature Spec: Writing feature specification...

*Creates a detailed specification for a single feature including user story, acceptance criteria, user flows, edge cases, API definitions, dependencies, and effort estimate.*

Activation

When this skill activates, output:

`Feature Spec: Writing feature specification...`

Then execute the protocol below.

Context Guard

| Context | Status | |---------|--------| | User says "feature spec", "spec this feature", "write a spec" | ACTIVE | | User says "functional requirements" for a specific feature | ACTIVE | | User needs a detailed breakdown of ONE feature for engineering | ACTIVE | | User wants a full product requirements document | DORMANT: use PRD Writer | | User wants multiple user stories for sprint planning | DORMANT: use User Story Generator |

Common Mistakes

| Mistake | Why It's Wrong | |---------|---------------| | "Spec the happy path only" | Edge cases cause 80% of bugs. Spec them upfront or pay for them in QA. | | "Skip the API contract" | Frontend and backend need to agree on the contract before building in parallel. | | "No acceptance criteria" | Without testable criteria, "done" is subjective. Define done before starting. | | "Spec the UI, not the behavior" | UIs change. Behavior specs survive redesigns. Focus on what happens, not what it looks like. | | "Forget to list what's out of scope" | Ambiguity invites scope creep. Explicitly list what this feature does NOT include. |

Protocol

Step 1: Gather Feature Context

If the user hasn't provided details, ask:

> 1. **Feature name**: what are you building? > 2. **User problem**: what problem does this feature solve? > 3. **Target user**: which persona uses this feature? > 4. **Context**: is this part of a larger project? What already exists? > 5. **Constraints**: timeline, tech stack, or design constraints?

Step 2: Write Feature Brief

## Feature Brief

**Feature:** [Feature name]
**Owner:** [Product owner / author]
**Date:** [Date]
**Status:** [Draft / In Review / Approved]

### Summary
[2-3 sentences: what this feature does and why it matters]

### User Story
As a [persona], I want to [action] so that [outcome].

### Business Value
- [Why this matters for the business: revenue, retention, efficiency]
- [Metric this feature is expected to move]

### Scope
**In scope:**
- [Specific capability 1]
- [Specific capability 2]
- [Specific capability 3]

**Out of scope:**
- [Explicitly excluded capability 1]
- [Explicitly excluded capability 2]

Step 3: Define User Flows

**Primary flow (happy path):**

### Primary Flow: [Action Name]

**Entry point:** [Where/how the user accesses this feature]
**Preconditions:** [What must be true: logged in, has permission, etc.]

1. User [action: clicks, enters, selects]
   → System [response: shows, loads, validates]
2. User [action]
   → System [response]
3. User [action: confirms, submits]
   → System [response: saves, sends, updates]
4. User sees [confirmation: success message, updated state, redirect]

**Exit state:** [What the system looks like after completion]

**Alternative flows:**

### Alternative Flow: [Variation Name]

**Trigger:** [When this flow happens instead of the primary]

1. [Step that diverges from primary flow]
2. [How the system handles the variation]
3. [Where it rejoins the primary flow, or how it terminates]

Step 4: Document Edge Cases & Error States

| # | Scenario | Expected Behavior | Priority | |---|----------|-------------------|----------| | E1 | User submits empty form | Show inline validation errors on required fields | Must handle | | E2 | Network request fails | Show error toast, preserve form state, offer retry | Must handle | | E3 | User double-clicks submit | Disable button after first click, prevent duplicate submission | Must handle | | E4 | Session expires during flow | Save draft state, redirect to login, restore after auth | Should handle | | E5 | Concurrent edit by another user | Show conflict notification, offer merge or overwrite | Should handle | | E6 | Input exceeds character limit | Enforce limit in UI, validate server-side, show remaining count | Must handle | | E7 | User navigates away with unsaved changes | Show "Unsaved changes" confirmation dialog | Should handle |

**Edge case discovery checklist:**

  • What happens with empty/null input?
  • What happens with maximum-length input?
  • What happens with special characters or Unicode?
  • What happens if the user has no permission?
  • What happens offline or with slow network?
  • What happens with concurrent actions?
  • What happens if a dependency (API, service) is down?

Step 5: Define API Contract (if applicable)

### API Endpoints

#### POST /api/[resource]
**Purpose:** [What this endpoint does]
**Auth:** Required, [Bearer token / API key / session]
**Rate limit:** [X requests per minute]

**Request:**
```json
{
  "field1": "string (required): [description]",
  "field2": "number (optional): [description, default: X]",
  "field3": "enum (required): [allowed values: a, b, c]"
}

**Response (200):**

{
  "id": "string: [description]",
  "field1": "string",
  "createdAt": "ISO 8601 datetime"
}

**Error responses:** | Status | Code | Message | When | |--------|------|---------|------| | 400 | VALIDATION_ERROR | "field1 is required" | Missing required field | | 401 | UNAUTHORIZED | "Authentication required" | No/invalid token | | 403 | FORBIDDEN | "Insufficient permissions" | User lacks permission | | 409 |

Read more
Ships withmemstack

The structured skill framework for Claude Code: 131 professional skills for deployment, security, databases, content, marketing, and more. Skills activate automatically when you need them. Say "deploy this to Railway" and the right skill loads on demand.

Get the whole plugin

Other skills on memstack.