Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Feature Spec

ASecurity

Write a concise feature spec for engineering handoff. Use when the user says "write a spec", "feature spec", "one-pager for eng", "spec this out", "write up this feature", "I need to hand this off to engineering", "shape this up", or wants a concise technical brief - even if they don't say "feature spec".

20 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentsgoapisecurityperformance

Works with

api

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add qa-aman/claude-skills --skill feature-spec --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Feature Spec?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Feature Spec
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/qa-aman-feature-spec/badge)](https://www.skillsdirectory.com/skills/qa-aman-feature-spec)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: feature-spec
description: >
  Write a concise feature spec for engineering handoff. Use when the user says "write a spec",
  "feature spec", "one-pager for eng", "spec this out", "write up this feature",
  "I need to hand this off to engineering", "shape this up", or wants a concise
  technical brief - even if they don't say "feature spec".
---

## Overview

Based on **Shape Up** by Ryan Singer (Basecamp). A feature spec is not a PRD. A PRD justifies building something. A spec tells engineers exactly what to build - but at the right altitude. Shape Up's principle: give engineers a shaped problem with clear boundaries, not a detailed recipe. Ambiguity in the spec becomes a bug in production. Over-specification kills ownership.

## Workflow

### Step 1: Write the header
```
# Feature Spec: [Feature Name]
**PM:** [your name]
**Eng Lead:** [engineer name]
**Appetite:** [1-2 weeks / 4-6 weeks]
**Status:** Draft | In Review | Approved
**Related PRD / Ticket:** [link]
```

### Step 2: Write the Problem (2-3 sentences)
What is broken or missing? Who is affected? Shape Up framing: "Jobs to be done" - what job is the user hiring this feature to do?

### Step 3: Write the Solution at the right altitude
Shape Up's "fat marker sketch" - describe the solution broadly. Engineers need room to make technical decisions. Write at the level of user-visible behavior, not implementation.

Structure:
- **Key interactions** - what users can do (not how)
- **Boundaries** - explicit scope limits
- **Rabbit holes** - specific traps to avoid

### Step 4: Write Functional Requirements
Number each. Cover in order:
1. Happy path
2. Error states
3. Empty states
4. Edge cases

### Step 5: Write Non-Functional Requirements
Only include what's genuinely constrained:
- Performance targets
- Accessibility level (WCAG AA minimum)
- Browser/device support
- Security or compliance requirements

Don't pad. If there's no real constraint, don't list one.

### Step 6: Define No-Gos (Shape Up)
Explicit list of what this spec does NOT include. This is Shape Up's most important contribution to spec writing - stating what you're NOT building is as important as what you are.

### Step 7: List Open Questions
```
Q: [question]
Owner: [name]
Due: [date]
```
No spec should be approved with unresolved questions. Assign owners.

### Step 8: Link assets
Figma files, API specs, data models. A spec without visuals is incomplete for UI work.

## Anti-Patterns

**1. Over-specifying implementation**
Bad: "The button is blue, 48px, positioned top-right with 16px margin."
Good: "Users can trigger X from the main action area. Exact placement per Figma [link]."
Shape Up: over-speccing removes creative ownership from engineers and designers.

**2. Missing error states**
Bad: "User submits the form and sees confirmation."
Good: Cover success, validation error, server error, empty state, and loading state.

**3. No rabbit holes section**
Bad: Spec that describes what to build but not what to avoid.
Good: "Don't rebuild the notification system for this - use existing email infrastructure."

**4. Spec approved with open questions**
Bad: "TBD" items in an approved spec.
Good: All open questions resolved or explicitly deferred with a named owner and date.

## Quality Checklist

- [ ] Appetite defined (small or big batch)
- [ ] Problem framed as "job to be done"
- [ ] Solution at the right altitude - behavior not implementation
- [ ] Requirements cover happy path, errors, empty states, edge cases
- [ ] No-Gos explicitly listed
- [ ] Rabbit holes called out
- [ ] Open questions have owners and due dates
- [ ] Figma / mockup links included for UI work
- [ ] Spec fits on one page (split if it doesn't)

Attribution

qa-amanqa-aman
View sourceSee grades on GitHubMore from qa-aman →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →