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

Product Spec

ASecurity

Turn a vague idea into something buildable — a PRD, feature spec, scoped MVP or ticket breakdown. Use when asked "how should we build X", to write requirements, or when a request is too fuzzy to start coding.

2 stars
0 votes
0 copies
0 views
Added 10/3/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 10/3/2026

$npx -y skills add ivanvp91/TRCode --skill product-spec --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Product Spec?

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

Security grade badge for Product Spec
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ivanvp91-product-spec/badge)](https://www.skillsdirectory.com/skills/ivanvp91-product-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: product-spec
description: Turn a vague idea into something buildable — a PRD, feature spec, scoped MVP or ticket breakdown. Use when asked "how should we build X", to write requirements, or when a request is too fuzzy to start coding.
description_ru: Превратить смутную идею в то, что можно построить — PRD, спецификацию фичи, MVP с границами, разбивку на задачи. Когда спрашивают «как нам сделать X», просят написать требования, или запрос слишком расплывчат, чтобы начинать код.
triggers: спека, спецификация, spec, prd, требования, requirements, техзадание, user story, юзер стори, mvp, скоуп, scope, разбей на задачи, break down, тикеты, tickets, бэклог, backlog
---

# Product spec

## 1. Nail the problem before the solution
Write: who has the problem, how often, what they do today, and what it costs them. If you cannot answer these, the spec is premature — ask. A spec that opens with a solution hides the fact that nobody checked the problem exists.

## 2. Define done
- **Goal**: one sentence.
- **Success metric**: the number that moves, and by how much.
- **Non-goals**: what this explicitly does not do. This section prevents more waste than any other.

## 3. Describe behaviour, not implementation
User stories or plain flows: trigger → steps → outcome. Cover the main path first, then:
- empty / first-run state,
- error and failure paths (offline, permission denied, invalid input),
- limits (rate, size, quantity) and what happens at the limit,
- permissions: who can see and do what,
- what happens to existing data and existing users (migration, backwards compatibility).

Leave the *how* to whoever builds it, unless a technical constraint is part of the requirement.

## 4. Scope honestly
Split into **must / should / later**. The "must" set is the smallest thing that delivers the outcome end to end — a thin slice all the way through, not half of every layer. If everything is a must, the scope is wrong.

## 5. Open questions
List every decision you could not make, with who must decide it and by when. An unmarked assumption is what gets rebuilt later.

## 6. Break it into work
Tickets that are independently shippable, each with a title, one-line goal, and acceptance criteria written as checkable statements ("returns 400 with `invalid_range` when `to` < `from`"). Note dependencies and order.

## What not to do
- No requirements phrased as "fast", "intuitive", "robust" — give the number or the check.
- Do not design the UI in the spec beyond what the behaviour requires.
- Do not silently expand scope; propose additions as separate "later" items.
- Do not skip non-goals and open questions to look decisive.

## Answer format
Problem → Goal & metric → Non-goals → Flows (with edge cases) → Scope (must/should/later) → Open questions → Tickets with acceptance criteria. One page for a feature, two for a product.

Attribution

ivanvp91ivanvp91
View sourceSee grades on GitHubMore from ivanvp91 →
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', ...

698431 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 →