📝

AI EngineeringShell

Specify

Specify is an AI Engineering skill for Claude Code, published by rsmdt in the-startup.

508 stars58 forkson rsmdt/the-startupAdded 2026/08/26+29% in starsRepository updated 2026/08/03

View source on GitHub Download repo ZIP

claude-codeclaude-code-pluginclaude-marketplaceclaude-plugin

Install in seconds

Install Specify

Copy Specify into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/rsmdt/the-startup/tree/main/plugins/start/skills/specify ~/.claude/skills/specify

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/rsmdt/the-startup.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: plugins/start/skills/specify/SKILL.md in rsmdt/the-startup
Installs to: ~/.claude/skills/specify
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Specify does

Specify creates a full implementation specification from a brief description. It gathers requirements, designs the solution, and routes decomposition to Direct, Incremental, or Factory based on complexity.

Specify is cataloged under AI Engineering on DirSkills. Specify comes from a repository tagged claude-code, claude-code-plugin, claude-marketplace and claude-plugin.

Documentation

README

Excerpt

Persona

Act as an expert requirements gatherer that creates specification documents for one-shot implementation.

Description: $ARGUMENTS

Interface

SpecStatus { requirements: Complete | Incomplete | Skipped solution: Complete | Incomplete | Skipped decomposition: { tier: Direct | Incremental | Factory | None status: Complete | Incomplete | Skipped } readiness: HIGH | MEDIUM | LOW }

State { target = $ARGUMENTS spec: string // resolved spec directory path (from specify-meta) perspectives = [] mode: Standard | Agent Team classification: Direct | Incremental | Factory // from reference/classifier.md status: SpecStatus }

Constraints

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Specify

What else does rsmdt publish alongside Specify?
Specify is one of 25 skills that DirSkills catalogs from rsmdt/the-startup, the repository it ships in. Its siblings there include Analyze, Brainstorm and Canonical Review. Each one is a separate skill with its own page in this directory, installs the same way Specify does, and is maintained by rsmdt in that same repository. The rest of the collection is listed on the rsmdt/the-startup page.
How does Specify compare to other AI Engineering skills?
Specify ranks #2169 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Specify against them. Open each page to compare what they document and how they install.

More from rsmdt/the-startup

Specify is one of 25 skills cataloged on DirSkills from rsmdt/the-startup.

See all 25 skills →

Analyze

Analyze performs mechanism-level codebase analysis of business rules, architecture, auth flows, data models, integrations, and performance hotspots. Use it when you need to trace how something works before making a change.

Brainstorm

Brainstorm explores user intent, requirements, and design before implementation. Use it before creative work to validate scope, compare approaches, and get approval on a direction.

Canonical Review

Canonical Review orchestrates multi-agent code review with specialist perspectives and structured findings. Use it to review a PR, branch, staged changes, or files and synthesize actionable issues.

Constitution

Constitution creates or updates a project constitution with governance rules. It discovers codebase patterns first, then drafts evidence-backed rules for approval before writing them.

Debug

Debug systematically diagnoses and resolves bugs through conversational investigation, reproduction, and root cause analysis. Use it when you need to trace a failure, test hypotheses, and verify a minimal fix.

Document

Document orchestrates specialist agents to generate and maintain documentation for code, APIs, and project components. Use it when you need to check existing docs, update stale content, or add coverage with consistent links and line references.

More AI Engineering skills

Specify is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #2169 by stars among them.

Browse all AI Engineering skills →

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.