Feature Fit

Analyzes new feature requests for EXISTING projects. Reads config/mcp context, performs Gap Analysis, and creates a Feature Brief.

9 stars 2 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ydnikolaev/antigravity-factory --skill feature-fit
Manual install
git clone --depth 1 https://github.com/ydnikolaev/antigravity-factory.git /tmp/antigravity-factory
mkdir -p ~/.claude/skills
cp -r /tmp/antigravity-factory/src/skills/feature-fit ~/.claude/skills/feature-fit

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Feature Fit Analyst

> **MODE**: ANALYSIS. You are the bridge between a new idea and an existing system.
> ✅ READ existing architecture first
> ✅ CHECK `CONFIG.yaml` and `mcp.yaml`
> ✅ OUTPUT Feature Brief for Product Analyst

## When to Activate

- "I want to add a new feature to this project"
- "We need to integrate X into the current app"
- "How would we implement [Feature]?" (Context: Existing project)

**DO NOT activate if**:
- Project is empty (Use `@idea-interview`)
- User wants to refactor code (Use `@refactor-architect`)

## Interview Strategy (The "Why" & "How")

**Tone**: Professional Systems Analyst. Precise, technical, but inquisitive.
**Language**: Mirror the user's language (Russian/English).

> [!IMPORTANT]
> **Question Format — Chat vs Artifact:**
> - **1-2 quick clarifications** → Ask in chat directly
> - **3+ structured questions** → Create Feature Brief artifact, list questions there, use `notify_user` for review
> 
> **Why?** Long question lists in chat are overwhelming. Keep chat light, use artifacts for structure.

### Question Examples
1.  **Context First**: "I see you use Postgres and Nuxt. Does this feature need real-time data?"
2.  **Constraint Checking**: "This changes the User schema. Is that acceptable for MVP?"
3.  **TDD Probe**: "How would we test this? Do we need a mock for X?"

## Workflow

### Phase 1: Context Loading (Crucial)
Before asking ANY questions, read the project state:
Read the full skill on GitHub

Details

Skill name
feature-fit
Path
src/skills/feature-fit/SKILL.md
Repo updated
28 January 2026

FAQ

What does the Feature Fit skill do?

Analyzes new feature requests for EXISTING projects. Reads config/mcp context, performs Gap Analysis, and creates a Feature Brief.

How do I install the Feature Fit skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ydnikolaev/antigravity-factory --skill feature-fit. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Feature Fit popular?

It lives in ydnikolaev/antigravity-factory, which has 9 GitHub stars and 2 forks.

Related skills

Backend Go Expert

9

ydnikolaev/antigravity-factory

Expert Go developer (1.25+) specializing in Clean Architecture and DDD.

Software Development

Bmad Architect

9

ydnikolaev/antigravity-factory

The Lead Architect for Antigravity TMA projects. Enforces DDD, BMAD V6, and coordinates the squad.

Other

CLI Architect

9

ydnikolaev/antigravity-factory

Expert in Go CLI Architecture (Cobra, Viper, POSIX).

Software Development

Hyperion

8

GPire/claude-skills-swarm

HYPERION: Meta-intelligence engine che replica e supera la logica cognitiva di Fable 5, Gemini 5.2, Kimi K2.6, DeepSeek V4 Pro, ChatGPT 5.5, Mythic 5 — anche su Haiku con effort minimo. Risolve i problemi specifici di ogni modello. MoE-style prompt routing, Constitutional Chain, Extended Reasoning Scaffold, Agentic Persistence, Calibrated Uncertainty, Effort Gradient Engine, Cross-Model Synthesis. Attiva per qualsiasi task che richiede il massimo dell'intelligenza possibile con il minimo dell'effort.

AI, LLMs & Agents

Agent Swarm

8

GPire/claude-skills-swarm

Orchestrazione avanzata di agenti AI: swarm intelligence, multi-agent systems, orchestratori intelligenti, pipeline agenti, Claude SDK multi-agent, Gemini CLI agents, agenti specializzati, agent-as-tool pattern, parallelizzazione, fan-out/fan-in, agent memory, agent handoff, MCP servers orchestration, tool use avanzato, agenti autonomi, agenti collaborativi. Attiva quando l'utente vuole creare sistemi multi-agente, orchestrare agenti, costruire pipeline AI, usare Claude SDK per agenti, creare swarm di agenti.

AI, LLMs & Agents

MCP Expert

9

ydnikolaev/antigravity-factory

Expert on Model Context Protocol (MCP) servers. Use this skill when designing, building, debugging, or integrating MCP servers with tools, resources, and prompts.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.