Do Feature — Development skill for Claude Code
description: Execute feature with team of agents — waves, reviews, commits.
How to install Do Feature
Installs to ~/.claude/skills/pavel-molyanov-molyanov-ai-dev-do-feature/SKILL.md
mkdir -p ~/.claude/skills/pavel-molyanov-molyanov-ai-dev-do-feature && curl -fsSL https://raw.githubusercontent.com/pavel-molyanov/molyanov-ai-dev/HEAD/commands/do-feature.md -o ~/.claude/skills/pavel-molyanov-molyanov-ai-dev-do-feature/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Do Feature does
description: | Execute feature with team of agents — waves, reviews, commits.
Use when: "выполни фичу", "do feature", "execute feature", "запусти фичу"
Do Feature
Execute a full feature using a team of agents.
Step 1: Load Skill
Invoke Skill tool: `Skill(skill: "feature-execution")`
Step 2: Find Feature
- User provides feature path or name
- Read
work/{feature}/tech-spec.md— verify exists and approved - Read
work/{feature}/tasks/— verify task files exist - If
Alternatives in Development
- Claude Skills Cookbook — A comprehensive guide to using Claude's Skills feature by Anthropic 36.3k ★
- Plan Feature: Comprehensive Archon Implementation Planning — Plan Feature: Comprehensive Archon Implementation Planning skill 17.6k ★
- Feature Dev — Comprehensive feature development with specialized agents 14k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Cohort Analysis
Cohort retention curves, feature adoption, and segment insights
Analyze Feature Requests
Prioritize feature requests by theme, impact, effort, and risk
02 Runtime Shims
Prompt 02: Runtime Shims for bun:bundle Feature Flags & MACRO Globals
Sniffly
Claude Code dashboard with usage stats, error analysis, and sharable feature.
New Feature
新功能全流程(需求审问 → 设计 → 实现)
Hippo Feature
Build one hippo feature from RESEARCH.md using the micro-eval TDD loop
Related Agents
New Track
Create a new track (feature, bug fix, chore, or refactor) with a detailed specification and phased i... - wsho
Civitai Correctness Review
Reviews a feature segment in the main Civitai Next.js app (src/) for safety gaps — authorization scoping, mone
Recon Ranker
Attack surface ranking agent. Takes recon output and hunt memory, produces a prioritized attack plan. Ranks by