finishing-a-development-branch
Branch close checklist: tests, commit message, pull request, and review request
Branch close checklist: tests, commit message, pull request, and review request
npx skills add https://github.com/obra/superpowers/tree/main/skills/finishing-a-development-branchBranch close checklist: tests, commit message, pull request, and review request
This repo contains 13 individual skills — each has its own dedicated page.
Structured ideation and problem decomposition frameworks
Split work across parallel subagents and coordinate their outputs
Execute a plan step-by-step with checkpoints and verification at each stage
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Prepare code for review: self-review, test coverage, and pull request description
Orchestrate specialized subagents for different parts of a task
Hypothesis-driven debugging loop: observe, hypothesize, test, verify
TDD loop: write the failing test first, implement the minimal change, verify, then refactor
Use git worktrees to run parallel agent sessions on separate branches
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Force a verification pass before any task is marked done
Write structured implementation plans before starting complex tasks
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Community skills for Claude Code: token optimization, productivity workflows, and development best practices. All skills tested with TDD methodology (RED-GREEN-REFACTOR). Features rescue-tokens skill: 90% verbosity reduction, eliminates rate limits through 9 optimization patterns.
🤖 Upgrade and optimize OpenClaw AI Agent project manager configurations for improved proactivity, session handling, and task efficiency.
The Claude Code setup that actually ships. 18 agents, 35 skills, 20 hooks, continuous learning. Enforcement-first: Plan → Work → Review → Learn → Compound.
Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans that survive context loss and /clear, plus a deterministic completion gate and multi-agent shared state on disk. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard.
AI-Powered Telegram Monitor 2026: Real-Time Message Classification & Insights Dashboard
Agent skills for the PipsGravity brand automation system. Each skill is a markdown file that teaches Claude a specific domain. Skills are fetched at runtime by n8n workflows via raw GitHub URL.