169 boosters for "developer-tools" — open source, verified from GitHub, ready to install
Persistent local memory for AI agents. Save, recall, and search project decisions as local JSON. Zero cloud, zero infrastructure.
A zero-friction checkpoint tool that instantly saves session context, memory, and progress to files without prompts or delays—essential for Claude Code users managing multi-turn projects and persistent state.
Use the SourceSage CLI from this repository checkout to generate repository summaries for the current repo or another local repo. Prefer the local checkout over assuming is globally installed. In this repository layout, the SourceSage tool root is the directory that contains this . 1. Resolve the S
Launch background tasks for parallel execution. Enables concurrent work on independent tasks with result aggregation. Launch a background task or manage running tasks. Start a new background task:
"name": "director-mode-lite", "description": "Use Claude Code like a Director, not a Programmer. Complete toolkit with 26 commands, 14 agents, 31 skills, and TDD-based Auto-Loop.", "name": "Lucas Wang",
This is a Shell/Markdown toolkit for Claude Code Director Mode. Keep shell scripts POSIX-compatible where possible. Markdown files are the primary deliverable.
A unified initialization booster that streamlines project setup by routing to specialized commands for documentation, preferences, and design tokens—ideal for developers standardizing new projects and maintaining consistent configurations.
"description": "You say it, AutoCode ships it. 47 skills. Code to deployment in one session. I-Lang v3.0 powered.", "name": "I-Lang Research, Eastsoft Inc.", "url": "https://github.com/ilang-ai/autocode"
"name": "claude-code-superpowers", "description": "24 elite skills across 5 layers: discipline, domain expertise, intelligence, coordination, and execution. Turn Claude Code into a proactive engineering partner.", "name": "GadaaLabs",
A comprehensive tutorial chapter teaching developers how to build and deploy intelligent AI agents with tool use and automation capabilities in AnythingLLM. Ideal for engineers looking to add autonomous workflows and function-calling to their self-hosted RAG systems.
Work Item Show is a CLI skill that displays comprehensive details about a specific work item, including status, dependencies, session history, and git information—useful for developers managing complex projects in Claude Code environments.
Session End guides developers through a structured workflow to complete coding sessions with quality checks, changelog updates, and learning documentation. It's ideal for developers using Claude Code who want to maintain organized, documented development practices.
pyDeprecate is a lightweight Python library (Python 3.9+) for decorator-based deprecation of functions, methods, and classes with automatic call forwarding. Zero runtime dependencies by design. Tests use a three-layer separation: 1. Targets () — new implementations
spec-gen automates the reverse-engineering of codebases into structured OpenSpec specifications through LLM-powered static analysis, enabling developers to maintain accurate, living documentation that reflects actual code behavior rather than intent.
Two tiers: hooks handle automatic context flow (surfacing, extraction, compaction survival). MCP tools handle explicit recall, write, and lifecycle operations. Three instances for neural inference. The wrapper defaults to . All three models auto-download via if no server is running (Metal on Appl
"name": "espalier-engineering", "description": "Train your AI coders the way you'd train a vine — discover your codebase's actual patterns, then encode them as rules, skills, agents, hooks, and a guided pipeline so generated code lands inside your conventions on the first try, not the fifth", "homep
The captain's log for your codebase. Every decision, discovery, and change logged as you ship code. Use GitHub as a complete knowledge graph where every brainstorm, commit, review, and decision is traceable. This skill orchestrates existing skills and references; it defines when and how to invoke th
"description": "Ship software systematically: project lifecycle, TDD, parallel agents, code review, security auditing, and infrastructure validation", "email": "lgbarn@users.noreply.github.com"
"name": "depwire-cli", "description": "Code cross-reference visualization and AI context engine for TypeScript, JavaScript, Python, Go, Rust, and C. Zero native dependencies — works on Windows, macOS, and Linux.", "depwire": "dist/index.js"
"description": "2389.ai skill collection including Firebase, CSS, testing, and development workflows",
"name": "claude-model-router-hook", "description": "Automatic model switching for Claude Code based on prompt complexity. No API calls.", "homepage": "https://github.com/tzachbon/claude-model-router-hook",
"name": "evolving-lite", "description": "Self-evolving Claude Code system that learns from corrections, manages context, and improves every session", "name": "PrimeLine AI",
Skill metadata (version, author, license, optional_mcps, fallback) lives in manifest.json and plugin.json. Claude Code only reads and from this frontmatter; extra keys are silently ignored, so they belong with
"name": "agent-lint", "description": "Check how well your repo supports AI coding agents.", "homepage": "https://github.com/0xmariowu/agent-lint",
