Discover tools scripting skills, compare source repositories and read the instructions for each workflow.
Generate post-run analysis reports for batch processing jobs. Analyzes manifests, timings, and failures to produce comprehensive markdown reports. Optionally sends to agent-inbox for cross-project communication...
Writes portable skills, rules, and commands that work across Claude Code, OpenCode, and Cursor. This skill should be used when the user asks to "write a portable skill", "make this work in Cursor/OpenCode", "se...
Expert system for generating official Antigravity/Gemini Agent Skills. Enforces folder structure, YAML standards, and best practices.
Debugs code issues, errors, failing tests, and broken flows using a systematic workflow. Identifies root causes, applies minimal fixes, and validates solutions. Works with errors, test failures, API issues, dat...
Use the OpenAI Codex CLI to analyze code, plan, and perform other tasks.
Targeted Claude Code problem solver for specific issues and implementation questions. Use when the user has a specific problem to solve, needs help with a particular feature, is debugging an issue, or wants to...
This skill should be used when the user asks to 'plan this', 'orchestrate', 'break down', 'split into phases', 'coordinate tasks', 'create a plan', 'multi-step feature', or has complex tasks needing structured...
Managing ML research and engineering workflows. Use when the user asks to "start a new research project", "refactor for cleanliness", or mentions "clean workflow" or "iterative research".
Implements Manus-style file-based planning for complex tasks. Creates plans in docs/plans//. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with native C...
Use the Google Gemini CLI to analyze code, plan, and perform other tasks.
Use when automating recurring tasks in spaces, setting up cron-like schedules, running agent prompts on a timer, or configuring periodic automation
Modern Python development with Python 3.12+, Django, FastAPI, async patterns, and production best practices. Use for Python projects, APIs, data processing, or automation scripts.
Automated CI/CD pipeline fixer - watches CI, fixes errors locally, commits, and loops until green. Use when CI is failing and you want to automatically fix and verify changes.
Open-source Terraform alternative for infrastructure provisioning with installation and workflow commands.
Automates browser interactions for web testing, form filling, screenshots, and data extraction.
Web automation using LLMs and Playwright. Enables agents to autonomously navigate web pages, interact with elements, and complete complex tasks.
Build state-machine based automation with human-in-the-loop support through Interactor. Use when implementing approval flows, multi-step processes, automated pipelines, or any workflow requiring user input at s...
Orchestrates Pukaist agents, enforces plan-first workflow, runs integrity tests, and delegates tasks; use for coordination or system audits.
Infrastructure as Code tool with installation, initialization, and provisioning workflow commands.
Automatically backs up files, saves diffs, uses agents/skills, and ensures modular code (
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool cal...
Intelligent auto-continuation skill for Claude Code sessions. Use when working on extended tasks requiring minimal interruption, continuous development workflows, or Ralph Loop style iterations.
Development environment, testing, CI/CD, and deployment procedures. Use this skill when working with moon commands, database lifecycle, GitHub Actions, or deployment workflows.
Ralph - Long-Running Task Agent. Autonomous AI that works through PRD tasks iteratively, with access to full ACT ecosystem knowledge across all 7 codebases.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.