Agent Skills

SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.

Trust Score Usefulness Recommended Stars Latest

Filters

Harness — Long-Running Agent Framework

stellarlinkco

A framework for long-running, multi-session agent tasks: progress checkpointing, failure recovery, task dependency management, and concurrency controls.

orchestrationprogresscheckpointing

7 triggers

Overnight — Autonomous Long-Running Coding

claude-skill-registry

Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges

orchestrationautonomygit

483

6 triggers

Looper — Bounded Autonomous Audit Loops

script-kit-next

Durable pattern and tooling for running bounded autonomous audit loops ("Go AFK for N hours") with cadence, budget, and safe stop conditions.

automationauditcron

7 triggers

Ask the Oracle

awesome-omni-skill

Run deep, long-running code analysis tasks (architecture review, memory leak debugging, comprehensive code review) by packing code and submitting to a high-capa

code-analysisarchitecturedebugging

7 triggers