Agent Skills & Evaluations
Available
Advisor Orchestrator Worker
Multi-Agent Hierarchical Collaboration • Intermediate
One model is a bottleneck. A team with one brain, twenty hands, and a board advisor is not.
Architecture Taxonomy Node
Agent Skills & Evaluations
Modular agent capabilities, structured reasoning protocols, reflection loops, and evaluation suites.
Showing 10 curated projects
← Back to all categories
Agent Skills & Evaluations
Available
Commit Archaeologist Agent Skill
Autonomous ReAct Agent Loop • Intermediate
git blame tells you who last changed a line. Commit Archaeologist reconstructs finds the introducing commit, orders later modifications, classifies commit.
Agent Skills & Evaluations
Available
Dependency Doctor Agent Skill
Autonomous ReAct Agent Loop • Intermediate
Dependency Doctor inspects one dependency manifest for surface-level, direct-manifest footguns. It catches unpinned versions, standard-library.
Agent Skills & Evaluations
Available
Project Graveyard Agent Skill
Autonomous ReAct Agent Loop • Intermediate
Every developer has the folder. Twenty-something dead projects, each abandoned for reasons nobody wrote down.
Agent Skills & Evaluations
Available
Scope Creep Detector
Autonomous ReAct Agent Loop • Intermediate
Checks a working, staged, saved, or branch diff against a one-line intent. It flags unrelated paths, new dependencies, public API renames, config or CI.
Agent Skills & Evaluations
Available
Openinterpreter
Autonomous ReAct Agent Loop • Intermediate
A coding agent for open models like Kimi K3 and GLM 5.3.
Agent Skills & Evaluations
Available
Planning With Files
Multi-Agent Hierarchical Collaboration • Intermediate
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style.
Agent Skills & Evaluations
Available
Openevolve
Autonomous ReAct Agent Loop • Intermediate
Open-source implementation of AlphaEvolve.
Agent Skills & Evaluations
Available
Rllm
Autonomous ReAct Agent Loop • Intermediate
Democratizing Reinforcement Learning for LLMs.
Agent Skills & Evaluations
Available
ANUS
Autonomous ReAct Agent Loop • Intermediate
A free coding agent in your terminal. It runs on the smartest free model that is up today.