Skill Claude CodeCodex
I deploy the application to production via GitHub Actions.
not rated 6 2mo ago A 14 tokens
original MIT
Skill Claude CodeCodex
Walks a contributor through adding a new benchmark to OpenChainBench. Covers spec format, harness contract, Prometheus scrape wiring, local validation, and PR conventions.
not rated 7 today A 39 tokens
original MIT
metrillm
27Skill Claude CodeCodex
Find the best local LLM for your machine. Tests speed, quality and RAM fit, then tells you if a model is worth running on your hardware.
not rated 6 3mo ago A 35 tokens
original Apache-2.0
Yinzhanqing/embodied-eval-automation
Skill Claude CodeCodex
Plan, explain, build, run, monitor, validate, transfer, and audit reproducible embodied-model studies and batch episode collection. Use when a user wants to connect a local, SSH, or cloud GPU host; understand and compare a policy, VLA, world model, world-action model, or hybrid with a benchmark; discover and reuse…
not rated 5 1mo ago A 145 tokens
original MIT
audit-post
29Skill Claude CodeCodex
The end-to-end procedure for auditing one already-published post to a scientific-organization standard. It chains the adversarial skills and — critically — re-runs the auditor on the CORRECTED post to confirm it now passes clean before committing. We are a scientific organization; we do not ship missteps. Run EVERY…
not rated 3 yesterday A 0 tokens
original MIT
cosmergon
30Skill Claude CodeCodex
Persistent multi-agent economy where autonomous AI agents compete for resources, trade on a marketplace, and benchmark decision-making against a standing population of always-on agents. Invite other agents for energy rewards. Auto-registers — no API key needed.
not rated 3 10d ago A 50 tokens
original MIT
Skill Claude CodeCodex
Run a standardized XORCISE agent benchmark — pick a ready-made playbook (or build your own from existing missions), point it at any OpenHands-supported model(s), and get a polished eval-card HTML report of how each model performed across the missions. Warns you about cost before spending anything.
not rated 2 1mo ago B 66 tokens
Skill Claude CodeCodex
Use when the user asks to lint, audit, test, benchmark, validate, or fix an agent skill — from a single SKILL.md frontmatter check to trigger-accuracy measurement or a corpus-wide audit of installed skills for duplication — driving the shakespii CLI (init, lint --json, test --run, bench) to resolve findings until…
not rated 2 1mo ago A 78 tokens
original MIT
unreal-mcp
33Skill Claude CodeCodex
Use this skill to perform actions inside an Unreal Engine project via a live-editor MCP connection. Trigger when the user wants to change, query, or run something in their Unreal Engine project, not for conceptual or docs questions. Concrete triggers: spawn/move/duplicate/transform actors in a level, open a .uproject…
not rated 2 1mo ago A 266 tokens
Skill Claude CodeCodex
Independent adversarial security review of a custody-spine change against SECURITY.md. Spawns a FRESH reviewer subagent that did NOT write the code, prompted to break the diff (cap overspend, window-slide, early release, fail-open void-return, TOCTOU, dedup/replay bypass, honest-scope overclaim, DrainBench fairness…
not rated 2 1mo ago A 143 tokens
original MIT
self-improve
35Skill Claude CodeCodex
Use when the user wants to proactively push a project forward by implementing its next feature. Reads project artifacts (specs' "future work" sections, README, TODOs, recent commit trajectory, codebase gaps), infers candidate features, asks the user to pick one, then implements it on an isolated branch with…
not rated 2 2mo ago A 99 tokens
eco-max
36Skill Claude CodeCodex
Maximum-savings variant of eco - the same frugality rules with a tighter reply budget, for routine chores (rename, small fix, quick lookup, boilerplate). Prefer plain eco for hard or high-stakes work. Works in any language.
not rated 2 18d ago A 53 tokens
original MIT
Skill Claude CodeCodex
Build, launch, smoke-test and drive the InferBench FastAPI backend (:7777) and its inference-engine orchestration. Use when asked to run, start, launch, boot, smoke-test, benchmark, or drive the inferbench backend / API / engines (llama.cpp, ollama, vLLM, SGLang, TGI), or to verify an engine actually starts and runs a…
not rated 2 10d ago A 90 tokens
original MIT
patchleague
38Skill Claude CodeCodex
Run, inspect, and compare multiple coding-agent CLIs on the same repository task with PatchLeague. Use when Codex should benchmark agents such as Codex, Claude Code, Gemini CLI, or OpenCode in isolated Git worktrees; verify their patches with tests; inspect saved runs or HTML reports; or preview and apply a selected…
not rated 1 1mo ago A 72 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: