52 tagged llm-evaluation, measured the same way as everything else here.
Browse within: evals 49llm-observability 43llm-ops 43sdlc 24benchmark 22game-development 20unreal-engine 20Multi-Agent 9llm-agents 9simulation-environment 9claude-code-plugin 7coding-agents 7agent-evaluation 6benchmarking 6
Skill Claude CodeCodex
Instrument AI agents with Tracely and turn their production traces into CI gates. Use when the user mentions Tracely, tracely-ai, tracelysdk, the tracely CLI, or asks to trace/observe an AI agent, add LLM evaluators or LLM-as-a-judge columns, debug why a trace or conversation isn't showing up, wire agent regression…
Skill Codex
Find, inspect, and check AI benchmark records with the Benchmark Radar CLI. Use when a request needs benchmark discovery, details, recent Radar evidence, or local data health; do not assume why the user needs the results.
Skill Codex
☠️ Finished candidates, fatal defects, readiness verdicts.
Skill Claude CodeCodex
Adapt an agent to run on BenchFlow (ACP) and verify it behaves identically inside the eval harness vs standalone — closing the eval↔prod gap. Use when adding a new agent to this repo or checking an existing one for eval/prod behavior parity.
Skill Claude CodeCodex
Run the hermeneutic deterministic English drift gate on an assistant draft before sending it when the draft contains numeric claims, completion language, universal quantifiers, or a summary of delegated work.
Skill Claude CodeCodex
Guard and improve prompts before expensive Codex, IDE, or CLI agent work. Use when a prompt is vague, broad, risky, costly, or should be optimized before implementation.
Skill Claude Code
Repair invalid local report.json files by inserting required report fields.
Skill Codex
A test-planning skill that turns a specification's requirements and acceptance conditions into observable results, test scenarios, evidence, and proof obligations. TDD means writing tests or defining expected behavior before implementation.
Skill Claude CodeCodex
Use this skill to inspect the current whiteboard.
Skill Claude Code
Statistically test whether a prompt or SKILL.md change is actually better than the old version. Use when the user asks to compare two prompts, A/B test a prompt change, check if a recent edit really improved things, find rule conflicts in a long prompt, or identify which sections of a prompt are pulling weight.…
Skill Claude CodeCodex
Build, style, and debug terminal user interfaces in Python with Textual. Use when the user mentions Textual, a TUI, App/Widget/Screen subclasses, reactive attributes, TCSS or Textual CSS, textual run, textual console, or compose(). Do NOT use for plain CLI argument parsing (use click-cli), Rich-only static output (use…
Skill Claude Code
Use when an agent, harness, or CI pipeline produces a scientific/numeric prediction and you need an INDEPENDENT third-party adjudication of whether that claim is trustworthy before acting on it. Also use when you need to turn "the agent said it validated itself" into a blocking gate with a real exit code. Covers…
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: