benchmarking skills

Marker-Inc-Korea/AutoRAG

Skill Claude CodeCodex

Configure AutoRAG for first use or repair its single-agent model, approved document roots, retrieval indexes, datasource skills, and health checks without exposing credentials.

Marker-Inc-Korea/AutoRAG

Skill Claude CodeCodex

Use an already configured AutoRAG librarian agent to search, summarize, compare, and answer questions from local document collections. Use autorag-setup for configuration or indexing changes.

aristoteleo/PantheonOS

Skill Claude CodeCodex

End-to-end workflow for gene panel design in scRNA-seq and spatial transcriptomics, that should be STRICTLY followed: dataset understanding + smart downsampling + train/test splits, algorithmic selection (HVG/DE/RF/scGeneFit/SpaPROS), optimal sub-panel discovery (ARI vs size), biological completion with a stability…

gregs1104/pgbent

Skill Claude CodeCodexCursor

Tune Matplotlib labels on pgbent PG18 charts: scatter point placement, horizontal bar value labels (inside bar with contrast color when they fit), overlap avoidance, and PNG regeneration. Use when fixing crowded scatter or bar labels, pg18-osm-power-.png, pg18-osm-relation-power.png, pg18-osm-relation-scatter.png…

Hmbown/Hegelion

Skill Claude CodeCodex

Dialectical reasoning and autocoding via Hegelion MCP tools.

ktwu01/benchmark-radar

Skill Claude CodeCodex

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.

kangarooking/X-growth-skills

Skill Claude CodeCodex

A research method for studying successful social-media accounts and their popular posts to find ideas for a distinct content approach.

morluto/flameox

Skill Claude CodeCodex

Use Flameox to investigate runtime performance, memory, execution, scaling, GPU kernels, inference, and reliability with preserved evidence and explicit claim quality.

tonyblu331/research-proof

Skill Claude CodeCodex

Turn vague research ideas, math-heavy claims, AI-lab style agent loops, benchmark claims, causal claims, prototype-readiness claims, design research, prompt-injection-sensitive evidence reviews, and medical-research style questions into falsifiable proof programs with fixed Claim/Verifier/Current…

MerlijnW70/sota-scan

Skill Claude CodeCodex

Benchmark the current repo against the state of the art by scanning real online repos (GitHub and the wider web) in the same domain, then produce a cited capability matrix and a ranked, repo-grounded gap list. Use when the user asks "is our X top-tier", "what are we missing", "compare us to the best", "study online…

patrick-toulme/harnessgym

Skill Claude CodeCodex

Optimize HarnessGym tensor-layout kernelplan.json tasks with a generated MCP server for plan validation, dev/final benchmarking, trace analysis, rollback-safe search, candidate application, history comparison, and experiment ranking. Use when a task asks to minimize bestcycles for benchmark.py or tune tensor…

patrick-toulme/harnessgym

Skill Claude CodeCodex

Use for the H100 Triton fused RMSNorm + SiLU gate optimization task. Provides the workflow and MCP tooling for objective runs, rollback-safe config sweeps, source diagnostics, benchmark history, and final held-out verification.

pinecone-io/cultivar

Skill Claude CodeCodex

Placeholder skill used only to smoke-test the eval framework's workdir-capture mechanism. Not a real skill — delete once a real code-gen skill exists.

pinecone-io/cultivar

Skill Claude CodeCodex

Placeholder skill used only to smoke-test the eval framework's workdir-capture mechanism. Not a real skill — delete once a real code-gen skill exists.

pinecone-io/cultivar

Skill Claude CodeCodex

Drive the cultivar CLI to test whether an agent skill improves behavior — scaffold tasks, run with/without the skill across Claude/Copilot/Gemini (locally or on Modal), grade against a rubric, and read the results.

wieslawsoltes/Performance-Skill

Skill Claude CodeCodex

Evidence-first performance engineering workflow for coding agents combining portable .NET diagnostics with platform-native profiling, BenchmarkDotNet, application benchmarking, statistical validation, deployment, container, graphics, and GPU procedures.

abinauv/business-consulting

Skill Claude CodeCodex

Comprehensive change management consulting toolkit — stakeholder mapping, ADKAR framework, Kotter's 8-Step Model, communication planning, resistance analysis, cultural assessment, readiness assessment, training needs analysis, impact assessment, and transition planning.

abinauv/business-consulting

Skill Claude CodeCodex

Analyze customer behavior, map journeys, develop personas, and identify growth opportunities. Use this skill when the user mentions: customer insights, voice of customer, VoC, customer journey, journey mapping, JTBD, jobs to be done, persona, customer segmentation, churn analysis, retention, NPS, CSAT, customer…

abinauv/business-consulting

Skill Claude CodeCodex

Assess digital maturity, build transformation roadmaps, evaluate AI/automation opportunities, rationalize technology stacks, and design data and cloud strategies. Use this skill when the user mentions: digital transformation, digital maturity, digital strategy, technology modernization, legacy modernization…

Firespawn-Studios/tne-sdk

Skill Claude CodeCodex

Play The Null Epoch, a persistent AI agent MMO. Use when the user wants to connect an agent to Null Epoch, check game state, submit actions, play the game, or interact with the Null Epoch API. Handles authentication, state polling, action submission, and survival strategy for the Sundered Grid. Do NOT use for general…

proyecto26/autoresearch-ai-plugin

Skill Claude CodeCodex

Autonomous LLM training optimization with GPU support. Runs 5-minute training experiments, measures valbpb, keeps improvements or reverts — repeat forever. Use this skill when the user asks to "train a model autonomously", "optimize LLM training", "run ML experiments", "autoresearch with GPU", "optimize valbpb"…

proyecto26/autoresearch-ai-plugin

Skill Claude CodeCodex

Autonomous experiment loop: edit code, commit, run benchmark, extract metrics, keep improvements or revert, repeat forever. Use this skill when the user asks to "run autoresearch", "start an experiment loop", "optimize a metric autonomously", "autonomous experiments", "benchmark loop", "keep/discard experiments"…

luckeyfaraday/fusion-engine

Skill Claude CodeCodex

Run a single prompt across multiple LLMs in parallel via OpenRouter, then synthesize their responses into one answer with a judge model. Use when the user wants multi-model fusion, ensemble LLM queries, parallel model comparison, or a second opinion across providers.

greynewell/mcpbr

Skill Claude CodeCodex

Quick-start command to run SWE-bench Lite evaluation with sensible defaults.