27,212 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
akitaonrails/llm-coding-benchmark
Skill Claude CodeCodex
Automatically evaluates an LLM coding benchmark result using a standardized 0-100 rubric across 8 dimensions. Use when a benchmark finishes, when the user asks to evaluate a model, analyze a run's quality, or generate a score for a result. Also activates for 'score', 'evaluate benchmark', 'audit model', or 'analyze…
Skill Claude Code
Render financial charts via the local chart web app (workspace at the repo root — Hono server + React front end, port 1792). Four chart types: intraday capital-flow line (flow) and cross-symbol signed-bar comparison (cohort) — both Recharts — plus SEPA strategy dashboard (sepa) and short-term multi-timeframe…
next-1688/1688-common-html-report-generator
Skill Claude CodeCodex
A skill that turns text data into interactive HTML reports using Python and preset templates. HTML is the format used to display web pages.
Skill Claude CodeCodex
Extracts structured data from websites and APIs, delivering clean datasets in multiple formats. Handles pagination, deduplication, and data enrichment for reliable business intelligence.
Plugin Claude Code
Bundles 2 skills · 249 tokens together
Edward Tufte's Visual Display of Quantitative Information — two executable skills (tufte-critique, tufte-chart) backed by a VDQI-sourced principles reference. Critiques graphics against a nine-criterion VDQI rubric with named chartjunk species and a 13-entry catalogue of dissected failures, and renders per-genre…
Skill Claude CodeCodex
Apply Edward Tufte's principles to any data visualization, chart, dashboard, or infographic. Use when the user asks to produce, design, critique, or improve a chart, graph, dashboard, KPI tile, table-with-data, sparkline, small multiple, time series, distribution plot, choropleth, or any other visual that communicates…
MCP server Claude CodeCodexCursor +2
MCP server for Snowflake. Runs locally from the snowflake-labs-mcp Python package. Needs 13 environment variables to run.
Skill Claude CodeCodex
Repo-local performance analysis skill for lo2cin4bt. Use when explaining generated metrics, equity curves, drawdowns, trades, rebalances, costs, slippage, benchmarks, Parameter Matrix, WFA, missing fields, and claims that require independent quantitative risk review.
Skill Claude CodeCodex
Domain playbook for optimization missions — any task whose goal is to move a metric: performance, latency, throughput, memory, cost, score, quality, compression, ranking, solver, model/eval, and similar metric-improvement work. Defines how to think about and run an optimization mission: establishing the ground truth…
saurabhsharma2u/search-console-mcp
Skill Claude CodeCodex
Expert AI agent skill for interacting with, configuring, and troubleshooting the Search Console MCP server (GSC, Bing, GA4, and PageSpeed).
liangdabiao/claude-data-analysis-ultra-main
Instructions file Claude Code
A set of Claude Code instructions for a data-analysis project. It covers the project overview, setup, data preparation, and how to call skills.
Skill Claude Code
Screen US stocks using William O'Neil's CANSLIM growth stock methodology. Use when user requests CANSLIM stock screening, growth stock analysis, momentum stock identification, or wants to find stocks with strong earnings and price momentum following O'Neil's investment system.
Agent Claude Code
Use when monitoring Bosun task execution with the simulator first, then daemon health and throughput only after a real task completes the full PR/review/merge path end to end. Also use when resuming the local monitor from .bosun-monitor session notes.
Skill Claude CodeCodex
A detailed financial review workflow for one company listed on China’s A-share stock markets. It examines profitability, cash flow, debt, operating efficiency, and signs that reported results may be unreliable.
Skill Claude CodeCodex
A skill that performs financial signal analysis using the DeepEar workflow.
Instructions file Claude CodeCodex
Instructions for tobilg/ai-observer, covering claude.md, project overview, build & development commands, setup and development.
akseolabs-seo/AK-Threads-booster
Skill Claude Code
Estimate likely 24-hour post performance from the user's historical data. Use after the user writes a post and wants a range estimate, upside view, or expectation check.
Skill Cursor
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…
Skill Claude CodeCodex
Periodically measure the retrieval quality of the knowledge base using evaluateretrieval (MRR@5, Recall@5, Precision@5) plus getindexstats for health metrics. Run weekly, after significant reindex activity, or when the user reports declining answer quality. Prevents silent index rot and grounds "should we tune X"…
Skill Claude CodeCodex
Rules and best practices when working on the dashboard React frontend codebase (including the inlined Gram Elements code).
Command Claude Code
You are the Analytics Collection Engine for the Viral Command system. You gather performance data for published content across all platforms, store it for pattern analysis, and prepare the feedback loop.
Skill Claude CodeCodex
Evaluate AI outputs with LayerLens. Upload traces, create judges, run evaluations, and retrieve quality scores -- all from within OpenClaw.
Skill Claude CodeCodex
Use to evaluate an LLM agent with evalyn. Orchestrates the full pipeline: install, instrument, trace, build dataset, suggest metrics, run eval, analyze, calibrate.
Agent Claude Code
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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: