Analytics and metrics skills

16,160 tagged Analytics and metrics, measured the same way as everything else here.

Browse within: LLM 161agents 144agent 143seo 96skills 86agentic-ai 81javascript 81ab-testing 74cli 60ai-assistant 57claude-code-plugin 57claude-code-skills 56marketing-automation 56claude-plugin 53

sfos-splunk-obs

577

alex-jb/solo-founder-os

Skill Claude Code

Ship reflections, eval drift, and bandit regret from the solo-founder-os 11-agent stack into Splunk over HEC. Five-minute install, zero new Python deps (stdlib urllib + json + sqlite3), six-panel dashboard you import once. Use when the user runs solo-founder-os agents on cron / launchd and asks "are my agents learning…

not rated 11 2mo ago A 136 tokens original MIT

destinyscout

578

Scofy0123/Destiny-job-scout

Skill Claude CodeCodex

A Chinese-language job-monitoring tool for BOSS Zhipin, a Chinese recruitment website.

not rated 11 5mo ago A 69 tokens

obai-strategy

579

sixteen-dev/obai

Skill Claude CodeCodex

Quantitative equity strategy design and backtesting via the OBaI backtest MCP server (http://localhost:8007/mcp). Use when the user wants to build, test, backtest, optimize, refine, repair, or compare a trading strategy, run walk-forward robustness validation, inspect trade logs, or follow up on a backtest job.…

not rated 11 changed today A 111 tokens

wudao-stock-data

580

jcdreamjc/wudao-mcp

Skill Claude CodeCodex

Use Wudao Data when an AI Agent needs read-only A-share market data through MCP: market overview, stock/index/ETF/convertible-bond data, K-line data, limit-up ladder, sector rotation, capital flow, Dragon Tiger List, research reports and post-market review workflows.

not rated 11 1mo ago A 65 tokens original MIT

charted

581

marzukia/charted

Skill Claude CodeCodex

Generate SVG or PNG charts from raw numbers or a CSV using charted, a zero-dependency Python chart library. Covers bar, column, line, scatter, bubble, pie, polararea, radar, area, box, histogram, heatmap, gantt, combo, and sankey, plus multi-series data, named palettes, and a CLI. Use when asked to plot, chart, or…

not rated 11 1mo ago A 90 tokens original MIT

costhq

582

brian-mwirigi/CostHQ

Skill Claude CodeCodex

The Active Circuit Breaker & Cost Tracker for AI SaaS. Enforce hard API budgets, track GPT-4o/Claude costs, and stop runaway agents before they break your unit economics.

not rated 11 3mo ago B 42 tokens original MIT

mac-optimizer

583

skalinets/mac_optimizer

Skill Claude Code

Analyze macOS performance — CPU, memory, swap, processes, browsers, containers — and battery drain, then provide actionable optimization recommendations. Use when the user asks to check Mac performance, optimize their system, diagnose slowness, audit running processes, or asks why the battery drains fast.

not rated 11 changed 5d ago A 62 tokens

featbit/featbit-skills

Skill Claude CodeCodex

End-to-end FeatBit experimentation and release-decision workflow. Use when shaping product intent, writing a hypothesis, defining feature flags and rollout strategy, designing metrics and instrumentation, creating or analyzing experiment runs, deciding continue/pause/rollback/inconclusive, or capturing learnings for…

not rated 11 5d ago A SkillSpector: warn 66 tokens original MIT

price-action-skills

585

AxisJu/price-action-skills

Skill Claude CodeCodex

Analyze stock price movements using Al Brooks Price Action methodology. Use when user wants price action analysis, support/resistance levels, trend channels, swing points, or entry setups (H1/H2/L1/L2) for A-Share or global stocks.

not rated 11 11d ago A 56 tokens

ai-product-research

586

allenGKC/ai-product-research

Skill Claude CodeCodex

A Chinese-language workflow for researching an AI product using its website, GitHub data, community opinions, and competitor comparisons.

not rated 11 4mo ago A 87 tokens original MIT

aeo-analytics-free

587

psyduckler/aeo-skills

Skill Claude CodeCodex

Track AI visibility — measure whether a brand is mentioned and cited by AI assistants (Gemini, ChatGPT, Perplexity) for target prompts. Runs scans, tracks mention/citation rates over time, detects trends, and identifies opportunities. Uses Gemini API free tier (with grounding) as primary method, web search as…

not rated 11 3mo ago A 152 tokens original MIT

job_health

588

DeepLink-org/probing

Skill Claude CodeCodex

Job-level health: cluster alive, step lag, slowdown proxy, comm trend.

not rated 11 3d ago A SkillSpector: pass 19 tokens original Apache-2.0

dashboard

589

hubzoid/hubzoid

Skill Claude CodeCodex

Build a polished single-file HTML dashboard (charts, KPIs, tables) from data you have gathered, and save it with writeartifact so the user gets a clickable link. Use when the user asks for a chart, graph, dashboard, report, or any visual summary of numbers.

not rated 11 5d ago A SkillSpector: pass 60 tokens original MIT

skills

590

upstash/agents-worldcup

Skill Claude CodeCodex

You are a football analyst competing against two other AI agents at predicting 2026 World Cup game outcomes. Each correct guess is worth +1 point.

not rated 11 2mo ago A 0 tokens

cc-user-autopsy

591

Imbad0202/cc-user-autopsy

Skill Codex

Produces a deep, honest peer-review of how someone uses Claude Code by statistically analyzing their local session data (/.claude/usage-data/ and /.claude/projects/). Trigger whenever the user asks to review, analyze, audit, or critique their own Claude Code usage, workflow, habits, or skill level — including phrases…

not rated 11 1mo ago A 271 tokens original MIT

x-twitter

592

nevaaron/x-smart-read

Skill Claude CodeCodex

Personal X (Twitter) analytics — timeline engagement, mentions, follower tracking, read any tweet/thread, bookmarks, and combined briefings via X API v2. Cost-optimized with persistent local store and daily budget guards.

not rated 11 6mo ago A 47 tokens original Apache-2.0

tufte-viz

593

quzhi-ai/tufte-viz

Skill Claude CodeCodex

Ideate and critique data visualizations using Edward Tufte's principles from "The Visual Display of Quantitative Information." Use this skill when: (1) Designing new data visualizations or charts (2) Critiquing or improving existing visualizations (3) Reviewing dashboards or reports for graphical integrity (4)…

not rated 11 3mo ago A 129 tokens original MIT

a-attia/scicomp-research-skills

Skill Claude Code

Use this skill at the start of any non-trivial session in this ecosystem -- the single biggest lever for reducing token / quota / context-window consumption and for keeping the agent productive across sessions. Make sure to load this whenever the work involves more than a few file reads, any PDF handling, multi-file…

not rated 11 5d ago A SkillSpector: warn 0 tokens original MIT

troykelly/codex-skills

Skill Claude CodeCodex

Setup Sentry AI Agent Monitoring in any project. Use this when asked to add AI monitoring, track LLM calls, monitor AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI. Automatically detects installed AI SDKs and configures the appropriate Sentry integration.

not rated 11 8mo ago A 70 tokens

teambition-statistics

597

teambition/skills

Skill Claude CodeCodex

A Teambition reporting skill for analysing company task data. Teambition is a project-management service, and the skill retrieves figures such as task totals, completion rates, bugs, and requirements.

not rated 11 4mo ago A 73 tokens

Ma1oneZhang/nsys-parquet-perfetto-skill

Skill Claude CodeCodex

Export NVIDIA Nsight Systems .nsys-rep or .qdrep reports to native Nsight Parquet tables, then use the published Rust and Apache DataFusion converter to create Perfetto/Chrome Trace JSON and aligned event Parquet. Use when Codex needs a fast, SQLite-free conversion of Nsight CUDA kernel, H2D/D2H/D2D memcpy, CUDA…

not rated 11 1mo ago A 143 tokens

yekwennnn/ashare-graham-screener

Skill Claude CodeCodex

An automated stock screener for Chinese A-share companies using Benjamin Graham’s defensive-investing rules, which favor financially stable businesses at reasonable prices.

not rated 11 1mo ago A 135 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: