Agent Skills

Cross-Project Analytics

orchestkit

Query local, privacy-safe cross-project analytics to report on agent, skill, hook, and team performance; replay sessions and estimate token costs.

Arize Experiment

awesome-copilot

Create, run, and analyze Arize experiments to evaluate and compare model performance using the ax CLI.

OpenTelemetry Skill — Observability Engineering Assistant

opentelemetry-skill

Expert OpenTelemetry observability skill for designing collectors, pipelines, sampling, cardinality management, security, and production-ready deployment patter

Swarma

swarma

Framework for running high-velocity growth experiments with agent teams that generate hypotheses, run tests, observe signals, and build a validated playbook.

Skill Optimizer

opencode-skills-collection

Diagnose and optimize Agent Skills (SKILL.md) using session transcripts and static analysis to improve triggers, workflows, and token efficiency.

Datadog Observability

claude-mpm-skills

Guides setup and best practices for Datadog APM, logs, metrics, synthetics and RUM to implement full-stack monitoring, tracing, and cost optimization in product

OpenJudge — LLM Evaluation Pipeline

openjudge

Tools and patterns to build automated evaluation pipelines for LLMs: graders, runners, aggregators, and analysis utilities for comparing model outputs and scori

OmniDocBench Evaluation Helper

opendatalab

Run, validate, and parse OmniDocBench document parsing evaluations with Docker/conda workflows and result parsing.

Code Quality Metrics Guide

dotfiles-claude

Practical guide to quantitative code-quality metrics (cyclomatic, cognitive, Halstead, maintainability index) with thresholds, formulas and measurement commands

Answering Natural Language Questions with dbt

comeonoliver

Use dbt's semantic layer or compiled SQL to answer business data questions: list metrics, modify compiled SQL when needed, and fall back to manifest analysis if

Body Composition Analyzer

vitaclaw

Analyze and track body composition metrics (body fat, muscle mass, visceral fat, BMI) and provide evidence-based recommendations and trend analysis.

Track ML Experiments (MLflow)

pjt222

Set up MLflow experiment tracking: server, autologging, artifact storage, run comparison and lifecycle management for reproducible ML workflows.

KB Stats (Knowledge Base Statistics)

AI-First SDLC Practices

Generates a markdown dashboard of knowledge-base health: inventory, layer/domain distribution, recent activity, and staleness metrics.

MetricFlow: Interactive Metric Definition

datus-agent

Interactively define MetricFlow metrics from natural-language business descriptions; proposes, validates, and dry-runs metric YAML for semantic modeling.

Metrics Report (codebase test & coverage analyzer)

ai-playground

Scans a repository, discovers and runs tests, computes coverage, evaluates test quality, and generates a metrics report website and JSON output.

LLM Evaluation

claude-plugins

Evaluation framework and tools for systematically measuring LLM performance using automated metrics, human judgment, and A/B testing.

SaaS Growth & Metrics Playbook

skills

Practical, cross‑language playbook to design and scale SaaS growth (PLG vs SLG), pricing, retention, and key metrics (ARR, NRR, CAC, LTV) with benchmarks and ca

Maverick Observability Best Practices

maverick

Practical observability standards: metrics, tracing, health checks, SLIs/SLOs and dashboards for production services.

Beads BV — Graph-Aware Triage

agentops

Graph-based backlog triage using bv/br: rank priorities, find bottlenecks, and produce machine-readable recommendations for agents (robot mode).

Vigil — Incident Response

claude-code-plugins-plus-skills

Incident response guidance for diagnosing production issues: gather symptoms, read logs, check metrics, trace requests, identify root cause, and recommend fixes

Outcome KPI Framework

nwave

A practical framework for writing measurable outcome-focused KPIs for features and user stories, mapping outcomes to leading indicators and measurement plans.

Agent Performance Optimization

agent-skills-hub

A structured workflow for improving agent performance via metrics, prompt engineering, testing (A/B), and safe staged rollouts.

Powertools for AWS Lambda

powertools-mcp

Guidance and utilities for building AWS Lambda functions with best practices: structured logging, X-Ray tracing, EMF metrics, idempotency and batch processing a

Grafana Mimir Metrics Storage

skills

Deploy and manage Grafana Mimir for scalable, long-term Prometheus and OpenTelemetry metrics storage with multi-tenancy support.

Code Statistics & Semantic Diff

claude-mods

Analyze codebase size, language composition, and semantic changes using tokei and difft.

Maple Rust Observability Style

maple

Implements OpenTelemetry observability in Rust using Maple's HTTP exporter and tracing-opentelemetry bridge.

Product Metrics Framework

catalyst

Establish a scientific hierarchy of leading and lagging indicators to predict product outcomes and design actionable dashboards.

SQL Analysis & Review

codex-is-all-you-need

Provides a rigorous framework for reviewing, creating, and validating SQL queries for business analysis and metric definition.

Agent Evaluation Layer

eval-layer

Add a rubric-based evaluation layer to agent projects to measure quality via LLM-as-a-judge scoring and weighted metrics.

Grafana Lens

grafana-lens

Full-spectrum Grafana observability: query metrics, logs, and traces, manage dashboards, and deploy Alloy data pipelines.