Analytics and metrics commands

kLOsk/adloop

Command Claude Code

Full optimization checklist for a Google Ads campaign.

px0-ai/px0

Command

Every execution — a workflow run, or a brain ask — is recorded: what triggered it, which tools it called, what it produced, and whether it succeeded. Records outlive their logs, so history stays inspectable after the logs age out.

suboss87/FDEOps

Command Claude Code

Realize. Promised, measured, accepted.

liorwn/claudetop

Command

Show Claude Code costs per git branch / PR.

liorwn/claudetop

Command

Open the claudetop web dashboard showing spending charts and session history.

s0912758806p/agentic-sop-to-work

Command

Lint a record / dataset / kit run for ALCOA+ data integrity (attribution, contemporaneity, completeness, accuracy, consistency). Deterministic findings + a human-judgment checklist; the report is a DRAFT, the human owns the verdict.

disler/agentic-drop-zones

Command Claude Code

This command analyzes bank statement CSV files, corrects missing or incorrect categorizations, and generates comprehensive spending reports with visual indicators for high spending areas.

agentii-ai/agentii-investment-intelligence

Command

Operational KPI dashboard — headcount trends, utilization rates, backlog/book-to-bill.

paladini/harness-score

Command

Audit this repository's AI harness maturity with the deterministic harness-score scanner.

moedesux/autoresearch-opencode

Command

Start or resume autoresearch experiment loop (optional args: off|dashboard).

mercurialsolo/claudectl

Command

Show or configure auto-generated insights from the claudectl brain — friction patterns, suggested rules, and workflow improvements.

sz8887031-bot/kol-claw

Command Claude Code

A command for analysing influencer data and assigning an advertising rating and suggested price.

mitulgarg/env-doctor

Command

The dashboard and report commands are part of the optional fleet monitoring add-on. The core CLI works without them.

kelviq/tare

Command

Diagnose Claude Code usage — where tokens went and why.

digipulse-engineering/GAAI-framework

Command

Show workspace audit log with filters and optional JSON export.

Dogacel/auto-gpu-kernel

Command Claude Code

Pipe output to a file (e.g. bench.log in repo root) — /log-experiment will attach it.

UiPath/skills

Command Claude Code

Build a Coding-Agents Scorecard Confluence page from two data sources and the canonical product→skill mapping below. Combines test coverage (static) with eval scores + pass/fail (a codereval run), maps both onto the org scorecard's product rows, and publishes a new Confluence page.

amplitude/builder-skills

Command

Delivers a daily briefing of the most important changes across your Amplitude instance. Use when the user asks for a "daily download", "morning briefing", "what's happening", "anything I should know", or wants a summary of recent metric changes, experiments, and user feedback.

amplitude/builder-skills

Command

Delivers a weekly briefing summarizing the most important trends, wins, and risks across your Amplitude instance. Use when the user asks for a "weekly review", "weekly summary", "week in review", "what happened this week", or wants a recap of the past 7 days to share with their team or leadership.

disler/pi-agent-observability

Command Claude Code

Install pi-agent-observability — Bun + SQLite obs server, Pi observability extension, Steelman product-agent demo (Vue/Vite). Checks prerequisites, installs deps across four packages, verifies Pi auth, leaves a runnable system without starting any servers.

ppgranger/token-saver

Command

Show token-saver compression statistics and savings.

Alegau03/CTX

Command

Benchmark | Run a reusable CTX memory benchmark suite.

Mark393295827/third-brain-v7-skills

Command

Estimate, log, and report token usage using runtime-supplied billing rates; never rely on embedded model prices.

xiaolai/nlpm

Command

Render a self-contained HTML report — per-file scores, score trend, cross-artifact graph, vocabulary noun-verb map, drift candidates, and findings — into .claude/nlpm-reports/. Opens directly via file://. No server, no build, no network.