skills.rest
hirokimry
hirokimryCOMMUNITY
Explore all skills by this author →
Website𝕏@hirokimryGitHub

cycle-metrics

Measure issue cycle time, token usage, and delivery bottlenecks from GitHub PR timelines.

1|Updated Mar 20, 2026
Search Tags:#claude code#issue tracking#token analysis#workflow analytics#github pr#cycle metrics
One-click install
npx skills add https://github.com/hirokimry/vibecorp --skill cycle-metrics
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cycle-metrics
Source: https://github.com/hirokimry/vibecorp/tree/main/skills/cycle-metrics
Command: npx skills add https://github.com/hirokimry/vibecorp --skill cycle-metrics

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the guesswork from understanding how long an issue cycle takes, how much token budget it consumes, and where delivery slows down across recent ship runs.

Core Features & Use Cases

  • Issue cycle timing: Measures end-to-end PR cycle time, first review latency, and CI duration from merged PR history.
  • Agent activity analysis: Aggregates Claude Code session logs by branch to summarize token usage, sidechain calls, and subagent activity.
  • Report generation: Produces a markdown report in the vibecorp cache so the data can be consumed later without polluting knowledge storage.
  • Use case: A team lead can review the latest full preset cycles to find whether review wait time or CI time is the main bottleneck before changing workflow rules.

Quick Start

Ask the AI to run cycle-metrics for the latest full preset issue cycles and save the generated report to the vibecorp cache path.

Frequently Asked Questions about cycle-metrics

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I measure issue cycle time and token usage from GitHub PR history?▼

Issue cycle time and token usage are measured by analyzing merged GitHub PR timelines alongside local JSONL session logs to calculate end-to-end delivery duration and agent token consumption. The Skill aggregates this data to identify workflow bottlenecks across recent ship cycles.

Can I analyze Claude Code session logs to find delivery bottlenecks in my repositories?▼

Claude Code session logs are analyzed by aggregating branch-level token usage, sidechain calls, and subagent activity to pinpoint delivery bottlenecks. It processes local JSONL logs from completed issue-to-PR runs to summarize where workflow cycles slow down.

What is the best way to track first review latency and CI duration for merged PRs?▼

First review latency and CI duration are tracked by extracting timing data from merged GitHub PR history. The Skill calculates these specific intervals to help team leads determine whether review wait time or CI time is the primary workflow bottleneck.

Do I need GitHub CLI access to generate workflow analytics reports?▼

GitHub CLI access is required to retrieve PR timeline data for workflow analytics. The Skill uses GitHub CLI to pull merged PR history and combines it with local JSONL session logs to generate a markdown report saved in the cache.

How does cycle-metrics generate reports without invoking a headless Claude instance?▼

Reports are generated through cache-based markdown creation without invoking headless Claude. The Skill processes GitHub PR timelines and Claude Code session logs directly to produce a markdown file in the vibecorp cache for later consumption.

Are there limitations when analyzing subagent activity across recent ship cycles?▼

Subagent activity analysis is limited to data available in local JSONL session logs and GitHub PR history. It requires completed issue-to-PR runs and cannot analyze incomplete cycles or sessions where local logs are unavailable.

Related Skills

Explore More Data & Analytics Skills→
maxvaegamaxvaega
38

cost

Parse local JSONL transcript logs to estimate pay-per-token API costs in USD and EUR.

Community
Intermediate
X-McKayX-McKay
3

get-capacity-recommendations

Analyze Kubernetes cluster capacity and forecast future resource needs.

Community
Intermediate
tombeliebertombelieber
101

daily-cost

Monitor daily Claude Code spending with aggregate and per-session cost breakdowns.

Community
Intermediate
cody-hutsoncody-hutson

context-budget-auditor

Monitors and reports token consumption for Claude Code sessions, flagging bloated components exceeding thresholds.

Community
Intermediate