kamkate

Dev Team Maturity Performance Skills — Data skill for Claude Code

Data community

Governed Claude Agent Skills for engineering delivery maturity analysis: deterministic KPIs, rule-based pattern detection, and catalog-only intervention recommendations from Jira data.

How to install Dev Team Maturity Performance Skills

This entry records only its repository, not the path inside it, so there is no exact command to give. Open kamkate/dev-team-maturity-performance-skills and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Dev Team Maturity Performance Skills does

Governed Claude Agent Skills for engineering delivery maturity analysis: deterministic KPIs, rule-based pattern detection, and catalog-only intervention recommendations from Jira data.

Alternatives in Data

  • Context Mode — Benchmark Results — Benchmarked against real outputs from popular Claude Code MCP servers, Skills, and dev tools 5.6k ★
  • LLM Redteam — LLM red-team corpus runner — fires categorized prompt-injection / jailbreak / system-prompt-leak / data-exfil 4.5k ★
  • Pipeline Feature — Add a feature to the FFmpeg transcode pipeline following Tunarr's pipeline builder pattern 2.5k ★

README

Dev Team Maturity & Performance — Claude Skills

[![Claude Skill](https://img.shields.io/badge/Claude-Agent%20Skill-D97757?logo=anthropic&logoColor=white)](https://docs.claude.com/en/docs/claude-code/skills) [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)

Three [Claude Agent Skills](https://docs.claude.com/en/docs/claude-code/skills) that turn a raw Jira export into a governed, explainable engineering-maturity analysis — no dashboards, no BI setup, no spreadsheet gymnastics. Point Claude at your data and ask.

Built as part of an MBA thesis prototype on AI-assisted engineering management. The skills are generic and reusable — no organization-specific data is included in this repo.


The problem

Engineering leaders are asked "how healthy is this team, really?" constantly, and usually answer it with one of three unsatisfying options:

  • Gut feel — whoever talks to the team most often sets the narrative
  • A BI dashboard someone built eighteen months ago that nobody trusts or maintains
  • A one-off spreadsheet pull that takes an afternoon and goes stale the moment the sprint ends

None of these hold up when a board, a VP, or a thesis committee asks "show me the evidence." And when an LLM is dropped in to "just analyze the Jira data," it tends to invent plausible-sounding numbers when fields are missing, and invents interventions that sound reasonable but aren't grounded in anything repeatable.

How this solves it

These three skills turn that into a governed, repeatable workflow:

  1. maturity-onboarding — a one-time (or per-change) setup wizard that captures how your organization actually tracks work in Jira, and produces versioned config files.
  2. maturity-engine — reads those config files plus your Jira export and produces a maturity report: facts (computed KPIs), signals (rule-based patterns), and interventions (from a fixed catalog) — never blended together, never invented.
  3. **`matu