Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Diagnose
A discipline for hard bugs. Skip phases only when explicitly justified.
When exploring the codebase, use the project's domain glossary to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.
## Phase 1 — Build a feedback loop
**This is the skill.** Everything else is mechanical. If you have a fast, deterministic, agent-runnable pass/fail signal for the bug, you will find the cause — bisection, hypothesis-testing, and instrumentation all just consume that signal. If you don't have one, no amount of staring at code will save you.
Spend disproportionate effort here. **Be aggressive. Be creative. Refuse to give up.**
### Ways to construct one — try them in roughly this order
1. **Failing test** at whatever seam reaches the bug — unit, integration, e2e.
2. **Curl / HTTP script** against a running dev server.
3. **CLI invocation** with a fixture input, diffing stdout against a known-good snapshot.
4. **Headless browser script** (Playwright / Puppeteer) — drives the UI, asserts on DOM/console/network.
…
The line at the top of this page pins the label git:20260502.38d5305, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_u35kagi3tcmh5xrx
GET https://markdownregistry.com/api/v1/resolve?ref=vodailocz/kilo-kit-mcp/diagnose
GET https://markdownregistry.com/api/v1/blob/28886402bbfa0470248086eab9106a103b964b76ae9496e63ff0c8a6761b6d13
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
vodailocz/kilo-kit-mcp · skills/agent-frameworks/agent-memory/SKILL.md · Use when implementing or managing persistent, hierarchical memory systems for AI agents. Covers cross-session state…
vodailocz/kilo-kit-mcp · skills/agent-frameworks/mcp-agent-patterns/SKILL.md · Use when integrating or optimizing Model Context Protocol (MCP) servers and clients. Keywords: MCP, Model Context…
vodailocz/kilo-kit-mcp · skills/agent-frameworks/workflow-state-machines/SKILL.md · Use when designing, implementing, or debugging complex agentic workflows using state machine patterns. Keywords: state…
vodailocz/kilo-kit-mcp · skills/ai-media/ai-multimodal/SKILL.md · Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files…
vodailocz/kilo-kit-mcp · skills/ai-media/screenshot/SKILL.md · Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel…
github/awesome-copilot · skills/diagnose/SKILL.md · Perform a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context…
pedrohcgs/claude-code-my-workflow · .claude/skills/diagnose/SKILL.md · Root-cause a failing or wrong empirical result with a disciplined reproduce → minimise → hypothesise → instrument → fix…
kerberosclaw/kc_ai_skills · diagnose/SKILL.md · Use when the user reports misbehaving software to investigate — a bug, crash, wrong output, flaky behavior, or…
skillberry-ai/cap-evolve · skills/phases/diagnose/SKILL.md · Extract the learning signal from execution traces — the textual analogue of a gradient. Use between evaluation and…
mycelium-hq/ai-brain-starter · skills/diagnose/SKILL.md · Use when an AI Brain vault needs a health check or something feels off: Claude ignores CLAUDE.md, journal entries…
