diagnose SKILL.md skillA

diagnose from datit309/supergraph is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add datit309/supergraph/diagnose@git:20260710.bbe810d

Pins git:20260710.bbe810d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
datit309/supergraph
Path
plugins/supergraph/skills/diagnose/SKILL.md
Versions recorded
2
Latest version
git:20260710.bbe810d, committed Jul 10, 2026
First version recorded
Jun 10, 2026
Size
4,088 bytes
Repository stars
21
License
MIT

Structured 6-phase debugging. Build feedback loop first, reproduce deterministically, hypothesize with ranked falsifiable theories, instrument one variable at a time, fix with regression test, cleanup. Use when a bug exists, tests fail unexpectedly, or behavior is wrong and cause is unknown.

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

# /supergraph:diagnose

Systematic debugging. Never guess and patch — build a feedback loop, prove the hypothesis, fix once.

Announce: "🐛 /supergraph:diagnose — building feedback loop..."

## Setup

**Read `.supergraph-env` for test/lint commands (if exists):**
```bash
[ -f .supergraph-env ] && source .supergraph-env
```
This sets `$TEST_CMD`, `$FOCUSED_TEST_CMD`, `$LINT_CMD`. If absent, detect from project config (package.json → jest/vitest, pubspec.yaml → flutter test, etc.) same as `/supergraph:scan`.

## Phases

### Phase 1 — Build Feedback Loop

Before touching any code, establish a fast, deterministic way to observe the bug.

```bash
# Identify the smallest command that shows the failure
$TEST_CMD --grep "<failing test name>"   # focused test run
# or
<minimal repro command>
```

**Goal:** failure visible in < 5 seconds. If not, slim down the repro.
Do NOT skip this phase. Debugging without a feedback loop is guessing.

### Phase 2 — Reproduce Cleanly

- Run the feedback loop 3 times — confirm it fails consistently
- Capture exact error output, stack trace, exit code
- Note any flakiness → treat as separate bug before continuing
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add datit309/supergraph/diagnose@sha256:9955c4191ef005ed

The line at the top of this page pins the label git:20260710.bbe810d, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_cg3rlmpsggxwigcl.svg)](https://markdownregistry.com/a/art_cg3rlmpsggxwigcl)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Jun 10, 2026 and Jul 10, 2026, about one every 30 days.

versioncommittedcommitsizeaudit
git:20260710.bbe810d latest2026-07-10 bbe810d 4,088 BA view · diff
git:20260610.52b7df72026-06-10 52b7df7 3,815 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4088 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

datit309/supergraph · 21 stars · license MIT · pushed 2026-10-22 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_cg3rlmpsggxwigcl
GET https://markdownregistry.com/api/v1/resolve?ref=datit309/supergraph/diagnose
GET https://markdownregistry.com/api/v1/blob/9955c4191ef005ed09d2d1a6a4b50e95c0f4fb0541f9a707e618cd1de22908b8

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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from datit309/supergraph

AGENTS.md@.opencode/plugins/supergraph AGENTS.md file
datit309/supergraph · .opencode/plugins/supergraph/AGENTS.md
git:20260706.3f5d0e0 · audit B · 21 stars
AGENTS.md AGENTS.md file
datit309/supergraph · AGENTS.md
git:20261022.c245456 · audit A · 21 stars
CLAUDE.md CLAUDE.md file
datit309/supergraph · CLAUDE.md
git:20261015.4c65c28 · audit A · 21 stars
AGENTS.md@plugins/supergraph AGENTS.md file
datit309/supergraph · plugins/supergraph/AGENTS.md
git:20261022.c245456 · audit A · 21 stars
CLAUDE.md@plugins/supergraph CLAUDE.md file
datit309/supergraph · plugins/supergraph/CLAUDE.md
git:20261015.4c65c28 · audit A · 21 stars
supergraph SKILL.md skill
datit309/supergraph · plugins/supergraph/SKILL.md · Meta-orchestrator — dispatches to the right skill for the task. Use before any non-trivial work.
git:20261015.757bcde · audit A · 21 stars
analyze SKILL.md skill
datit309/supergraph · plugins/supergraph/skills/analyze/SKILL.md · Risk analysis and approach selection before planning. Use when requirements are ambiguous, approaches vary, or work…
git:20260916.9261b03 · audit A · 21 stars
architecture SKILL.md skill
datit309/supergraph · plugins/supergraph/skills/architecture/SKILL.md · Proactive architecture review — explore codebase structure, generate a self-contained HTML report with Mermaid diagrams…
git:20260826.3720324 · audit A · 21 stars
browser-agent SKILL.md skill
datit309/supergraph · plugins/supergraph/skills/browser-agent/SKILL.md · Autonomous human-like browser control and professional QA/QC testing. Powered by agent-browser (Rust native CDP, zero…
git:20261015.5053f3b · audit C · 21 stars
caveman SKILL.md skill
datit309/supergraph · plugins/supergraph/skills/caveman/SKILL.md · Persistent token-compression mode (~75% reduction) — now always-on by default. Strips filler while keeping code exact.
git:20260827.dce0fb4 · audit A · 21 stars
database-migrations SKILL.md skill
datit309/supergraph · plugins/supergraph/skills/database-migrations/SKILL.md · Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across…
git:20260710.92fdf2f · audit A · 21 stars
design-taste-frontend SKILL.md skill
datit309/supergraph · plugins/supergraph/skills/design-taste-frontend/SKILL.md · Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right…
git:20260916.6b6ff2a · audit B · 21 stars

Every file in datit309/supergraph

Other files named diagnose

diagnose SKILL.md skill
github/awesome-copilot · skills/diagnose/SKILL.md · Perform a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context…
git:20260506.7f59e01 · audit A · 40,226 stars
diagnose SKILL.md skill
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…
git:20260927.6535de7 · audit A · 1,666 stars
diagnose SKILL.md skill
kerberosclaw/kc_ai_skills · diagnose/SKILL.md · Use when the user reports misbehaving software to investigate — a bug, crash, wrong output, flaky behavior, or…
v0.3.0 · audit A · 79 stars
diagnose SKILL.md skill
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…
git:20261010.2b56481 · audit A · 66 stars
diagnose SKILL.md skill
tserentserenov/fmt-exocortex-template · .claude/skills/diagnose/SKILL.md · Диагностика ступени мастерства (Диагност R28, FORM.089 §6.1 v5.0) прямо в VS Code / claude.ai. До 6 вопросов, ~3 мин…
v5.0.0 · audit A · 63 stars
diagnose SKILL.md skill
anantys-oss/koan · koan/skills/core/diagnose/SKILL.md · Analyze the last mission failure and queue a fix attempt
v1.0.0 · audit A · 47 stars
diagnose SKILL.md skill
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…
git:20260816.6ac8364 · audit A · 47 stars
diagnose SKILL.md skill
timharris707/skills · skills/run/diagnose/SKILL.md · The disciplined bug-fixing loop: no fix ships without a cause the fixer can state in one plain sentence, with evidence…
git:20261008.0b04f1c · audit A · 44 stars

Browse by kind, by grade A, or by owner.