Home / cercano-ai / cercano · GitHub

systematic-debugging SKILL.md skillA

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

systematic-debugging from cercano-ai/cercano is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add cercano-ai/cercano/systematic-debugging@git:20260709.887cd3f

Pins git:20260709.887cd3f in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: cercano-ai/cercano
Path: .claude/skills/systematic-debugging/SKILL.md
Versions recorded: 1
Latest version: git:20260709.887cd3f, committed Jul 9, 2026
Size: 3,975 bytes
Repository stars: 11
License: Apache-2.0

Reduce, observe, reason, predict, probe, then fix — no guessing.

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

# Systematic Debugging Protocol

You are now operating under Dave's debugging protocol. This is not optional guidance — it is the mandatory sequence for investigating any failure. Agents who skip steps reliably produce wrong fixes that waste time and create new bugs.

## The Protocol

Every debug cycle follows this sequence. No skipping steps.

### 1. REDUCE

Before tracing anything, reduce to the **smallest case that still fails**.

- Remove variables one at a time until you find the one that matters
- If a complex test fails, try the simplest version first
- If multiple things are broken, isolate one failure before investigating
- The dimension you add back that triggers the failure is where the bug lives

If the minimal case passes, use **divergence-point analysis**: compare the passing case against the failing case signal-by-signal, log-by-log, output-by-output. The first thing that diverges is closest to root cause.

### 2. OBSERVE

What does the data show? Not what you think should happen — what **actually** happens.

- List specific values, states, outputs at specific points
- Cover ALL relevant signals/variables, not just the one that looks wrong
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add cercano-ai/cercano/systematic-debugging@sha256:307a58b3207f8ece

The line at the top of this page pins the label git:20260709.887cd3f, 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](https://markdownregistry.com/badge/art_kp7yd4pwtxl4k24j.svg)](https://markdownregistry.com/a/art_kp7yd4pwtxl4k24j)

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

Versions

The registry has recorded 1 version of this file, committed on Jul 9, 2026.

version	committed	commit	size	audit
git:20260709.887cd3f latest	2026-07-09	887cd3f	3,975 B	A	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 (3975 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

cercano-ai/cercano · 11 stars · license Apache-2.0 · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_kp7yd4pwtxl4k24j
GET https://markdownregistry.com/api/v1/resolve?ref=cercano-ai/cercano/systematic-debugging
GET https://markdownregistry.com/api/v1/blob/307a58b3207f8ecefbdde12530ee3695869aac5d98da3e2a5c9ce2a77e62ccdc

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 cercano-ai/cercano

cercano-classify SKILL.md skill

cercano-ai/cercano · .agents/skills/cercano-classify/SKILL.md · Classify or triage text using the configured model route via Cercano. Returns a category, confidence level, and brief…