Diagnosing Bugs
A discipline for hard bugs and perf regressions: build a feedback loop first, bisect, instrument, redact secrets
- What
- A discipline for hard bugs and perf regressions: build a feedback loop first, bisect, instrument, redact secrets
- Cost
- Free
- Needs
- an AI agent harness (Claude Code, Codex, Pi, Antigravity, Hermes, or Muse) with access to your repo and its test/build tooling
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — the craft lesson distilled to one line: "if you have a tight pass/fail signal, you will find the cause; without one, no amount of staring at code will save you." Phase 1 is always building a feedback loop (a failing test, a curl, a CLI invocation); then bisection to narrow, instrumentation to see, and redaction of secrets (<REDACTED>) before showing any outputs to a human. Skip phases only when explicitly justified. Distinct from obra's systematic-debugging (lot 34, four-phase root-cause process): this one is the "tight signal" discipline for hard bugs and performance regressions. Also distinct from the stale `diagnose` skill dropped in lot 33 — different id, repo path, and content; the word "diagnose" in its description is just a trigger keyword. By @mattpocock, listed here with credit to its creator. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Diagnosing Bugs is a free Muse skill offering a discipline for hard bugs and performance regressions: build a feedback loop first, bisect, instrument and redact secrets. Its craft lesson: with a tight pass-or-fail signal you will find the cause, and without one, no amount of staring at code will save you, so phase one always builds a feedback loop.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 49dd158Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: an AI agent harness (Claude Code, Codex, Pi, Antigravity, Hermes, or Muse) with access to your repo and its test/build tooling Install "Diagnosing Bugs" for me. A discipline for hard bugs and perf regressions: build a feedback loop first, bisect, instrument, redact secrets Repository: https://raw.githubusercontent.com/mattpocock/skills/49dd158d1076134a641b33efb035946536778336/skills/engineering/diagnosing-bugs/SKILL.md Pinned version: install the code at commit 49dd158d1076134a641b33efb035946536778336 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file for the mattpocock-diagnosing-bugs skill from the repository into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "mattpocock-diagnosing-bugs". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. any accounts, API keys, or CLI tools mentioned in the prerequisites above). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. Never ask me to paste secrets in chat — credentials go through the secure vault or environment variables. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 49dd158 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.