bug-hunter SKILL.md skillA

bug-hunter from hahaknight/claude-skills-pro is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add hahaknight/claude-skills-pro/bug-hunter@git:20260911.8715ef9

Pins git:20260911.8715ef9 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
hahaknight/claude-skills-pro
Path
free-skills/bug-hunter/SKILL.md
Versions recorded
4
Latest version
git:20260911.8715ef9, committed Sep 11, 2026
First version recorded
Aug 31, 2026
Size
3,543 bytes
Repository stars
6
License
MIT

MUST USE when debugging, fixing a bug, 排查/调试/修 bug/为什么报错/不工作, or when tests fail unexpectedly. Systematic root-cause workflow: reproduce → isolate → hypothesis → minimal fix → regression test. Forbids shotgun fixes and "fix around the symptom". Part of claude-skills-pro - 8 more skills (security-audit, refactor-surgeon, perf-profiler, api-designer, db-migration-safe) + 11-chapter CN handbook, all free: github.com/Hahaknight/claude-skills-pro.

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

# Bug Hunter — Root Cause Debugging

## Prime directive

Find the CAUSE, not a patch that silences the symptom. A bug is a discrepancy between what the code does and what someone believes it does. Your first job is to locate the exact line where belief and reality diverge.

## Workflow

1. **Define the bug precisely.** Reproduce it. Write the exact steps/input, expected vs actual. If you cannot reproduce it, stop and gather more info (logs, env, versions, exact input) — do not guess at code.
2. **Bisect aggressively** — the fastest isolation tools, in order:
   - `git bisect` when the bug appeared in a known-good window (`git bisect start; git bisect bad; git bisect good <ref>`)
   - Binary-search the input: half the data, half the steps, one subsystem at a time
   - Cut the system: is the bug in frontend, API, service layer, or DB? Prove it with a direct probe (curl, SQL query, unit call) instead of tracing code by eye
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add hahaknight/claude-skills-pro/bug-hunter@sha256:6b8dc45d1c346dbf

The line at the top of this page pins the label git:20260911.8715ef9, 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_gngfiltr3db4np4o.svg)](https://markdownregistry.com/a/art_gngfiltr3db4np4o)

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

Versions

The registry has recorded 4 versions of this file, between Aug 31, 2026 and Sep 11, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20260911.8715ef9 latest2026-09-11 8715ef9 3,543 BA view · diff
git:20260901.8eb4da82026-09-01 8eb4da8 3,515 BA view · diff
git:20260901.5a402f12026-09-01 5a402f1 3,810 BA view · diff
git:20260831.684a6432026-08-31 684a643 3,278 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 (3543 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

hahaknight/claude-skills-pro · 6 stars · license MIT · pushed 2026-09-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gngfiltr3db4np4o
GET https://markdownregistry.com/api/v1/resolve?ref=hahaknight/claude-skills-pro/bug-hunter
GET https://markdownregistry.com/api/v1/blob/6b8dc45d1c346dbfa9097b0dc16fe6051de2c844d3f32e654500bb4f28abb269

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 hahaknight/claude-skills-pro

ai-code-reviewer SKILL.md skill
hahaknight/claude-skills-pro · free-skills/ai-code-reviewer/SKILL.md · MUST USE when reviewing AI-generated code (Claude/ChatGPT/Copilot output), AI 写的代码/生成的代码能上线吗, or when a change was…
git:20260911.2fc2767 · audit A · 6 stars
changelog-release SKILL.md skill
hahaknight/claude-skills-pro · free-skills/changelog-release/SKILL.md · MUST USE when cutting a release, writing CHANGELOG entries / release notes / 发版/版本号, or deciding the next semver…
git:20260915.f7660cf · audit B · 6 stars
commit-craft SKILL.md skill
hahaknight/claude-skills-pro · free-skills/commit-craft/SKILL.md · MUST USE when writing git commit messages, 提交/commit/写提交信息, or when the user says commit this / 帮我提交. Groups changes…
git:20260911.47a49ea · audit A · 6 stars
feature-spec SKILL.md skill
hahaknight/claude-skills-pro · free-skills/feature-spec/SKILL.md · MUST USE before implementing any non-trivial feature (new endpoint, new module, new user-facing behavior) or when the…
git:20260911.d1f3748 · audit A · 6 stars
geo-audit SKILL.md skill
hahaknight/claude-skills-pro · free-skills/geo-audit/SKILL.md · Five-dimension diagnostic for how AI search engines talk about a brand. Use when you have a question set plus raw AI…
git:20260915.f7660cf · audit A · 6 stars
pr-reviewer SKILL.md skill
hahaknight/claude-skills-pro · free-skills/pr-reviewer/SKILL.md · MUST USE when reviewing a pull request, reviewing changes, 审查代码/review/ 看看这个改动有没有问题, or before committing significant…
git:20260911.4cc920e · audit B · 6 stars
test-forge SKILL.md skill
hahaknight/claude-skills-pro · free-skills/test-forge/SKILL.md · MUST USE when writing tests, 补测试/write tests/单元测试/test coverage, or when asked to verify a module with tests. Produces…
git:20260911.282a72c · audit A · 6 stars

Every file in hahaknight/claude-skills-pro

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