hl-debug SKILL.md skillA

hl-debug from hugolopes45/hl-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add hugolopes45/hl-skills/hl-debug@git:20261023.8a53261

Pins git:20261023.8a53261 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
hugolopes45/hl-skills
Path
skills/hl-debug/SKILL.md
Versions recorded
4
Latest version
git:20261023.8a53261, committed Oct 23, 2026
First version recorded
Oct 13, 2026
Size
13,657 bytes
Repository stars
2
License
MIT

Investigate a bug by first building a fast feedback loop that shows the symptom, then running discriminating experiments, and report the supported hypotheses or the defect proven by toggling it. Fixes only when asked, behind a failing regression test. Use when something fails (including a named test the user asks you to explain), behaves unexpectedly, is flaky, or got slower and the cause is unknown. Not for fixing failing pull request checks (use `hl-ci-fix`).

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

# Debug

Input: `[bug description or report path]`

Rules for every mode, including referenced instructions:

Do not retry a permission-denied action through another command, tool, path, or environment. Report the blocker.

Ground factual claims in supplied evidence or results you observed in this session.
- Take line numbers from numbered reads, not list-item numbers. Copy hashes, quotes, and errors exactly; verify stated counts.
- Report each check's command, directory, and actual execution count. Count runs, not tool calls or test cases; include failures, exclude denied attempts. Reconcile counts with observed results.
- Report another agent's findings only after its result returns and you check them.
- Separate observations, inferences, and estimates. An outside fact without a checked source is unverified, not an estimate.
- Scope all, only, and none to what you checked. A code-backed prediction is not an observed run.
- Missing evidence: say what is unknown. Name a file or function instead of inventing a line number.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add hugolopes45/hl-skills/hl-debug@sha256:10aa5884828d55e2

The line at the top of this page pins the label git:20261023.8a53261, 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_kb3vgsrs4qygfqia.svg)](https://markdownregistry.com/a/art_kb3vgsrs4qygfqia)

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

Versions

The registry has recorded 4 versions of this file, between Oct 13, 2026 and Oct 23, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20261023.8a53261 latest2026-10-23 8a53261 13,657 BA view · diff
git:20261013.5d39ecd2026-10-13 5d39ecd 12,176 BA view · diff
git:20261013.c2321782026-10-13 c232178 12,132 BA view · diff
git:20261013.59162d22026-10-13 59162d2 7,562 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 (13657 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

hugolopes45/hl-skills · 2 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_kb3vgsrs4qygfqia
GET https://markdownregistry.com/api/v1/resolve?ref=hugolopes45/hl-skills/hl-debug
GET https://markdownregistry.com/api/v1/blob/10aa5884828d55e208a3cd6ae584bf207b748b155654ff8ab86c22edee0e2704

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 hugolopes45/hl-skills

CLAUDE.md@evals/checkpoint/files/with-rule CLAUDE.md file
hugolopes45/hl-skills · evals/checkpoint/files/with-rule/CLAUDE.md
git:20261013.59162d2 · audit B · 2 stars
AGENTS.md@evals/lessons/files/covered AGENTS.md file
hugolopes45/hl-skills · evals/lessons/files/covered/AGENTS.md
git:20261013.59162d2 · audit B · 2 stars
AGENTS.md@evals/lessons/files/mechanical AGENTS.md file
hugolopes45/hl-skills · evals/lessons/files/mechanical/AGENTS.md
git:20261013.59162d2 · audit B · 2 stars
AGENTS.md@evals/routing/files/mechanical AGENTS.md file
hugolopes45/hl-skills · evals/routing/files/mechanical/AGENTS.md
git:20261013.59162d2 · audit B · 2 stars
commit SKILL.md skill
hugolopes45/hl-skills · evals/writing-for-agents/files/skill-new/skills/commit/SKILL.md · Write a conventional commit message for the staged changes and commit them. Use only when the user explicitly asks to…
git:20261013.59162d2 · audit A · 2 stars
commit SKILL.md skill
hugolopes45/hl-skills · evals/writing-for-agents/files/skill-overlap/skills/commit/SKILL.md · Write a conventional commit message for the staged changes and commit them. Use only when the user explicitly asks to…
git:20261013.59162d2 · audit A · 2 stars
hl-adr SKILL.md skill
hugolopes45/hl-skills · skills/hl-adr/SKILL.md · Draft an architecture decision record (ADR): context, options actually considered, decision, consequences, and reversal…
git:20261023.8a53261 · audit A · 2 stars
hl-ambitious SKILL.md skill
hugolopes45/hl-skills · skills/hl-ambitious/SKILL.md · Raise a task's standard, not its scope. Explain the expert move, primary material, concrete methods and tools borrowed…
git:20261023.48ea5fe · audit A · 2 stars
hl-challenge SKILL.md skill
hugolopes45/hl-skills · skills/hl-challenge/SKILL.md · Test a plan, decision, design, or just-finished work against its goal and agreed reference, using code, evidence, and…
git:20261023.8a53261 · audit A · 2 stars
hl-checkpoint SKILL.md skill
hugolopes45/hl-skills · skills/hl-checkpoint/SKILL.md · Before clearing or compacting the conversation context, check that decisions, evidence, pending work, and the next…
git:20261023.8a53261 · audit A · 2 stars
hl-ci-fix SKILL.md skill
hugolopes45/hl-skills · skills/hl-ci-fix/SKILL.md · Diagnose failing required checks on a pull request and apply bounded fixes without weakening tests or CI policy. Use…
git:20261023.8a53261 · audit A · 2 stars
hl-code-review SKILL.md skill
hugolopes45/hl-skills · skills/hl-code-review/SKILL.md · Review a diff (current branch, pull request, ref range, tag, or commit) statically at a known revision, with location…
git:20261026.3911d7c · audit A · 2 stars

Every file in hugolopes45/hl-skills

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