debug SKILL.md skillA

debug from tercel/code-forge is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add tercel/code-forge/debug@git:20260422.d0e053f

Pins git:20260422.d0e053f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
tercel/code-forge
Path
skills/debug/SKILL.md
Versions recorded
5
Latest version
git:20260422.d0e053f, committed Apr 22, 2026
First version recorded
Mar 13, 2026
Size
5,767 bytes
Repository stars
6
License
none declared

Use when encountering any bug, test failure, or unexpected behavior — enforces root cause investigation before fixes. Prevents symptom-fixing, masking bugs, and "just try this" approaches. For code-forge features, use code-forge:fix instead.

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

# Code Forge — Debug

## ⚡ Execution Entry Point

@../shared/execution-entrypoint.md

**For this skill:** start at **the first executable step**. If you catch yourself about to say "falling back to manual debugging", STOP and go to the indicated step.

---

Systematic root cause debugging for any technical issue.

## When to Use

- Any test failure, bug report, or unexpected behavior
- Performance degradation, build failures, integration issues
- ESPECIALLY when under time pressure or when "one quick fix" seems obvious

**For code-forge features:** Use `/code-forge:fix` instead — it adds upstream document tracing and state tracking on top of this methodology.

## Iron Law

**NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.**

No "let me just try this." No "obvious fix." No guessing. Investigate first.

## Workflow

```
Root Cause Investigation → Pattern Analysis → Hypothesis Testing → Implementation (TDD fix)
```

## Phase 0: Understand the Project

Before investigating, build situational awareness of the codebase:

@../shared/project-analysis.md
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add tercel/code-forge/debug@sha256:8071d17d56962e4b

The line at the top of this page pins the label git:20260422.d0e053f, 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_7wcwx2cwljzhu2qn.svg)](https://markdownregistry.com/a/art_7wcwx2cwljzhu2qn)

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

Versions

The registry has recorded 5 versions of this file, between Mar 13, 2026 and Apr 22, 2026, about one every 10 days.

versioncommittedcommitsizeaudit
git:20260422.d0e053f latest2026-04-22 d0e053f 5,767 BA view · diff
git:20260409.eba6a052026-04-09 eba6a05 6,703 BA view · diff
git:20260325.3fb4c8a2026-03-25 3fb4c8a 5,529 BA view · diff
git:20260320.e1d5c1b2026-03-20 e1d5c1b 5,006 BA view · diff
git:20260313.0860d482026-03-13 0860d48 5,012 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 (5767 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

tercel/code-forge · 6 stars · license none declared · pushed 2026-09-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7wcwx2cwljzhu2qn
GET https://markdownregistry.com/api/v1/resolve?ref=tercel/code-forge/debug
GET https://markdownregistry.com/api/v1/blob/8071d17d56962e4b649bcdcdda4ba8471eec59753b7fb36f324ad707a9c9a2e4

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 tercel/code-forge

code-forge SKILL.md skill
tercel/code-forge · SKILL.md · Complete Codex development workflow for turning requirements, feature docs, or prompts into working code. Use when the…
v1 · audit A · 6 stars
finish SKILL.md skill
tercel/code-forge · skills/finish/SKILL.md · Use when implementation is complete and you need to merge, create a PR, or clean up — verifies tests pass, presents 4…
git:20260422.d0e053f · audit A · 6 stars
fix SKILL.md skill
tercel/code-forge · skills/fix/SKILL.md · Use when fixing a DEFECT IN SOURCE CODE — wrong runtime behavior, a crash, a failing test, or the issues listed in a…
git:20260813.bd84674 · audit A · 6 stars
impl SKILL.md skill
tercel/code-forge · skills/impl/SKILL.md · Execute pending tasks for a feature — TDD-driven implementation with sub-agent isolation and progress tracking. Use…
git:20260610.fdf95d5 · audit A · 6 stars
parallel SKILL.md skill
tercel/code-forge · skills/parallel/SKILL.md · Use when facing 2+ independent problems that can be solved concurrently — dispatches one sub-agent per problem domain…
git:20260422.d0e053f · audit A · 6 stars
plan SKILL.md skill
tercel/code-forge · skills/plan/SKILL.md · Analyze documentation (or a prompt) and generate an implementation plan with task breakdown, TDD steps, and progress…
git:20260916.6717348 · audit A · 6 stars
port SKILL.md skill
tercel/code-forge · skills/port/SKILL.md · Port a documentation-driven project to a new target language — initializes project skeleton, analyzes reference…
git:20260422.d0e053f · audit A · 6 stars
review SKILL.md skill
tercel/code-forge · skills/review/SKILL.md · Use ONLY when reviewing SOURCE CODE — a code change, a feature implementation, a whole repository, or a GitHub pull…
git:20260820.fc44708 · audit A · 6 stars
status SKILL.md skill
tercel/code-forge · skills/status/SKILL.md · Display code-forge feature dashboard with task-level progress from state.json, or show detailed status for a specific…
git:20260610.16e086f · audit A · 6 stars
tdd SKILL.md skill
tercel/code-forge · skills/tdd/SKILL.md · Use when implementing any feature or fix outside code-forge workflow — enforces Red-Green-Refactor cycle with mandatory…
git:20260422.d0e053f · audit A · 6 stars
verify SKILL.md skill
tercel/code-forge · skills/verify/SKILL.md · Use before claiming ENGINEERING WORK is done, fixed, or passing — work whose correctness a command can demonstrate…
git:20260813.bd84674 · audit A · 6 stars
worktree SKILL.md skill
tercel/code-forge · skills/worktree/SKILL.md · Use when starting feature work that needs workspace isolation — creates git worktree with automatic project setup and…
git:20260422.d0e053f · audit A · 6 stars

Every file in tercel/code-forge

Other files named debug

debug SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/debug/SKILL.md · Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction
git:20260925.570ed1c · audit A · 40,624 stars
debug SKILL.md skill
nanocoai/nanoclaw · .claude/skills/debug/SKILL.md · Debug container agent issues. Use when things aren't working, container fails, authentication problems, or to…
git:20261022.0474572 · audit B · 31,085 stars
debug SKILL.md skill
agentic-community/mcp-gateway-registry · .claude/skills/debug/SKILL.md · Debug issues in the MCP Gateway Registry using first-principles thinking. Invoke when something is broken, timing out…
v1.0 · audit A · 1,038 stars
debug SKILL.md skill
suboss87/fdeops · skills/debug/SKILL.md · Investigate a failure, regression or incorrect result in an integration or application, even before it can be…
git:20261005.ed7f271 · audit A · 827 stars
debug SKILL.md skill
rsmdt/the-startup · plugins/start/skills/debug/SKILL.md · Systematically diagnose and resolve bugs through conversational investigation and root cause analysis
git:20261011.48bd3ee · audit A · 577 stars
debug SKILL.md skill
me2resh/apexyard · .claude/skills/debug/SKILL.md · Hypothesis-driven debugging — architecture-first reading + evidence-before-fix. For bugs that resisted naïve fix…
git:20261015.37f5689 · audit A · 542 stars
debug SKILL.md skill
ericrisco/rsc-harness · skills/debug/SKILL.md · Use when something is broken — a failing or flaky test, crash, wrong result or regression — and the root cause must be…
git:20261103.e41612d · audit A · 505 stars
debug SKILL.md skill
fcakyon/labrat · plugin/skills/debug/SKILL.md · Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list…
git:20260430.e4e97e0 · audit A · 452 stars

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