Skip to content
Skills Library
Programming · Testing

dte-debug

/dte-debug

Track a bug to its ROOT CAUSE and fix it once where all callers route — for a failing test, an exception, a wrong result, or flaky behavior. Composes ce-debug (root-cause hypothesis loop), majestic rails-debugger, Augment for tracing call paths, AppSignal for production error context, and a runnable repro before and after the fix. Use when the user says "debug this", "why is this failing/broken", "fix this bug", "this exception", "find the root cause", or "this test is flaky". Loops over a list of bugs. Not for a broad code review (use dte-deep-reviewer) or a planned feature (use dte-feature).

Repository
dte-skills ↗
Licence
MIT
Last repository change
13.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 13.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Track a bug to its ROOT CAUSE and fix it once where all callers route — for a failing test, an exception, a wrong result, or flaky behavior. Composes ce-debug (root-cause hypothesis loop), majestic rails-debugger, Augment for tracing call paths, AppSignal for production error context, and a runnable repro before and after the fix. Use when the user says "debug this", "why is this failing/broken", "fix this bug", "this exception", "find the root cause", or "this test is flaky". Loops over a list of bugs. Not for a broad code review (use dte-deep-reviewer) or a planned feature (use dte-feature).

Triggers from the description

debug thiswhy is this failing/brokenfix this bugthis exceptionfind the root causethis test is flaky
Original author description

Track a bug to its ROOT CAUSE and fix it once where all callers route — for a failing test, an exception, a wrong result, or flaky behavior. Composes ce-debug (root-cause hypothesis loop), majestic rails-debugger, Augment for tracing call paths, AppSignal for production error context, and a runnable repro before and after the fix. Use when the user says "debug this", "why is this failing/broken", "fix this bug", "this exception", "find the root cause", or "this test is flaky". Loops over a list of bugs. Not for a broad code review (use dte-deep-reviewer) or a planned feature (use dte-feature).

How it works

  1. Input
  2. Procedure (per bug)
  3. For a list of bugs
  4. Degrade gracefully
  5. Done when
Original SKILL.md headings · 40 lines, 437 words
SKILL.md preview
---
name: dte-debug
description: Track a bug to its ROOT CAUSE and fix it once where all callers route — for a failing test, an exception, a wrong result, or flaky behavior. Composes ce-debug (root-cause hypothesis loop), majestic rails-debugger, Augment for tracing call paths, AppSignal for production error context, and a runnable repro before and after the fix. Use when the user says "debug this", "why is this failing/broken", "fix this bug", "this exception", "find the root cause", or "this test is flaky". Loops over a list of bugs. Not for a broad code review (use dte-deep-reviewer) or a planned feature (use dte-feature).
---

# dte-debug — reproduce → root cause → fix once → prove it

Read `../../references/conventions.md` first (looping, **Runnable gate**, **Verify don't advise**). This
skill **finds the cause, not the symptom**, and fixes it where every caller routes through — the lazy fix
is the root-cause fix. It composes the debug tools; it does not patch the path the ticket names and walk away.

## Input
- A bug: a failing test, a stack trace/exception, a wrong output, or flaky behavior. Get a repro if missing.
- Or a **list** of bugs → handle each (serial by default — bugs in shared code interact).
- Read the project `CLAUDE.md`/`AGENTS.md`; honor interactors-not-services + the test framework.

## Procedure (per bug)
1. **Reproduce first.** Make it fail on demand — a failing test (write the smallest one if none exists), a
   console repro, or the exact request. **No repro → say so and stop guessing.** This same repro proves the
   fix at the end.
2. **Gather context.** Map the failing path with Augment `codebase-retrieval`. If it's a production error,
   pull **AppSignal** (backtrace, frequency, recent deploys, params). Read the actual flow end to end.
3. **Find the root cause.** Run **`ce-debug`** (hypothesis → test → narrow loop) and/or majestic
   **`rails-debugger`**. **Grep every caller** of the function you suspect — the bug usually lives in the
   shared function, and the report only named one symptom. Name the cause in one line before editing.
4. **Fix once, at the cause.** One guard/fix in the shared path beats a guard in every caller — and patching
   only the named path leaves sibling callers broken. Follow existing patterns; interactors not services.
5. **Prove it.** Re-run the step-1 repro → must pass. Run the project **gate** (tests + boot/eager-load
   check) → green. Add/keep a regression test that fails without the fix. A fix you can't demonstrate failing
   before and passing after is **not done**.

## For a list of bugs
One sub-agent per bug through 1–5 (serial by default), then a roll-up noting each bug's root cause, the
shared-path fix, and any sibling callers that were also affected. Report + pause per bug.

## Degrade gracefully
- No ce-debug → drive the hypothesis loop manually (bisect, log, narrow), note it.
- No AppSignal → use logs/local repro for production bugs, note production context unavailable.

## Done when
Each bug has a **runnable repro** that failed before and passes after, the **root cause named** (not just
the symptom), the fix applied **once at the shared path** with all callers checked, a regression test, and
a **green gate**. Surfaced (not silently): any caller you couldn't fix in scope.

Versions

The database has no other skills named dte-debug.

Database snapshot: 13.11.2026 · package version 79561e75edf0 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90dte-perf
    Performance review of a Rails app, endpoint, query, job, or front-end page — find the real bottlenecks (N+1s, missing indexes, slow queries, fat allocations, slow front-end paint/bundle) with measured evidence, and propose ranked fixes. Composes majestic performance-reviewer +…
  • 92debug
    Find the root cause of a bug before you fix it. Read this skill before you fix any bug. Read it also when the fix looks obvious. Use it when the user says "fix", "broken", "not working", "error", "failing", or "bug". Use it also when a test fails unexpectedly during other work.
  • 90dte-arc-review
    Architectural review of a Rails app, a subsystem, or a vertical slice, producing a written findings doc. Composes Augment context retrieval, layered-rails analyzers, expectation-fit audit, majestic Rails reviewers, and a ponytail over-engineering pass into one severity-ranked…
  • 100ra-systemic-debug
    Systemic multi-hop root-cause debugger that fixes bugs from the upstream root cause and strictly bans symptom band-aids. Use when the user says "debug this", "diagnose", "fix this bug", or reports something broken, regressing, stuck, or failing.
  • 90debug
    Find the root cause of a bug, failing test, crash, flaky test, slow regression or production incident before fixing it, then fix and prove it. Use when something is broken, intermittent, slow or down, or a fix did not work. Not for reviewing code that works (lll:review), deep…
  • 100claude-debug
    Send a bug or failing test to Claude Code for root-cause analysis and fix. Use when you've hit an error you can't trace, a test is failing for unclear reasons, or a behavior is wrong and the cause is deep in the codebase.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.