Skip to content
Skills Library
Programming · Analysis

trove-debug

/trove-debug

Systematic debugging workflow. Use for bug reports, failing tests, broken behavior, red CI, regressions, or unexplained production symptoms.

Repository
trove ↗
Licence
MIT
Last repository change
08.10.2026

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
2
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 08.10.2026, without references to retired models or APIs.

Licence

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

What to check before installing
  • SKILL.md zawiera komentarze HTML (2). Nie widać ich w podglądzie Markdown, a model je czyta.

What it does and when to use it

Systematic debugging workflow. Use for bug reports, failing tests, broken behavior, red CI, regressions, or unexplained production symptoms.

Original author description

Systematic debugging workflow. Use for bug reports, failing tests, broken behavior, red CI, regressions, or unexplained production symptoms.

How it works

  1. Session Init
  2. Workflow
  3. Root cause, not symptom
  4. Decision Gate: reproduction
  5. Output
Original SKILL.md headings · 44 lines, 356 words
SKILL.md preview
---
name: trove-debug
description: "Systematic debugging workflow. Use for bug reports, failing tests, broken behavior, red CI, regressions, or unexplained production symptoms."
---
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
<!-- Regenerate: bun run build:skills -->

## Session Init

This skill ships Trove conventions. Prefer existing project patterns over generic best practices when they conflict.

If a sibling skill in this plugin matches the request more directly, defer to it. See `AGENTS.md` (or `docs/routing.md` in the marketplace) for the per-plugin routing index.

# trove-debug

Reproduce, narrow, hypothesize, verify - in that order.

## Workflow

1. Capture the observed failure and expected behavior.
2. Reproduce it with the smallest command, test, fixture, or manual path available.
3. Narrow the failing layer by reading code and adding temporary inspection only when needed.
4. State one hypothesis at a time.
5. Apply the smallest fix that addresses the verified cause.
6. Re-run the reproduction and any nearby regression tests.

## Root cause, not symptom

Every step from symptom to cause should trace to runtime evidence (a log line, a value, a failing assertion) — not a guess. When a hypothesis is refuted, revert the probe and try the next one; don't stack guards.

- **Resist the masking guard.** A nil-check or `try/except` that silences a crash without explaining why it was nil is a hidden root cause, not a fix.
- **Restart bugs: suspect state before code.** If a bug only appears after a restart, suspect state, not logic — code doesn't change between runs, state does. If clearing a state file restores behavior, the bug is in how that state is written or validated.
- **Cheap test target?** Hand off to `trove-tdd` to pin the bug with a failing-test-first cadence before fixing.

## Decision Gate: reproduction

Context: A fix without reproduction can mask the bug or create a second one.
Question: Do we have a concrete reproduction?
Options:
- A. Yes - proceed to narrow and fix.
- B. No - create or request a reproduction first.
- C. The issue is intermittent - collect logs or add targeted instrumentation.
Default: B, because verified bugs beat guessed fixes.

## Output

Report the reproduction, root cause, fix, and verification. If verification is partial, say exactly what is still unproven.

Versions

The database has no other skills named trove-debug.

Identical content appears in 3 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version c9c49ae5da3a (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

  • 100debug
    Systematic debugging workflow: reproduce first, write failing test, then fix. Use when encountering bugs, unexplained errors, or unexpected behavior.
  • 100ia-debugging
    Systematic root-cause debugging with verification. Use for errors, stack traces, broken tests, flaky tests, regressions, or anything not working as expected. For validating bug reports before fixing, use bug-reproduction-validator agent.
  • 90debugging
    Systematic root-cause debugging: reproduce, investigate, hypothesize, fix with verification. Use when asked to "debug this", "fix this bug", "why is this failing", "troubleshoot", or mentions errors, stack traces, broken tests, flaky tests, regressions, or unexpected behavior.
  • 100sr-systematic-debugging
    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
  • 100debugging
    Systematic root-cause debugging with verification. Use for errors, stack traces, broken tests, flaky tests, regressions, or anything not working as expected. For validating bug reports before fixing, use bug-reproduction-validator agent.
  • 90adev:debug
    Context-aware systematic debugging. Checks ADRs for known issues, specs for expected behavior, and orientation for architecture context before investigating. Use when encountering any bug, test failure, or unexpected behavior. Trigger on 'fix this', 'fix the bug', 'something is…

Feedback and reports

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