trove-debug
/trove-debug
Systematic debugging workflow. Use for bug reports, failing tests, broken behavior, red CI, regressions, or unexplained production symptoms.
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 2
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 08.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- 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
- Session Init
- Workflow
- Root cause, not symptom
- Decision Gate: reproduction
- Output
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…