debug-sop
/debug-sop
Diagnose errors, failed tests, crashes, hangs, regressions, suspicious outputs, and unexpected experimental results through reproducible hypothesis-driven debugging. Use whenever a script or system behaves incorrectly, even if the user only says it is broken or pastes an error. Respect diagnosis-only requests; implement a fix only when authorized.
- Author
- whenpoem ↗
- Repository
- aiscientist ↗
- Licence
- MIT
- Last repository change
- 09.10.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 09.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Diagnose errors, failed tests, crashes, hangs, regressions, suspicious outputs, and unexpected experimental results through reproducible hypothesis-driven debugging. Use whenever a script or system behaves incorrectly, even if the user only says it is broken or pastes an error. Respect diagnosis-only requests; implement a fix only when authorized.
Original author description
Diagnose errors, failed tests, crashes, hangs, regressions, suspicious outputs, and unexpected experimental results through reproducible hypothesis-driven debugging. Use whenever a script or system behaves incorrectly, even if the user only says it is broken or pastes an error. Respect diagnosis-only requests; implement a fix only when authorized.
How it works
- Inputs and output
- 1. Recover history before guessing
- 2. Reproduce and bound the failure
- 3. Build and eliminate hypotheses
- 4. Isolate the root cause
- 5. Fix only when authorized
- 6. Verify proportionally
- 7. Record the failure
- Recovery branches
- Completion criteria
SKILL.md preview
--- name: debug-sop description: Diagnose errors, failed tests, crashes, hangs, regressions, suspicious outputs, and unexpected experimental results through reproducible hypothesis-driven debugging. Use whenever a script or system behaves incorrectly, even if the user only says it is broken or pastes an error. Respect diagnosis-only requests; implement a fix only when authorized. --- # Debug SOP ## Inputs and output Capture the exact symptom, expected behavior, reproduction command, relevant inputs, environment, first known bad state, and whether fixing is authorized. Return a compact incident report with reproduction, root cause or surviving hypotheses, evidence, changed files if any, verification commands, and the failure-ledger id. ## 1. Recover history before guessing 1. Call `mcp__memory__match_signatures` with the exact error plus the operation that triggered it. Read matching resolutions, but verify they still apply. 2. Inspect recent relevant changes, logs, configuration, and run manifests. 3. Distinguish the visible symptom from a proposed cause. Do not edit merely because a familiar exception suggests an easy fix. ## 2. Reproduce and bound the failure 1. Run the smallest safe command that should reproduce the symptom. 2. Record whether it is deterministic, intermittent, machine-specific, data-specific, or dependent on ordering/timing. 3. If reproduction would be destructive, costly, or use reserved data, stop and request the needed authority or choose a non-mutating probe. 4. If the failure cannot be reproduced, compare environment, command, inputs, Git state, and dependency locks before declaring it gone. ## 3. Build and eliminate hypotheses List plausible causes and, for each, the cheapest observation that would distinguish it. Prefer direct evidence in this order: 1. exact traceback, exit code, or incorrect output; 2. minimal reproduction; 3. focused logging or state inspection; 4. controlled input/config variation; 5. history or non-destructive bisection. Change one explanatory variable at a time. Do not use destructive Git reset or discard unrelated user work during bisection. ## 4. Isolate the root cause Reduce the case until removing one condition removes the failure. For data or statistical failures, also check leakage, seed sensitivity, stale code/config, and baseline-budget mismatch. For integration failures, verify each boundary separately: executable discovery, configuration loading, process startup, protocol exchange, shared workspace/state path, then UI behavior. If multiple causes remain possible, say which evidence is missing instead of choosing the most convenient story. ## 5. Fix only when authorized For a diagnosis request, stop after proving the cause and proposing a scoped fix. For a requested repair: 1. make the smallest change that removes the cause; 2. preserve compatibility and unrelated user changes; 3. add or update a regression test that failed before the fix; 4. avoid hiding the symptom with broad exception handling or relaxed checks. ## 6. Verify proportionally Run the minimal reproduction first, then the focused regression tests, then the repository-required broader checks. Verify the original user-visible path, not only the helper function. For intermittent failures, repeat enough times to make the remaining uncertainty explicit. ## 7. Record the failure Call `mcp__memory__record_failure` with: - `trigger`: operation and preconditions; - `symptom`: exact externally visible failure; - `root_cause`: proven mechanism, not a guess; - `resolution`: change and verification command; - appropriate empirical or proof domain. If unresolved, record the diagnostic evidence and surviving hypotheses rather than inventing a root cause. ## Recovery branches - Cannot reproduce: compare manifests and ask for the missing command/input. - Flaky: identify timing, ordering, shared-state, or randomness dimensions and run controlled repetitions. - External dependency failure: prove the local boundary is healthy, record the upstream error, and provide a safe retry or fallback. - Fix causes a different regression: revert only your scoped change, preserve evidence, and return to the hypothesis list. - Repeated dead end: stop changing code, summarize tested hypotheses, and state the exact user input or external change needed. ## Completion criteria Debugging is complete when the symptom is reproducible or its absence is explained, the root cause is supported by discriminating evidence, any authorized fix passes the original reproduction and regression checks, and the failure ledger contains enough detail for the next agent to avoid repeating the investigation.
Files in this package (2)
- SKILL.md 5 KB
- evals/evals.json 2 KB
Versions
The database has no other skills named debug-sop.
Identical content appears in 1 other GitHub folders. We show one copy with the highest score.
Database snapshot: 13.11.2026 · package version 3ce64fbc8a27 (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
- 90debug
Debug errors, test failures, incorrect output, browser failures, intermittent bugs, and performance regressions through a tight red/green diagnosis loop. Use when behavior is broken, failing, flaky, slow, or unexplained. - 86vibe-debug
Diagnose and fix a reproducible failure in an existing project. Use for crashes, broken behavior, or failing checks, not greenfield planning. - 85bug-diagnosis
Diagnose broken behavior, errors, hangs, intermittent failures, or regressions with a measured reproduction loop, ranked hypotheses, root-cause proof, regression tests, and cleanup. Includes incident recovery and runtime or trace forensics. Use when something "is broken",… - 100debug-error
Diagnose one bug with hypotheses and runtime evidence before fixing. Use when "debug this error" or behavior is unexpected. FE↔BE mismatch → debug-fe-be-integration. Bug to PR → workflow-fix-and-ship. Sentry backlog → debug-sentry-monitor. - 100debug
Debug errors and unexpected behavior with log analysis. Use for issues and error messages. - 100debug
Systematic debugging with hypothesis-driven investigation. Use when something is broken, tests are failing, unexpected behavior occurs, or errors need investigation. Triggers on: 'this is broken', 'debug', 'why is this failing', 'unexpected error', 'not working', 'bug', 'fix…