CtrlK
BlogDocsLog inGet started
Tessl Logo

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/superpowers/skills/systematic-debugging/SKILL.md

The canonical home for this skill is jbvc/systematic-debugging

SKILL.md
Quality
Evals
Security

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is a well-sequenced debugging methodology with strong workflow clarity and feedback loops, but it is padded with redundant exhortation sections and leans on three supporting files that are not actually present. Tightening the repetition and delivering the referenced technique files would materially raise quality.

Suggestions

Collapse the overlapping 'Red Flags', 'Common Rationalizations', and 'your human partner's Signals' sections into a single concise list to remove repetition.

Create the referenced root-cause-tracing.md, defense-in-depth.md, and condition-based-waiting.md files (or remove the dangling references) so progressive disclosure resolves to real content.

Convert the pseudocode instrumentation template into concrete, runnable commands or mark it explicitly as a pattern to adapt.

DimensionReasoningScore

Conciseness

The body is efficient in that it does not explain basic concepts Claude already knows, but sections like 'Red Flags', 'Common Rationalizations', and 'your human partner's Signals' repeatedly restate the same anti-guessing message and could be tightened.

2 / 3

Actionability

A concrete 4-phase process and an executable bash instrumentation block give real guidance, but a substantial portion is abstract behavioral direction (e.g. 'Read Error Messages Carefully') and the instrumentation template is partly pseudocode, so it falls short of fully copy-paste-ready.

2 / 3

Workflow Clarity

The four phases are explicitly sequenced with a hard ordering rule, plus validation checkpoints ('Verify Before Continuing', 'Verify Fix') and clear feedback loops (failed fix -> new hypothesis; 3+ failures -> question architecture), matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

References to root-cause-tracing.md, defense-in-depth.md, and condition-based-waiting.md are clearly signaled one level deep, but those files do not exist in the bundle and the main body is a long, fairly monolithic document, so the disclosure is only partially realized.

2 / 3

Total

9

/

12

Passed

Description

65%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is trigger-focused with strong, natural "when" guidance but omits any statement of what the skill does, leaving completeness and specificity underdeveloped. It is a serviceable trigger but reads as half a description.

Suggestions

Add a capability clause stating what the skill does, e.g. prepend 'Systematically investigates root causes of bugs before fixing' before the 'Use when' trigger.

Keep the natural trigger terms (bug, test failure, unexpected behavior) but consider adding 'root cause' or 'debugging' so the description conveys the skill's purpose and distinguishes it from generic coding help.

DimensionReasoningScore

Specificity

The description names the domain concretely ("any bug, test failure, or unexpected behavior") but never states what the skill actually does, so it lands in the 'names domain and some actions, but not comprehensive' band rather than listing multiple concrete actions.

2 / 3

Completeness

The explicit "Use when..." clause answers "when" strongly, but the "what does this do" half is absent (no mention of systematic debugging or root-cause investigation), so it does not reach the both-answered anchor.

2 / 3

Trigger Term Quality

Phrases like "bug", "test failure", and "unexpected behavior" are natural terms a user would actually say, giving good coverage of trigger vocabulary.

3 / 3

Distinctiveness Conflict Risk

"before proposing fixes" gives a distinct debugging niche, but the broad triggers ("bug", "unexpected behavior") could still overlap with general coding skills, and the missing capability statement weakens distinguishability.

2 / 3

Total

9

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.