CtrlK
BlogDocsLog inGet started
Tessl Logo

systematic-debugging

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

52

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/systematic-debugging/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%Weight 40%Scale 1-5

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

The content is a well-sequenced debugging methodology with strong validation gates and feedback loops, plus a genuinely actionable instrumentation example. Its main weaknesses are repetitive enforcement sections that pad the length and three referenced supporting files that are not actually present in the bundle.

Suggestions

Add the missing referenced files (root-cause-tracing.md, defense-in-depth.md, condition-based-waiting.md) or remove the references to avoid broken navigation.

Merge the overlapping Iron Law, Red Flags, Common Rationalizations, and Signals sections into a single consolidated 'anti-patterns' block to cut redundancy.

Tighten the abstract phases (Trace Data Flow, Pattern Analysis) with a concrete minimal example inline rather than only deferring to another file.

DimensionReasoningScore

Conciseness

The core Four Phases and the executable instrumentation example are efficient, but the Iron Law, When to Use, Red Flags, Common Rationalizations, and 'your human partner's Signals' sections repeatedly restate the same 'do not skip investigation' point and could be consolidated.

3 / 5

Actionability

Concrete steps (read stack traces, reproduce, git diff, per-boundary logging) and a copy-pasteable bash instrumentation block give mostly executable guidance, though a few phases ('Trace Data Flow', 'Find Working Examples') remain high-level hints pointing to another file.

4 / 5

Workflow Clarity

The Four Phases are explicitly sequenced with a 'MUST complete each phase' gate, and Phase 3/Phase 4 provide clear validation checkpoints plus feedback loops (verify before continuing, count failed fixes, return to Phase 1, 3+ failures → question architecture), with a Quick Reference checklist.

5 / 5

Progressive Disclosure

A 'Supporting Techniques' section clearly signals one-level-deep references to root-cause-tracing.md, defense-in-depth.md, and condition-based-waiting.md, but none of these files exist in the bundle, so navigation is broken; the 280-line body also inlines content that could be split out.

3 / 5

Total

15

/

20

Passed

Description

43%Weight 40%Scale 1-5

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 a pure trigger clause with strong 'when' guidance but entirely omits the 'what', leaving the skill's purpose implicit. Trigger terms are natural and well-chosen, yet the lack of any capability statement and the broad trigger surface limit distinctiveness.

Suggestions

Add a 'what' clause stating the skill's action, e.g. 'Systematically investigates root causes of bugs before fixing — read errors, reproduce, gather evidence, and form tested hypotheses.'

Narrow or qualify the trigger to reduce overlap, e.g. 'Use when a fix has failed or the root cause is unclear' rather than 'any bug'.

Include common synonyms such as 'error', 'crash', or 'exception' to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

The phrase 'encountering any bug, test failure, or unexpected behavior' names the problem domain but the description states zero concrete actions the skill performs — it never says what it does (e.g. diagnose root causes), only when to invoke it.

2 / 5

Completeness

Only the 'when' is supplied ('Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes') with no 'what' — the skill's actual capability is never described, matching the 'only when present without what' anchor.

2 / 5

Trigger Term Quality

Natural user-facing terms 'bug', 'test failure', 'unexpected behavior' are present and would naturally be said, though common synonyms like 'error', 'crash', 'exception', or 'broken' are missing.

4 / 5

Distinctiveness Conflict Risk

The qualifier 'before proposing fixes' carves a systematic-investigation niche, but the trigger surface 'any bug, test failure, or unexpected behavior' is very broad and could overlap with many troubleshooting skills.

3 / 5

Total

11

/

20

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
obra/superpowers
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.