CtrlK
BlogDocsLog inGet started
Tessl Logo

systematic-debugging

Root-cause route for actual bugs, failing tests, build errors, crashes, stack traces, and unexpected behavior. Do not use for test-first/TDD feature work, test-report packaging, review-feedback handling, or final completion evidence.

71

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

73%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, validation-rich debugging methodology with strong workflow clarity and decent actionability. Its main weakness is progressive disclosure: it is a long monolithic body that cites three supporting files that are not present in the bundle, leaving the navigation broken.

Suggestions

Add the missing referenced bundle files (root-cause-tracing.md, defense-in-depth.md, condition-based-waiting.md) to the skill directory so the in-body references resolve.

Move the "Common Rationalizations", "Red Flags", and "your human partner's Signals" sections into a single supporting file to slim the SKILL.md body and reduce token cost.

Replace the illustrative instrumentation block with a runnable, parameterized script under scripts/ so the diagnostic step is copy-paste executable.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence, but sections like the "Common Rationalizations" table, "your human partner's Signals", and repeated emphatic injunctions ("STOP", "Iron Law") add padding that could be trimmed without losing the core method.

4 / 5

Actionability

Provides concrete executable guidance (git diff, instrumentation snippet, bash logging commands) and specific procedural steps, but the diagnostic-instrumentation block is illustrative pseudocode rather than a reusable copy-paste script.

4 / 5

Workflow Clarity

A clear four-phase sequence with explicit validation checkpoints ("MUST complete each phase"), a verify-before-continue loop in Phase 3, and an explicit 3+ fix escalation path that questions architecture, matching the explicit-validation/feedback-loop anchor.

5 / 5

Progressive Disclosure

The body references three bundle files (root-cause-tracing.md, defense-in-depth.md, condition-based-waiting.md) but none of these files exist in the bundle, so the references are broken; the main file is also a near-300-line monolith that inlines substantial technique detail rather than splitting it out.

2 / 5

Total

15

/

20

Passed

Description

100%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 excellent: it states the skill's concrete purpose, lists natural trigger terms users would say, and explicitly delineates when not to use it against adjacent skills. It is concise, third-person, and highly distinctive.

DimensionReasoningScore

Specificity

Lists multiple concrete trigger categories ("actual bugs, failing tests, build errors, crashes, stack traces, and unexpected behavior") with a concrete action framing ("Root-cause route"), matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both what ("Root-cause route for...") and when (the trigger list and the explicit "Do not use for..." boundary), matching the anchor that requires concrete trigger phrases for both.

5 / 5

Trigger Term Quality

Uses natural terms a user would say ("bugs", "failing tests", "build errors", "crashes", "stack traces") plus several exclusions ("TDD", "test-report packaging"), giving comprehensive coverage of natural language and synonyms.

5 / 5

Distinctiveness Conflict Risk

A clear niche (root-cause debugging) with an explicit exclusion list carving it apart from sibling skills (TDD, test reports, completion evidence), minimizing conflict risk.

5 / 5

Total

20

/

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
foryourhealth111-pixel/Vibe-Skills
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.