systematic-debugging

Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions. Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

0.85x

Quality

76%

Does it follow best practices?

Impact

68%

0.85x

Average score across 2 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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 body is a strong, well-sequenced debugging process with explicit checkpoints, feedback loops, and executable examples. Its primary weakness is conciseness — motivational stats and a rationalizations table reiterate the red-flags content — and the lack of any bundle files means progressive disclosure rests entirely on in-file structure.

Suggestions

Collapse the 'Common Rationalizations' table into the 'Red Flags' section (or move it to a reference file) to remove redundancy and improve token efficiency.

Trim or relocate the 'Real-World Impact' statistics, which read as motivational padding rather than actionable guidance.

Consider extracting the multi-layer instrumentation example into a references/ file and linking to it, keeping the main body lean while preserving the detailed walkthrough.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and focused on debugging specifics rather than explaining known concepts, but noticeable reiteration (Red Flags, Common Rationalizations table, and Real-World Impact stats overlap in message) adds padding that could be trimmed.	3 / 5
Actionability	Provides concrete executable bash examples (multi-layer instrumentation, bun/npm test commands) alongside specific process steps; minor gaps in that some guidance remains procedural rather than code-backed.	4 / 5
Workflow Clarity	Clear four-phase sequence with mandatory ordering, explicit validation checkpoints ('Verify Before Continuing'), and feedback loops (re-analyze on failure, 3+ fixes triggers architectural review).	5 / 5
Progressive Disclosure	Single well-organized SKILL.md with clearly labeled sections and a Quick Reference table; no bundle files exist, and references to sibling skills are inline rather than to this skill's own deeper files, leaving minor organization room.	4 / 5
	Total	16 / 20 Passed

Description

78%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 well-constructed: it states the skill's purpose, includes an explicit 'Use when' trigger clause with natural keywords, and is clearly distinguishable. Its main weakness is specificity — it describes the framework abstractly rather than naming the concrete phases or actions.

Suggestions

Name the four phases explicitly in the description (e.g., 'reproduce, investigate root cause, form hypothesis, implement fix') to raise specificity from abstract framework to concrete actions.

Add a few common trigger synonyms (errors, crashes, exceptions, stack traces) to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('four-phase debugging framework') and a concrete action ('ensures root cause investigation before attempting fixes'), but does not enumerate the phases or multiple concrete actions, so coverage is incomplete.	3 / 5
Completeness	Explicitly answers both what ('Four-phase debugging framework that ensures root cause investigation') and when ('Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('any bug, test failure, or unexpected behavior', 'before proposing fixes') with good coverage, though a few common synonyms (errors, crashes, exceptions) are absent.	4 / 5
Distinctiveness Conflict Risk	Debugging is a clear niche with distinct triggers and an explicit anti-pattern framing ('Never jump to solutions'), with only minor overlap risk against general coding skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: secondsky/claude-skills
Path: plugins/systematic-debugging/skills/systematic-debugging/SKILL.md
Commit: ad16332

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.