systematic-debugging

4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

75%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 well-organized, lean debugging playbook with concrete commands, per-phase templates, verification checklists, and anti-patterns — it does not waste tokens explaining concepts Claude already knows. It falls short of 5s mainly because of a redundant master checklist, placeholder-based templates, and the absence of an explicit fix-failed feedback loop.

Suggestions

Add an explicit feedback loop in Phase 4, e.g. 'If verification fails, return to Phase 2 (Isolate) with the new evidence — do not layer more fixes on top.'

Remove or merge the standalone 'Debugging Checklist' section into the per-phase checklists to eliminate redundancy and tighten conciseness.

Provide one fully-worked concrete debugging example (real commands + filled-in RCA) so the templates are not purely placeholder scaffolding.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it offers templates, checklists, and commands rather than explaining what debugging or git is — but the standalone 'Debugging Checklist' section (Before Starting / During Investigation / After Fix) substantially overlaps the per-phase checklists, which is trimmable redundancy.	4 / 5
Actionability	Provides copy-paste-ready commands ('git log --oneline -20', 'git diff HEAD~5', 'grep -r "errorPattern" --include="*.ts"', 'pm2 logs app-name --err --lines 100') and structured fill-in templates; the phase templates use placeholders like '[Exact step to reproduce]', which is appropriate scaffolding for an instruction skill but not fully copy-paste executable.	4 / 5
Workflow Clarity	The Reproduce → Isolate → Understand → Fix & Verify sequence is clearly enumerated with per-phase checklists and a dedicated verification checklist ('Bug no longer reproduces', 'Test added to prevent regression'), but there is no explicit error-recovery feedback loop telling Claude to return to Isolate if verification fails.	4 / 5
Progressive Disclosure	Self-contained single file with clear section headers (Overview, 4 phases, Checklist, Commands, Anti-Patterns) and easy navigation, no nested or buried references; at ~100 lines it exceeds the under-50-line simple-skill exception and the redundant master checklist is a minor organization gap, so it stops short of 5.	4 / 5
	Total	16 / 20 Passed

Description

75%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 clear, concise, and answers both what the skill does and when to use it with an explicit trigger clause. It lists several specific techniques rather than vague fluff, landing solidly above the midpoint on every dimension. The main gap is a single narrow trigger phrase and missing common synonyms, which keeps it at 4 rather than 5.

Suggestions

Broaden the 'Use when...' clause with multiple concrete triggers, e.g. 'Use when debugging complex issues, performing root cause analysis, troubleshooting bugs, or investigating why something is broken.'

Add common synonyms users say (troubleshooting, bug, fixing bugs) to improve trigger term coverage toward a 5.

Optionally enumerate the four phases briefly in the description so the 'what' is more concrete than '4-phase methodology'.

Dimension	Reasoning	Score
Specificity	Quotes '4-phase systematic debugging methodology', 'root cause analysis', and 'evidence-based verification' — three specific named techniques rather than vague language, though they are methodological concepts rather than concrete object-level actions like the PDF anchor's 'extract text, fill forms'.	4 / 5
Completeness	Clearly states the 'what' (4-phase RCA methodology with evidence-based verification) and an explicit 'when' ('Use when debugging complex issues'), but the trigger is a single phrase rather than the multiple concrete trigger phrases that define a 5.	4 / 5
Trigger Term Quality	Includes natural user-facing terms ('debugging complex issues', 'root cause analysis', 'systematic debugging') that a user would actually say, but misses common synonyms like 'troubleshooting', 'bug fixing', or 'why is X broken'.	4 / 5
Distinctiveness Conflict Risk	The '4-phase systematic debugging' framing with RCA and evidence-based verification carves a recognizable niche, but the 'debugging complex issues' trigger is broad enough to risk minor overlap with general coding/troubleshooting skills.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/systematic-debugging/SKILL.md
Commit: 211561c

Reviewed: 8 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.