common-debugging

Troubleshoot systematically using the Scientific Method. Use when debugging crashes, tracing errors, diagnosing unexpected behavior, or investigating exceptions.

Quality

76%

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 ./.github/skills/common/common-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 an efficient, actionable debugging protocol with clear sequencing and validation, plus a well-signaled supporting reference. It sits consistently at 4 across dimensions — strong but with minor room to tighten the meta/anchors section and elaborate validation checkpoints.

Suggestions

Trim or relocate the 'Canonical response anchors' block, which reads as meta-prompting noise rather than skill guidance, to push conciseness toward 5.

Spell out the VERIFY checkpoint slightly more concretely (e.g., name the exact regression command or test scope) to lift workflow_clarity from 4 to 5.

Consider moving the 'Incident pressure checklist' into the references bundle so the overview stays a clean pointer, improving progressive_disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no padding about what debugging is; the 'Canonical response anchors' section ('hypothesis, one hypothesis, stop ... minimal') is slightly meta and could be trimmed, keeping it just below 5.	4 / 5
Actionability	Concrete behavioral guidance throughout — numbered protocol steps, explicit stop-conditions ('Stop if you are changing code before repro'), and named anti-patterns ('No shotgun debugging'). As an instruction-only methodology skill this is appropriately actionable with only minor gaps.	4 / 5
Workflow Clarity	A clear OBSERVE→REPRODUCE→HYPOTHESIZE→EXPERIMENT→FIX→VERIFY sequence with explicit validation (VERIFY re-runs failing case and regressions), Red-Flag stop conditions, and a feedback loop (re-open root cause); narrowly below 5 because some checkpoints are terse rather than fully spelled out.	4 / 5
Progressive Disclosure	Well-organized into clear sections with one real, clearly-signaled one-level-deep reference (references/bug-report-template.md, verified present); not a 5 only because the inlined 'Canonical response anchors' content adds minor organizational noise.	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 strong, with explicit what/when framing and good natural trigger coverage. It is slightly less comprehensive on distinct concrete capabilities, since the methodology is expressed as a single approach supported by trigger phrasing.

Suggestions

Lead with a tighter enumeration of concrete debugging actions (e.g., 'isolate the failing layer, capture a repro, bisect recent changes') to lift specificity from 3 toward 5.

Add a couple of high-frequency natural synonyms (e.g., 'stack trace', 'broken build') to push trigger_term_quality from 4 to 5.

Dimension	Reasoning	Score
Specificity	Names the debugging domain and several concrete actions ('debugging crashes, tracing errors, diagnosing unexpected behavior, investigating exceptions'), but the core capability is a single methodology ('Troubleshoot systematically using the Scientific Method') rather than a comprehensive list of distinct actions.	3 / 5
Completeness	Explicitly states both what ('Troubleshoot systematically using the Scientific Method') and when ('Use when debugging crashes, tracing errors...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural trigger terms are well covered ('debug', 'fix bug', 'crash', 'error', 'exception', 'troubleshooting') and would match what a user actually says, though a few natural variations like 'stack trace' or 'broken' are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a clear debugging-methodology niche with distinct triggers and minimal conflict risk; only minor overlap with general coding skills keeps it below 5.	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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: HoangNguyen0403/agent-skills-standard
Path: .github/skills/common/common-debugging/SKILL.md
Commit: 405cdd5

Reviewed: 4 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.