Name: debugging-toolkit-smart-debug
Rating: 40.8 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

debugging-toolkit-smart-debug

Use when working with debugging toolkit smart debug

Quality

40%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/debugging-toolkit-smart-debug/SKILL.md

The canonical home for this skill is debugging-toolkit-smart-debug in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

56%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 lays out a thorough, well-sequenced debugging workflow with explicit validation, but is padded with AI-flavored role-play and relies on non-executable pseudocode for its single example. The one external reference points to a file that does not exist.

Suggestions

Remove the 'You are an expert AI-assisted debugging specialist...' sentence and other 'AI-powered/AI suggests' filler to tighten the token budget.

Replace the pseudocode example with real, executable calls (e.g., actual Sentry/DataDog SDK snippets) or explicitly label it as illustrative.

Fix or remove the broken reference to resources/implementation-playbook.md, or create that file and move the tool catalogs and example into it for one-level-deep progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with useful lists, but includes role-play padding ('You are an expert AI-assisted debugging specialist...') and repeated 'AI-powered/AI suggests' filler that could be trimmed, matching the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	Tool and category lists are concrete, but the example uses non-executable pseudocode (aiAnalyze, getSentryIssue, getDataDogTraces) and workflow steps are descriptive rather than command-driven, matching the 'pseudocode instead of executable code; missing key details' anchor.	3 / 5
Workflow Clarity	A clear 10-step sequence runs from Initial Triage through Validation to Prevention, with an explicit validation step and success criteria, fitting 'clear sequence with most checkpoints present; minor validation gaps' rather than the 5 anchor which requires explicit fix-retry feedback loops.	4 / 5
Progressive Disclosure	The ~190-line body is monolithic and references a non-existent file (resources/implementation-playbook.md), with tool catalogs and the example inlined rather than split, matching the 'some structure but could be better organized; references present but not clearly signaled' anchor.	3 / 5
	Total	13 / 20 Passed

Description

25%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 near-empty template: it gives a 'Use when' trigger but no statement of capabilities, only a generic domain name, and no natural trigger keywords. It fails to distinguish the skill or tell Claude what it does.

Suggestions

Replace the placeholder with a concrete 'what' clause listing the skill's actual capabilities (e.g., 'Triages errors, gathers observability data, ranks root-cause hypotheses, and proposes validated fixes').

Add natural trigger phrases users would say, such as 'debug an error', 'investigate a stack trace', 'find a root cause', or 'analyze production incidents'.

Narrow the niche so the skill is distinguishable from generic debugging skills — name the specific toolkit or workflow it targets.

Dimension	Reasoning	Score
Specificity	The description names the domain ("debugging toolkit smart debug") but lists no concrete actions, matching the 'names the domain but actions are minimal or generic' anchor rather than the entirely-vague 1 or the action-listing 3.	2 / 5
Completeness	It supplies only a 'when' trigger ('Use when working with debugging toolkit smart debug') with no statement of what the skill does, matching the 'only when is present without what' anchor and the missing-what cap.	2 / 5
Trigger Term Quality	Only the generic keyword 'debugging' appears and 'smart debug' is not a phrase users naturally say, with no synonyms or file extensions, fitting the 'one or two generic keywords; missing the natural phrases users say' anchor.	2 / 5
Distinctiveness Conflict Risk	Debugging is a very broad domain and the description offers no niche narrowing, so it risks overlapping with many general debugging skills, matching the 'very broad; high overlap risk' anchor.	2 / 5
	Total	8 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/debugging-toolkit-smart-debug/SKILL.md
Commit: 57c135b

Reviewed: 3 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.