CtrlK
BlogDocsLog inGet started
Tessl Logo

error-diagnostics-smart-debug

Use when working with error diagnostics smart debug

40

Quality

40%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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

SKILL.md
Quality
Evals
Security

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 body is a well-structured 10-step debugging workflow with a worked example and explicit validation/success criteria, but it leans on illustrative pseudocode and over-enumerates familiar tooling. It also references a playbook file that is not part of the bundle.

Suggestions

Trim the enumerated lists of vendor tool names (Sentry/Rollbar/Bugsnag, DataDog/New Relic/Dynatrace, etc.) to one representative example per category to reduce token cost.

Make the TypeScript example executable by using real library calls or clearly mark it as illustrative pseudocode with a justified note.

Fix the dangling reference to 'resources/implementation-playbook.md' (also note the directory is 'resources', not the conventional 'references') by either shipping the file or removing the pointer.

DimensionReasoningScore

Conciseness

The body is mostly organized and efficient but enumerates many tool names (Sentry, Rollbar, DataDog, Jaeger, etc.) and concepts Claude already knows, plus a padded persona line ('You are an expert AI-assisted debugging specialist...'), fitting anchor 3 ('mostly efficient but includes some unnecessary explanation').

3 / 5

Actionability

It offers a structured workflow and a TypeScript example, but the example calls non-real helpers (aiAnalyze, getSentryIssue, getDataDogTraces) and much guidance is high-level ('AI suggests optimal breakpoint locations') rather than executable, matching anchor 3 ('some concrete guidance but incomplete; pseudocode instead of executable code').

3 / 5

Workflow Clarity

A clear 10-step numbered sequence is present with validation in step 9 (run tests, canary monitor, AI review) and success criteria, matching anchor 4 ('clear sequence with most checkpoints present; minor validation gaps') rather than 5 because checkpoints are not uniformly explicit across all production-safe/deploy steps.

4 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets absent) and the one referenced path 'resources/implementation-playbook.md' does not exist, while all detailed content is inlined in SKILL.md, matching anchor 3 ('some structure but could be better organized; references present but not clearly signaled').

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 essentially a restatement of the skill name wrapped in a 'Use when' clause: it states when to invoke the skill but never says what it does. It lacks concrete capabilities, natural trigger terms, and distinctiveness.

Suggestions

Add a concrete 'what' clause listing specific debugging actions (e.g., 'Analyzes stack traces, queries APM/tracing data, ranks root-cause hypotheses, and proposes validated fixes').

Replace the tautological 'error diagnostics smart debug' with natural trigger terms a user would actually say (e.g., 'debug an error', 'investigate a stack trace', 'find a root cause in production').

Narrow the domain so it does not collide with general debugging/troubleshooting skills — call out observability-driven RCA specifically.

DimensionReasoningScore

Specificity

The description "Use when working with error diagnostics smart debug" names a domain but lists zero concrete actions, fitting anchor 2 ('Names the domain but actions are minimal or generic') rather than anchor 1 only because it at least names the domain.

2 / 5

Completeness

Only a 'when' clause is present with no 'what' content, matching anchor 2 ('only when is present without what', example 'Use when working with documents') rather than 3 which requires a clear 'what'.

2 / 5

Trigger Term Quality

"error diagnostics" and "smart debug" are generic/jargon terms rather than natural phrases a user would say, matching anchor 2 ('one or two generic keywords; missing the natural phrases users say').

2 / 5

Distinctiveness Conflict Risk

"error diagnostics smart debug" is broad debugging language with high overlap risk against many troubleshooting/debugging skills, matching anchor 2 ('very broad; high overlap risk').

2 / 5

Total

8

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.