CtrlK
BlogDocsLog inGet started
Tessl Logo

debugging-toolkit-smart-debug

Use when working with debugging toolkit smart debug

41

Quality

40%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/debugging-toolkit-smart-debug/SKILL.md
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, genuinely useful debugging playbook with a clear 10-step workflow and validation, but it is padded with generic boilerplate and a role line, its code example is illustrative rather than executable, and it is a monolithic single file with no progressive disclosure into references.

Suggestions

Remove the generic 'Use this skill when / Do not use / Instructions' boilerplate and the 'You are an expert...' role line; they restate what the skill already implies.

Replace fictional functions in the example (aiAnalyze, getSentryIssue) with real, runnable calls or clearly label the block as a schematic rather than executable code.

Split the tool catalog (observability/Apm/tracing vendors) and the worked example into reference files linked from SKILL.md to reduce inline length and improve navigability.

DimensionReasoningScore

Conciseness

The body is mostly efficient structured lists, but it carries noticeable padding: the role line 'You are an expert AI-assisted debugging specialist...' and the generic 'Use this skill when / Do not use / Instructions' boilerplate add little debugging-specific value, matching 'mostly efficient but could be tightened'.

3 / 5

Actionability

It names concrete tools (Sentry, DataDog, Jaeger, OpenTelemetry) and gives a worked example, but the example relies on fictional functions (aiAnalyze, getSentryIssue, getDataDogTraces) so it is illustrative pseudocode rather than copy-paste executable, matching the 'pseudocode instead of executable code' anchor.

3 / 5

Workflow Clarity

A clearly sequenced 10-step workflow (Triage → Prevention) with an explicit Validation step and success-criteria checklist provides most checkpoints, but it lacks a tight validate→fix→retry error-recovery loop, so it sits at 'clear sequence with most checkpoints' rather than 5.

4 / 5

Progressive Disclosure

No references/scripts/assets bundle exists and the skill is a single ~150-line file with everything inline; section headers give structure, but content that could live in separate references (tool catalog, RCA checklist, example) is not split out, matching 'some structure but could be better organized'.

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-tautological trigger clause ('Use when working with debugging toolkit smart debug') that fails to say what the skill does and relies on a generic, circular domain label. It would be hard for a model to distinguish it from other debugging-related skills.

Suggestions

State concrete actions the skill performs, e.g. 'Triages production errors, gathers observability data, generates ranked hypotheses, and proposes validated fixes'.

Add explicit natural trigger phrases users would say, such as 'debug', 'root cause', 'stack trace', 'production incident', or 'error spike'.

Replace the circular 'debugging toolkit smart debug' label with a one-line 'what' so the description answers both what it does and when to use it.

DimensionReasoningScore

Specificity

The description 'Use when working with debugging toolkit smart debug' names the domain but names zero concrete actions (no 'analyzes', 'triages', 'instruments'), matching the 'names domain but actions minimal/generic' anchor rather than score 1 only because the domain is identified.

2 / 5

Completeness

It has only a 'when' clause ('Use when working with...') with no real 'what' — the 'what' is the circular restatement 'debugging toolkit smart debug' — mirroring the anchor example 'Use when working with documents'.

2 / 5

Trigger Term Quality

It offers only the generic keywords 'debugging' and 'debug' and the tautological product-ish phrase 'debugging toolkit smart debug'; it lacks the natural phrases a user would actually say, matching the 'one or two generic keywords' anchor.

2 / 5

Distinctiveness Conflict Risk

'Debugging' is very broad and would overlap with many general skills, and the description provides nothing to carve out a niche, matching the 'very broad; high overlap risk' anchor.

2 / 5

Total

8

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rmyndharis/antigravity-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.