CtrlK
BlogDocsLog inGet started
Tessl Logo

debug

Diagnose and fix a bug in the current project

63

Quality

75%

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 ./app/src/main/assets/skills/debug/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-crafted, lean debugging skill: concrete heuristics, a clearly sequenced method with an explicit verification checkpoint, and tight organization with no concept-explanation padding. It is strong across every content dimension.

DimensionReasoningScore

Conciseness

The body is lean and dense with concrete heuristics, with no padding explaining what bugs or basic language constructs are; every section earns its tokens.

3 / 3

Actionability

As an instruction-only skill it gives concrete, executable guidance — Grep for every assignment to a variable, check '<' vs '<=', confirm a CSS rule applies via Grep — and the rubric notes code absence is not penalized when guidance is this actionable.

3 / 3

Workflow Clarity

A clear six-step Method is sequenced with an explicit verification gate ('Verify with Read/Grep before editing') and a closing test-note step, and the falsifiable-hypothesis framing supplies the validate/reform feedback loop.

3 / 3

Progressive Disclosure

Under 50 lines with no need for external references, it is organized into clear sections (Method, Heuristics, Don't) and no bundle files exist, satisfying the 'under 50 lines, well-organized' path to a 3.

3 / 3

Total

12

/

12

Passed

Description

50%

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 concise and uses third-person voice, but it is uniformly mid-tier: it states the what but not the when, and relies on a single trigger keyword. A few targeted additions would lift every dimension.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when the user reports an error, crash, stack trace, or unexpected behavior.'

Expand the action list beyond 'Diagnose and fix' to specific concrete actions like 'reproduce, isolate the root cause, and patch' to lift specificity.

Include common trigger variations ('error', 'crash', 'exception', 'not working') directly in the description so it surfaces on more natural user phrasings.

DimensionReasoningScore

Specificity

Names the debugging domain and two concrete actions ('Diagnose and fix a bug') but is not comprehensive — it stops at two generic verbs rather than listing multiple specific actions.

2 / 3

Completeness

It states what the skill does ('Diagnose and fix a bug') but lacks an explicit 'Use when...' trigger, so per the guideline completeness is capped at 2 with 'when' only implied.

2 / 3

Trigger Term Quality

'bug' is a natural keyword users would say, but the description omits common variations like 'error', 'crash', or 'exception' (those appear only in the separate when_to_use field, not the description).

2 / 3

Distinctiveness Conflict Risk

'bug' gives a recognizable niche but is broad enough to overlap with general code-editing or refactoring skills, and no distinct trigger phrasing separates it from them.

2 / 3

Total

8

/

12

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
shiaho777/web-to-app
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.