CtrlK
BlogDocsLog inGet started
Tessl Logo

suggest-fix-issue

Given the details of an issue, suggests a fix for the issue.

36

Quality

33%

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 ./src/lm/skills/suggest-fix-issue/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

32%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 short, sectioned instruction-only skill, but it is padded and repetitive and offers only abstract guidance with no concrete examples or validation steps. It is well-organized structurally but lacks actionable substance.

Suggestions

Collapse the redundant Purpose and Usage sections into one concise statement of what the skill does and when to invoke it.

Add a concrete worked example showing the transformation from an issue description to a proposed fix with a real code block and file reference.

Replace the abstract bullets with a concrete sequence: locate the relevant file, identify the root cause, propose the fix, and verify the fix addresses the reported symptom.

DimensionReasoningScore

Conciseness

The Purpose and Usage sections repeat the same idea and pad it with audience commentary ("particularly useful for developers...or those new to troubleshooting"), which is unnecessary explanation Claude does not need; not a 3 because the redundancy is pervasive rather than incidental.

2 / 5

Actionability

The guidance is high-level hints ("identify the root cause", "output code-blocks and reference real files") with no executable code, commands, or concrete examples, matching the 'minimal concrete guidance; high-level hints' anchor.

2 / 5

Workflow Clarity

A rough read-then-diagnose-then-suggest sequence is implied but steps are poorly defined with no validation checkpoints; the task is non-destructive so the destructive cap does not apply, but it still fits the 'rough sequence with many gaps' anchor better than 3.

2 / 5

Progressive Disclosure

Content is short and organized into clear Purpose/Usage/How sections with no bundle files needed; not a 5 because the Purpose and Usage split is somewhat redundant rather than cleanly scoped.

4 / 5

Total

10

/

20

Passed

Description

33%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 conveys a basic 'what' but is vague and lacks any explicit 'when' trigger guidance or natural keywords, making it unlikely to be selected reliably. It also carries high overlap risk with general troubleshooting skills.

Suggestions

Add an explicit 'Use when...' clause stating the trigger conditions, e.g. 'Use when the user asks for help fixing or troubleshooting a reported issue.'

Include natural trigger terms and synonyms users would actually say, such as 'bug report', 'troubleshoot', 'root cause', or 'GitHub issue'.

Tighten the action to be more concrete, e.g. 'Analyzes an issue's description and comments to propose a code-level fix referencing real workspace files.'

DimensionReasoningScore

Specificity

Names the domain ("issue") but the single action "suggests a fix" is minimal and generic, matching the 'names the domain but actions are minimal or generic' anchor; it lacks the 1-2 concrete actions needed for a 3.

2 / 5

Completeness

It states a clear 'what' ("suggests a fix for the issue") but provides no explicit 'when' trigger guidance, which caps completeness at 3 per the rubric guidelines; not a 2 because the 'what' is clear rather than vague.

3 / 5

Trigger Term Quality

Only the generic keywords "issue" and "fix" appear with no natural trigger phrases users would say (no "Use when...", synonyms, or file types), matching the 'one or two generic keywords' anchor.

2 / 5

Distinctiveness Conflict Risk

"Suggests a fix for the issue" is very broad and would overlap with many debugging/troubleshooting skills, matching the 'very broad; high overlap risk' anchor.

2 / 5

Total

9

/

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
microsoft/vscode-pull-request-github
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.