CtrlK
BlogDocsLog inGet started
Tessl Logo

suggest-fix-issue

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

44

Quality

46%

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

42%

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

The body is short and neatly sectioned, but it offers only vague, abstract instructions with no concrete examples or validation steps, and the Purpose/Usage sections are redundant and padded.

Suggestions

Replace the abstract bullets with concrete, executable guidance and at least one worked example (e.g., a sample issue and the suggested fix with referenced files and a code block).

Tighten or merge the Purpose and Usage sections to remove redundant restating and drop the audience filler about developers and new troubleshooters.

Make the workflow steps unambiguous and sequenced (read description and comments -> locate root cause in real files -> propose fix as a code block referencing those files) rather than hedging with 'where possible' and 'try to'.

DimensionReasoningScore

Conciseness

The Purpose and Usage sections restate each other and include padded phrasing like 'This can be particularly useful for developers looking for guidance...', fitting 'mostly efficient but could be tightened'; it does not, however, explain elementary concepts Claude already knows, so it stays above 1.

2 / 3

Actionability

The guidance is abstract ('try to identify the root cause', 'Where possible output code-blocks') with no executable code or concrete commands, matching the 'vague or abstract; no concrete code/commands' anchor.

1 / 3

Workflow Clarity

Three steps are listed (read the issue, output a fix referencing real files, address root cause for bugs) giving a basic sequence, but they are hedged with 'where possible' and 'try to' and lack any checkpoints, matching 'steps listed but validation gaps; checkpoints missing or implicit'.

2 / 3

Progressive Disclosure

The skill is under 50 lines with no external references needed and is organized into clear sections (Purpose, Usage, How to suggest a fix), which per the guidelines allows a 3 for simple skills based on well-organized sections alone.

3 / 3

Total

8

/

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 identifies a single concrete action, but it lacks explicit trigger guidance and only names one action, leaving it generic and potentially overlapping with related skills.

Suggestions

Add a 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when the user asks for help fixing a reported issue or wants a suggested fix for a bug').

List multiple concrete actions beyond 'suggest a fix' (e.g., analyze root cause, propose code changes, reference affected files) to lift specificity.

Include natural trigger variations users would say (e.g., 'bug report', 'issue fix', 'troubleshoot') to improve distinctiveness and trigger quality.

DimensionReasoningScore

Specificity

The description names a domain (an 'issue') and one concrete action ('suggests a fix'), matching the 'names domain and some actions, but not comprehensive' anchor; it is more concrete than 'helps with documents' but does not list multiple specific actions.

2 / 3

Completeness

It states what the skill does ('suggests a fix for the issue') but provides no 'Use when...' trigger guidance, so per the guidelines a missing trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

It uses naturally spoken words like 'fix' and 'issue', but coverage is thin with no common variations or trigger phrasing, fitting 'some relevant keywords but missing common variations' rather than the fuller coverage of a 3.

2 / 3

Distinctiveness Conflict Risk

'Suggests a fix for an issue' is narrower than 'helps with code and documents' but still generic enough to overlap with debugging or code-fix skills, matching the 'somewhat specific but could still overlap' anchor.

2 / 3

Total

8

/

12

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.