CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fixissueno

fixIssueNo

33

Quality

42%

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 ./.github/skills/fixissueno/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

55%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 admirably lean but underspecified: it names one tool call and then leaves Claude to guess what 'propose a solution' means — a comment, a patch, a plan? The silent-workflow instruction ('NEVER share any thinking process...') is a real behavioral constraint but arrives without context. Concrete output expectations and a defined final step would lift this from a hint to a workflow.

Suggestions

Specify the concrete invocation, e.g. "Call the get_issue tool with the issue number" — the current backtick phrasing ('Use the `get_issue`') is grammatically ambiguous about the tool's actual name.

Define what 'propose a solution' means concretely: the expected output format (e.g. diagnosis, root cause, and a fix plan or patch) and where it should be delivered.

Add minimal section headers (e.g. '## Process', '## Output') so the two instruction types — workflow steps and the silence constraint — are visually separated.

DimensionReasoningScore

Conciseness

The body is three short sentences plus one behavioral constraint with no padding and no explanation of concepts Claude already knows — every token carries instruction weight.

5 / 5

Actionability

"Use the `get_issue` to retrieve its details" is the only semi-concrete step (and even the tool name/arguments are ambiguous), while "Understand the issue and propose a solution to solve it" is a high-level hint with no specifics on what a proposal looks like or what to do with it.

2 / 5

Workflow Clarity

A rough sequence exists (retrieve details → understand → propose) but steps are poorly defined — the terminal action 'propose a solution' has no defined form, output, or follow-up, and no checkpoints of any kind. The destructive/batch cap does not apply since this is neither.

2 / 5

Progressive Disclosure

The skill is under 50 lines with no external references needed and all content appropriately inline, but it has no organizational structure at all — the simple-skill path to a 5 requires well-organized sections, and even one or two headers would help.

4 / 5

Total

13

/

20

Passed

Description

3%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 just the skill's name restated as a camelCase identifier, so it fails every function a description serves: no capabilities, no triggers, no usage conditions. It is indistinguishable from a placeholder. It needs a full rewrite as a third-person sentence describing what the skill does and when to invoke it.

Suggestions

Rewrite the description as a third-person capability statement, e.g. "Retrieves a GitHub issue with get_issue, analyzes it, and proposes a solution".

Add an explicit trigger clause, e.g. "Use when the user provides a GitHub issue number and asks for a fix or solution".

Include natural trigger terms users would actually say (GitHub issue, issue number, fix issue, resolve bug) so the skill is discoverable and distinguishable from general bug-fixing skills.

DimensionReasoningScore

Specificity

The description is the bare identifier "fixIssueNo" with no verbs or concrete actions — it names nothing the skill does, matching the 'entirely vague; pure abstract language' anchor.

1 / 5

Completeness

Neither 'what does this do' nor 'when should it be used' is communicated — the description is only a name, and no 'Use when...' clause or equivalent exists.

1 / 5

Trigger Term Quality

"fixIssueNo" is a camelCase identifier, not a natural phrase a user would say; there are no natural keywords or synonyms at all.

1 / 5

Distinctiveness Conflict Risk

"fix issue" is a very broad capability hint that would overlap with any bug-fixing or issue-handling skill, though it does narrow slightly to GitHub issues compared to an entirely generic phrase.

2 / 5

Total

5

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

description_field

'description' is very short (10 chars), consider making it more detailed

Warning

Total

15

/

16

Passed

Repository

microsoft/vscode

Path

.github/skills/fixissueno/SKILL.md

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.