CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

create-vercel-ai-issue

Create a well-formed GitHub issue in vercel/ai using the gh CLI. Use when reporting an AI SDK bug or preparing an issue body that contains logs, code blocks, versions, reproduction steps, and shell-sensitive text.

69

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A model of token-efficient, sequenced instruction for an external-write task, with a genuine safety gate on the irreversible action. The remaining gap is executable specificity: what 'inspect vercel/ai' should check for and what the issue body should actually look like.

Suggestions

Replace "inspect vercel/ai" with the concrete checks intended, e.g. search existing issues for duplicates and read the repo's issue template.

Include a compact example issue body (or the exact section headings) so the --body-file format is copy-paste ready.

State the expected failure handling when gh auth status fails or issue creation errors, closing the workflow's feedback loop.

DimensionReasoningScore

Conciseness

Ten lean lines with no padding and no explanations of concepts Claude already knows (no gh CLI tutorial, no issue-format primer); every token earns its place, matching the 'lean and efficient' anchor.

5 / 5

Actionability

Concrete executable commands are given ("gh auth status", "gh issue create -R vercel/ai --title \"<title>\" --body-file <file>"), but "inspect vercel/ai" is unspecified, no example issue body or template is provided, and the command placeholders are left for Claude to construct, so it sits at 'mostly executable with minor gaps' rather than copy-paste ready.

4 / 5

Workflow Clarity

Five clearly-sequenced steps include a precheck ("Confirm gh auth status") and an explicit gate on the risky external write ("Do not create the external issue unless the user has authorized that write"). Issue creation is not destructive or batch, so the score-3 cap does not apply, but "inspect vercel/ai" leaves the validation intent implicit, holding this at the 'most checkpoints present, minor gaps' anchor.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, with no bundle files present and no external references needed; the numbered list plus standalone safety note is well-organized, which the simple-skill guidance rates at the top anchor.

5 / 5

Total

18

/

20

Passed

Description

82%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.

A tight, explicit description with a clear what and a concrete 'Use when...' clause targeted at a single repo. Its only weaknesses are the single-action framing in the what-clause and a few missing natural trigger synonyms.

Suggestions

Name one or two more concrete actions in the what-clause (e.g., check for duplicate issues, attach a minimal reproduction) to lift specificity.

Add trigger synonyms such as "file an issue" or "open a bug report in vercel/ai" so users phrasing the request differently still surface the skill.

DimensionReasoningScore

Specificity

"Create a well-formed GitHub issue in vercel/ai using the gh CLI" names the domain and tool but only one concrete action; the trailing clause describes issue contents rather than additional actions, so it matches the '1-2 concrete actions, not comprehensive' anchor rather than the 'lists several specific actions' anchor above.

3 / 5

Completeness

It explicitly answers what ("Create a well-formed GitHub issue in vercel/ai using the gh CLI") and when ("Use when reporting an AI SDK bug or preparing an issue body that contains logs, code blocks, versions, reproduction steps, and shell-sensitive text") with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Natural phrases like "reporting an AI SDK bug", "GitHub issue", and "logs, code blocks, versions, reproduction steps" are present, but common synonyms such as "file an issue" or "open a bug report" are missing, placing it at the 'good coverage, a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

The description is pinned to the vercel/ai repository and AI SDK bugs with a distinct trigger set, giving it a clear niche with minimal risk of firing for unrelated issue-creation or SDK skills.

5 / 5

Total

17

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

FranciscoMoretti/chat-js

Path

.agents/skills/create-vercel-ai-issue/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.