CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

Quality

78%

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 ./.agents/skills/create-vercel-ai-issue/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is concise and well-structured for a simple skill, but its actionability and workflow clarity are constrained by implicit details about the body file and a lack of explicit validation for the external write step.

Suggestions

Show a concrete example of writing the issue body to a temp file (e.g., a printf/heredoc snippet) so the --body-file workflow is copy-paste ready.

Add an explicit validation step after gh issue create (e.g., confirm the returned URL is reachable) before reporting success to the user.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, with no padding or explanation of concepts Claude already knows; every line earns its place, matching the 'lean and efficient' anchor.

3 / 3

Actionability

Concrete commands are present (gh auth status, gh issue create with --body-file), but the issue body construction and the temporary body file path are described rather than given as complete executable examples, leaving key details implicit.

2 / 3

Workflow Clarity

Steps are numbered and sequenced, but for an outward-facing write operation there is no explicit validation checkpoint confirming the issue was created beyond returning the URL, so checkpoints are implicit rather than explicit.

2 / 3

Progressive Disclosure

As a simple skill under 50 lines with no external references, the content is well-organized into a clear numbered sequence; per the simple-skills note, this earns the top score without needing bundle files.

3 / 3

Total

10

/

12

Passed

Description

80%

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 specific, complete, and clearly scoped to a niche, with explicit 'what' and 'when' triggers. Trigger term quality is good but leans technical rather than reflecting natural user phrasing.

DimensionReasoningScore

Specificity

Names concrete actions: 'Create a well-formed GitHub issue in vercel/ai using the gh CLI' and details the contents of the issue body (logs, code blocks, versions, reproduction steps, shell-sensitive text), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly states what it does ('Create a well-formed GitHub issue...') and when to use it ('Use when reporting an AI SDK bug or preparing an issue body...'), satisfying both the 'what' and explicit 'when' triggers of the top anchor.

3 / 3

Trigger Term Quality

Includes relevant terms like 'GitHub issue', 'gh CLI', and 'AI SDK bug', but these are somewhat technical and lack common user-phrased variations (e.g., 'report a bug', 'file an issue'); missing common variations places it at the middle anchor.

2 / 3

Distinctiveness Conflict Risk

Scoped to 'vercel/ai' with the 'gh CLI' and AI SDK bug context, giving it a clear niche unlikely to trigger for unrelated skills; matches the 'clear niche with distinct triggers' anchor.

3 / 3

Total

11

/

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
FranciscoMoretti/chat-js
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.