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.

72

Quality

89%

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.

An efficient, actionable procedure for filing a vercel/ai issue with concrete gh commands and a sensible authorization gate. Could be strengthened with a sample issue-body template and an auth-failure recovery step.

Suggestions

Include a short concrete example of the temporary body-file contents (a minimal markdown skeleton matching the listed sections) so the issue body is copy-paste ready.

Add a one-line recovery branch for step 1, e.g. 'If `gh auth status` fails, run `gh auth login` before continuing.'

Show the literal `--body-file` invocation with a real temp path pattern (e.g. `$(mktemp)` or `issue-body.md`) to remove placeholder ambiguity.

DimensionReasoningScore

Conciseness

Lean numbered procedure with no concept explanations or padding; every line (auth check, body-file rationale, the gh command, return the URL) earns its place and assumes Claude's competence.

5 / 5

Actionability

Concrete executable commands are present (`gh auth status`, `gh issue create -R vercel/ai --title "<title>" --body-file <file>`) and sections are enumerated, but no concrete example of the body-file content is shown, leaving a minor gap.

4 / 5

Workflow Clarity

A clear five-step sequence with checkpoints (`gh auth status` precondition, an explicit authorization gate before the external write), though an explicit error-recovery feedback loop (e.g. what to do if auth fails) is absent.

4 / 5

Progressive Disclosure

A simple, under-50-line single-purpose skill with a clear title and well-organized numbered steps and no need for external references, satisfying the simple-skill exception.

5 / 5

Total

18

/

20

Passed

Description

92%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, well-targeted description that names the domain, tool, and concrete contents, and gives an explicit 'Use when' trigger. Only minor room to add synonym phrasings like 'file/open an issue'.

DimensionReasoningScore

Specificity

Lists concrete actions ('Create a well-formed GitHub issue in vercel/ai using the gh CLI', 'reporting an AI SDK bug', 'preparing an issue body') plus a comprehensive enumeration of body contents (logs, code blocks, versions, reproduction steps, shell-sensitive text).

5 / 5

Completeness

Explicitly states the what ('Create a well-formed GitHub issue in vercel/ai using the gh CLI') and the when ('Use when reporting an AI SDK bug or preparing an issue body...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural terms like 'GitHub issue', 'vercel/ai', 'AI SDK bug', 'issue body', and 'reproduction steps' align with what a user would say, though a few synonyms (e.g. 'file/open an issue', 'report a bug' as a bare phrase) are not present.

4 / 5

Distinctiveness Conflict Risk

Scoped to a specific repo (vercel/ai) and tool (gh CLI) with distinct triggers, giving it a clear niche and minimal overlap with other skills.

5 / 5

Total

19

/

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
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.