CtrlK
BlogDocsLog inGet started
Tessl Logo

grok-media

xAI Grok image and video generation guide covering authentication, endpoints, prompt structure, image editing, reference-image video, and async polling.

56

Quality

62%

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/grok-media/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

A well-organized, mostly lean Grok media reference that scores well on structure, but it lacks executable request examples and an explicit numbered polling workflow with validation checkpoints. Consolidating the duplicated prompting guidance would also improve conciseness.

Suggestions

Add at least one copy-paste-ready request example per endpoint (e.g. a curl or JSON body for POST /images/generations and POST /videos/generations).

Turn the video flow into an explicit numbered workflow with a poll-and-retry loop and explicit checkpoints for the 'failed' and 'expired' states.

Merge '## Image prompting' and the '### Images' subsection under Grok-Specific Prompt Guidance into one section to remove the overlapping advice.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes competence (no padding about what Grok or an API is), but prompting guidance is split across '## Image prompting' and '### Images' under Grok-Specific Prompt Guidance with overlapping advice, so it could be tightened.

2 / 3

Actionability

It names concrete endpoints, fields, status values, and placeholders, but provides no executable request examples (curl or JSON bodies), so a caller still has to infer the full request shape.

2 / 3

Workflow Clarity

The video polling sequence (POST generations -> GET /{request_id} -> done/failed/expired) and a Failure Handling section are present, but there is no explicit numbered workflow with validation checkpoints or a poll->retry feedback loop.

2 / 3

Progressive Disclosure

No bundle files exist and none are referenced; the single-purpose API reference is well-organized into clear sections with no nested references, fitting appropriately in one self-contained file.

3 / 3

Total

9

/

12

Passed

Description

67%

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 and clearly niche-scoped to xAI Grok media, but it omits an explicit 'Use when...' trigger and relies on some technical jargon over natural user phrasing. Adding trigger guidance and common synonyms would lift the weaker dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when generating images or video with xAI Grok, editing Grok images, or doing reference-image video generation.'

Swap jargon like 'async polling' for user-facing terms (e.g. 'polling for video results') and add common phrasings such as 'text-to-video' and 'image-to-video'.

DimensionReasoningScore

Specificity

Enumerates multiple concrete capabilities — 'authentication, endpoints, prompt structure, image editing, reference-image video, and async polling' — matching the anchor for listing several specific concrete actions rather than vague language.

3 / 3

Completeness

It clearly states what the skill covers, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Natural terms like 'xAI Grok', 'image and video generation', and 'image editing' are present, but it leans on jargon ('async polling', 'reference-image video') and misses common variations a user might say (e.g. 'text-to-video', 'image-to-video', 'generate a picture with Grok').

2 / 3

Distinctiveness Conflict Risk

The 'xAI Grok' qualifier pins it to a specific provider and media niche, making it unlikely to trigger for unrelated image/video skills.

3 / 3

Total

10

/

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
calesthio/OpenMontage
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.