CtrlK
BlogDocsLog inGet started
Tessl Logo

minimax-image-to-video

Animate an image through Hermes Web UI using the MiniMax image-to-video API.

61

Quality

73%

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 ./packages/skills/minimax-image-to-video/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 lean, highly actionable single-purpose skill: exact endpoint, deterministic credential/URL resolution, an executable example, and explicit error handling with recovery guidance. The main gaps are minor: duplicated token-resolution logic between prose and script, and no specification of what a successful response looks like.

DimensionReasoningScore

Conciseness

The body is almost purely operational (endpoint, URL/token resolution order, field defaults, model list, executable curl script) with no explanation of concepts Claude already knows. Not 5 because the token-resolution rules are stated twice — once as a numbered list and again re-implemented in the example script — a redundancy that could be trimmed.

4 / 5

Actionability

Fully executable guidance: exact endpoint path, ordered environment-variable fallbacks for both base URL and bearer token, a copy-paste-ready bash/curl example, complete JSON field list with defaults and allowed model values, and concrete handling of the 'missing_minimax_token' error. Not below 5 because the common case is fully covered with concrete commands.

5 / 5

Workflow Clarity

The sequence is clear and ordered (resolve base URL → resolve token → attach profile header → POST → handle error codes → return output_path), with explicit error-recovery checkpoints (stop and report auth/connection/generation errors; instruct user on MINIMAX_API_KEY vs MINIMAX_CN_API_KEY). Not 5 because the success path is underspecified — no description of the success response shape or how to confirm the downloaded mp4 exists at output_path.

4 / 5

Progressive Disclosure

The skill is self-contained with no bundle files (no references/, scripts/, or assets/ exist), organized under clear headings (intro, Workflow, fields, Example, error handling). Not 5 because the body runs ~84 lines — above the under-50-line simple-skill threshold — so sections like the model/field reference could arguably live in a separate reference file.

4 / 5

Total

17

/

20

Passed

Description

65%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 names a clear, distinctive niche with one concrete action, but it omits any explicit 'when to use' trigger guidance and covers only a single capability, which limits specificity and completeness. Adding a Use-when clause with natural trigger phrases would raise it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to animate an image, turn a picture into a video/MP4, or mentions MiniMax, Hailuo, or image-to-video generation.'

Enumerate 1-2 more concrete capabilities in the description (e.g. model selection, duration/resolution options, saving the finished mp4 to a path) so coverage reads as comprehensive rather than a single action.

Include a couple of natural synonyms/file extensions users actually say (e.g. 'make a video from this image', .png/.jpg input, .mp4 output) to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

"Animate an image" is one concrete action and the domain is clear (MiniMax image-to-video API via Hermes Web UI), but no further capabilities are enumerated. Not 4 because the description lists only a single action rather than 'several specific actions with minor gaps'; not 2 because the action named is concrete, not generic.

3 / 5

Completeness

The 'what' is clear (animate an image through Hermes Web UI using the MiniMax image-to-video API), but there is no 'Use when...' clause or equivalent trigger guidance in the description, which caps completeness at 3 per the judging guidelines. Not 4 because the 'when' is entirely absent rather than merely implicit.

3 / 5

Trigger Term Quality

Natural phrases users would say are present: "Animate an image", "image-to-video", "video", "MiniMax". Not 5 because common variations like 'turn an image into a video', 'make a video from this photo', or file extensions (.png/.jpg/.mp4) are missing; not 3 because the core natural phrasing ('animate an image', 'image to video') is already covered.

4 / 5

Distinctiveness Conflict Risk

A clear niche is stated: MiniMax image-to-video routed through Hermes Web UI — vendor, modality, and direction (image-to-video, not text-to-video) are all pinned. Minimal conflict risk with generic media or video skills; not 4 because no closely-related overlap is left ambiguous.

5 / 5

Total

15

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
EKKOLearnAI/hermes-studio
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.