CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

apiko/apiko-media

Generate or edit images and generate videos through the APIKO API (Nano Banana, GPT Image, Seedream, Wan 3.0, Seedance). Use when the user asks to create an image, edit or combine photos, make a video from text, an image or reference clips, or call APIKO image/video models from code. Handles async submit, polling, local reference uploads, cost checks and saving the result.

Quality

94%

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

Overview
Quality
Evals
Security
Files

Quality

Content

100%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.

The body is an exemplary skill document: lean and entirely composed of non-obvious operational facts, fully executable commands with a fallback path, a well-sequenced workflow with cost and error-recovery checkpoints, and clean one-level-deep reference structure. No dimension shows a meaningful weakness.

DimensionReasoningScore

Conciseness

Every section carries APIKO-specific facts Claude cannot know (model ids, price rules, timing ranges, error codes, upload limits) with no padding or explanation of familiar concepts — e.g. "Images are priced per image by tier; videos per second of output by resolution" — so each token earns its place.

5 / 5

Actionability

Three copy-paste-ready `python3 scripts/apiko_media.py` commands cover the common image, edit, and reference-video cases with exact flags, the script's output contract is documented ("prints one JSON line with task_id, file and url"), and a complete plain-HTTP fallback with endpoints, polling interval, and auth header is provided.

5 / 5

Workflow Clarity

A clear three-step sequence (understand request → check cost and run → report result) with explicit checkpoints and recovery loops: cost approval before billing ("wait for a yes"), timeout recovery ("do not submit again... Resume with status <task_id>"), and per-error-code fixes (400 → fix the field; unreachable reference URL → fix the input before retry).

5 / 5

Progressive Disclosure

The body is a concise overview with a decision-useful model table inline, and detail is split one level deep into a real, clearly signaled [references/models.md](references/models.md) (linked twice) plus a bundled script; the reference file itself contains no nested reference chains, so navigation is easy.

5 / 5

Total

20

/

20

Passed

Description

88%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 strong description that clearly states capabilities and explicit trigger conditions in third person, with only minor gaps in synonym coverage and a small risk of overlapping generic image-generation triggers. It closely matches the good examples in both structure and specificity.

Suggestions

Add one or two common synonyms such as "picture" or "generate/render an image" to the Use-when clause to broaden natural trigger coverage.

Mention output file types (e.g., PNG/JPEG images, MP4 video) in the description to catch users who ask by extension.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Generate or edit images and generate videos", "async submit, polling, local reference uploads, cost checks and saving the result" — giving comprehensive coverage of the skill's workflow in third-person voice, matching the top anchor.

5 / 5

Completeness

It explicitly answers both "what" (image generation/editing and video generation through the APIKO API, plus submit/poll/upload/cost-check/save handling) and "when" ("Use when the user asks to create an image, edit or combine photos, make a video... or call APIKO image/video models from code") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases like "create an image", "edit or combine photos", "make a video from text, an image or reference clips" cover the main triggers well, but common synonyms ("picture", "draw", "render") and output file extensions (.png, .jpg, .mp4) are missing, so it falls just short of the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The APIKO-specific niche and named model families (Nano Banana, GPT Image, Seedream, Wan 3.0, Seedance) make it mostly distinct, but broad triggers like "create an image" create minor overlap risk with any other image-generation skill, so it fits the 4 anchor rather than 5.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Reviewed

On this page