CtrlK
BlogDocsLog inGet started
Tessl Logo

arcads-external-api

Creates and retrieves AI video and image-related assets via the Arcads external API (Seedance 2.0, Sora 2, Veo 3.1, Kling, Grok Video, Nano Banana, b-roll, scene, script/actor flows). Loads prompts from the bundled prompting guide and model library, respects HTTP Basic auth from ARCADS_API_KEY, and polls assets/videos until ready. Use when the user mentions Arcads, external-api.arcads.ai, Seedance, Sora2, Veo, Kling, Nano Banana, b-roll, UGC scripts, or generating marketing creative through Arcads.

73

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A thorough, highly actionable skill body with strong workflow sequencing and clean progressive-disclosure navigation. Its only weakness is redundancy, where mandatory gates are restated in multiple places rather than defined once and referenced.

Suggestions

Define the dialogue-confirmation gate and the credit-cost confirmation gate once each, then reference them by anchor from the execution checklist and QA section instead of restating the rules in each place.

Collapse the repeated 'MANDATORY before generating' framing into a single 'Gates before generation' subsection so the credit, dialogue, and generation-count confirmations are stated once.

The execution checklist (steps 3, 6, 11) duplicates prose already covered in dedicated sections — shorten each checklist item to a one-line pointer plus the gate name.

DimensionReasoningScore

Conciseness

The body is densely operational and avoids explaining concepts Claude already knows, but key instructions are restated across sections — the credit-confirmation gate and dialogue-confirmation gate each appear in a dedicated section, again in the execution checklist, and once more in the QA exception — so it could be tightened.

2 / 3

Actionability

Provides concrete endpoints ("POST /v2/videos/generate" with model: "seedance-2.0"), exact curl, JSON bodies, duration enums, and ffmpeg commands that are copy-paste ready rather than abstract direction.

3 / 3

Workflow Clarity

A 14-step sequenced execution checklist with explicit validation checkpoints (dialogue approval gate, credit-cost confirmation, .gitignore check, image QA) and a regenerate-with-revised-prompt feedback loop with a retry cap.

3 / 3

Progressive Disclosure

The body acts as an overview pointing to well-signaled one-level-deep references (reference.md, prompting/prompt-library/*.md) with a dedicated Supporting files index; no bundle files were present to verify, but the navigation structure is clearly one level deep.

3 / 3

Total

11

/

12

Passed

Description

100%

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, third-person description that pairs concrete capabilities with an explicit trigger clause and a well-scoped niche. It is specific, complete, and low-conflict.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Creates and retrieves AI video and image-related assets", "Loads prompts from the bundled prompting guide and model library", "respects HTTP Basic auth from ARCADS_API_KEY", and "polls assets/videos until ready" — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what (create/retrieve assets, load prompts, auth, poll) and when (a dedicated "Use when…" clause with explicit triggers), satisfying the top anchor.

3 / 3

Trigger Term Quality

The "Use when the user mentions Arcads, external-api.arcads.ai, Seedance, Sora2, Veo, Kling, Nano Banana, b-roll, UGC scripts, or generating marketing creative through Arcads" clause gives strong coverage of natural terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The Arcads external-API niche and vendor-specific model-name triggers make it clearly distinguishable and unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 56 missing, 43 deeper-than-1-level, 7 suspicious

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository
krusemediallc/arcads-claude-code
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.