replicate

Discover, compare, and run AI models using Replicate's API. Strong fit for image, audio, and video generation pipelines that swap models frequently.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/replicate/SKILL.md

Quality

Content

47%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 a concise catalogue stub that delegates the real workflow to the upstream repository, so it is well-structured but lacks executable, in-skill guidance. Actionability and workflow clarity are weak because no concrete API usage or install commands are provided.

Suggestions

Add a minimal executable example for the core skill operation (e.g., a `replicate run` or curl/Python snippet that actually calls a model), rather than only opening the upstream URL.

Specify the install step with a concrete command or exact path instead of 'install the upstream bundle into your active agent's skills directory'.

Include a brief validation checkpoint (e.g., how to confirm the skill is installed and invokable) so the workflow has a feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned; only minor meta commentary ('This catalogue entry advertises the skill in OpenDesign...') and the repeated description sentence could be trimmed.	4 / 5
Actionability	The only concrete command is `open https://github.com/replicate/skills`, which merely opens a URL; there is no executable guidance for actually discovering, comparing, or running models via the Replicate API.	2 / 5
Workflow Clarity	A rough sequence is implied (inspect upstream README, install bundle, invoke by name/trigger) but the install step is undefined with no actual command, and there are no validation checkpoints.	2 / 5
Progressive Disclosure	Short, well-organized into clear sections with the upstream reference clearly signaled; no bundle files exist locally so there is no local one-level-deep navigation to evaluate.	4 / 5
	Total	12 / 20 Passed

Description

75%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 is specific, well-scoped to Replicate, and answers both what and when with concrete modality context. It stops short of an explicit 'Use when...' trigger clause and the action verbs are somewhat generic.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when the user wants to run, compare, or swap image/audio/video generation models via Replicate').

Include common synonyms and file/identifier forms users might say (e.g., 'Replicate models', 'run a model on Replicate').

Sharpen the action verbs beyond 'discover, compare, run' with concrete outcomes like 'generate images from prompts' or 'compare model outputs side-by-side'.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Discover, compare, and run AI models') scoped to Replicate's API, plus modality-specific pipeline context; minor gaps versus a fully comprehensive action list.	4 / 5
Completeness	Clearly states what it does and provides a 'when' via 'Strong fit for image, audio, and video generation pipelines that swap models frequently', though not phrased as an explicit 'Use when...' trigger clause.	4 / 5
Trigger Term Quality	Good natural keyword coverage ('AI models', 'Replicate's API', 'image, audio, and video generation', 'model comparison'); a few common synonyms or phrasings users might say are missing.	4 / 5
Distinctiveness Conflict Risk	The Replicate branding carves a clear niche with distinct triggers; minor overlap risk with other generic AI-model-runner skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/replicate/SKILL.md
Commit: d4138ea

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.