Name: roboflow-inference
Rating: 56.00000000000001 (1 reviews)
Author: roboflow

roboflow-inference

Deployment option comparison (serverless, dedicated, self-hosted, batch) and Workflow execution patterns. For raw API URL patterns, auth, and request/response formats, see roboflow-api-reference.

Quality

63%

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/inference/SKILL.md

Quality

Content

61%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 content is well-structured and highly actionable with concrete tools and copy-paste CLI examples, but it carries some verbosity and its primary batch workflow lacks an explicit validation gate before exporting results.

Suggestions

Add an explicit validation checkpoint to the Batch Processing flow, e.g. "Verify job status is `complete` (via `show-job-details`) before running `export-batch`".

Trim padding: remove the microservice analogy and condense the agent source-of-truth blockquote to the essential rule.

Provide one worked `workflows_run` example with a concrete `workflow_id` and `parameters` payload so the most common integration call is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete tables and commands, but includes padding such as the microservice analogy ("similar to the extensibility benefits of a microservice over a point-to-point call"), a lengthy agent source-of-truth blockquote, and repeated "don't pick silently" messaging that could be tightened.	3 / 5
Actionability	Provides concrete, mostly executable guidance including named MCP tools, full copy-paste `inference rf-cloud` CLI commands, and a minimal end-to-end batch example, with minor gaps where key execution details (e.g. a worked `workflows_run` call with parameters) are deferred to referenced files.	4 / 5
Workflow Clarity	The Batch Processing flow is a clear 5-step sequence (save workflow, stage inputs, submit, monitor, export) with CLI per step, but it lacks an explicit validation checkpoint verifying job completion before export; per the rubric, missing validation in a batch operation caps workflow clarity at 3.	3 / 5
Progressive Disclosure	SKILL.md acts as an overview with well-signaled, one-level-deep references ("see [`batch-staging`](batch-staging.md) for nuances", "See [workflows](./workflows.md)"), splitting detail into separate files; minor gaps come from mixed `./file.md` and `roboflow://` URI navigation styles and dense inline CLI command tables.	4 / 5
	Total	14 / 20 Passed

Description

66%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 clearly states what the skill covers and enumerates concrete deployment options with good boundary management against a sibling skill, but it lacks an explicit "Use when..." trigger clause, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when choosing a Roboflow inference deployment (serverless, dedicated, self-hosted, batch) or running a saved workflow."

Include a couple more natural user phrases such as "deploy a model", "run inference", or "scale inference" to broaden trigger coverage.

Lead with a concrete action verb (e.g. "Compares and runs...") rather than a noun phrase ("Deployment option comparison") to strengthen specificity.

Dimension	Reasoning	Score
Specificity	Enumerates four concrete deployment options ("serverless, dedicated, self-hosted, batch") plus "Workflow execution patterns", listing several specific concrete items rather than generic actions, with minor gaps in coverage.	4 / 5
Completeness	The "what" is clear (deployment comparison + workflow execution patterns), but there is no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes natural deployment terms users would say ("serverless", "dedicated", "self-hosted", "batch", "Workflow execution"), but misses common variations like "deploy", "run inference", or "scale".	4 / 5
Distinctiveness Conflict Risk	It actively disambiguates from a sibling skill ("For raw API URL patterns, auth, and request/response formats, see roboflow-api-reference"), giving a mostly distinct niche with minor overlap risk from "Workflow execution patterns" against a potential workflows-specific skill.	4 / 5
	Total	15 / 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
relative_links	Relative link issues: 8 missing, 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: roboflow/computer-vision-skills
Path: skills/inference/SKILL.md
Commit: f3b2cbd

Reviewed: 10 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.