CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

roboflow-inference

Interactive image/video previews, deployment option comparison (serverless, dedicated, self-hosted, batch), Workflow publishing, device management and Vision Events. For raw API URL patterns, auth, and request/response formats, see roboflow-api-reference.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/roboflow-inference/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 well-structured, highly actionable overview that gives concrete MCP tools, commands, and validation gates while delegating detail to clearly labeled one-level-deep references. The main improvement opportunities are trimming duplicated guidance across the opening callouts and slimming the inline batch CLI tables that duplicate the referenced batch-staging/batch-jobs files.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — no explanations of Docker, WebRTC, or basic library usage — with actionable tables instead of prose. It falls short of a 5 due to real duplication: workflows_run/models_infer guidance appears in the MCP tip callout, the 'Prefer Workflows' callout, and the tools table, and the streaming deployment options are covered both in the opening callout and again in 'When to Use Which'.

4 / 5

Actionability

Fully executable guidance throughout: a copy-paste-ready end-to-end 'inference rf-cloud' bash sequence (stage → submit → monitor → export), MCP tool tables with parameters, exact pip commands ('pip install inference-cli && inference server start'), and concrete output shapes ('{"type": "base64", "value": "..."}') with JsonField iteration advice. Specific examples cover the common cases, matching the anchor 5 example's completeness.

5 / 5

Workflow Clarity

The Batch Processing 'Flow' is a clear 5-step numbered sequence, and Workflow authoring Mode A has explicit checkpoints ('Validate with workflow_specs_validate before saving or running', 'test them with workflow_specs_run before publishing') plus recovery paths (restart-job, fetch-logs). It is not 5 because the batch Flow itself lacks an explicit validation checkpoint before submitting a job, and the streaming paths defer verification without a feedback loop.

4 / 5

Progressive Disclosure

References are clearly signaled, purpose-annotated ('for media upload, clip limits, and clients without the preview app'; 'for nuances (data sources, JSONL reference format, multipart batches, webhook notifications)'), and one level deep with no nested chains. It falls short of 5 because the inline Batch Processing section (~75 lines including full CLI command tables) overlaps content delegated to batch-staging.md/batch-jobs.md and could largely live in those files, and none of the referenced bundle files are present alongside this SKILL.md to verify the paths resolve.

4 / 5

Total

17

/

20

Passed

Description

70%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 specific, well-disambiguated description that clearly delineates the skill from its API-reference sibling and enumerates its capability areas. Its main weakness is the complete absence of explicit trigger guidance — no 'Use when...' clause — which both caps completeness and leaves natural trigger synonyms uncovered.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to run inference on images or videos, preview or test a saved Workflow, compare or choose a deployment option, publish a Workflow, or manage devices and production Vision Events.'

Include a few natural trigger synonyms users would actually say — such as 'run a model', 'deploy', 'test a workflow on an image' — to improve trigger term coverage alongside the existing platform terminology.

Consider converting the noun-phrase capability list toward concrete actions (e.g., 'Preview Workflows interactively on images/videos, compare deployment options...') to lift specificity from several specific items to fully comprehensive action coverage.

DimensionReasoningScore

Specificity

Lists several concrete capabilities — "Interactive image/video previews", "Workflow publishing", "device management and Vision Events" — and enumerates the four deployment options ("serverless, dedicated, self-hosted, batch"), but they are noun-phrases rather than explicit action verbs and "device management" is left generic. This matches anchor 4 (several specific actions, minor gaps) rather than 5, whose example shows comprehensive verb-led coverage.

4 / 5

Completeness

The "what" is clear (previews, deployment comparison, Workflow publishing, device management, Vision Events), but there is no "Use when..." clause or equivalent explicit trigger guidance — the second sentence ("For raw API URL patterns, auth, and request/response formats, see roboflow-api-reference") is a cross-reference to a sibling skill, not usage triggers. Per the rubric guideline, a missing 'Use when' clause caps completeness at 3; it is not 2 because the 'what' is specific and multi-part.

3 / 5

Trigger Term Quality

Natural keywords like "previews", "serverless", "self-hosted", "batch", "Workflow publishing", and "Vision Events" map well to what a Roboflow user would say, but common variations and synonyms (e.g., "run inference", "deploy a model", "streaming") are absent. Good coverage with a few natural terms missing fits anchor 4; anchor 5 requires synonyms and file extensions, which are not present.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche via platform-specific terms ("Vision Events", "Workflow publishing", "serverless, dedicated, self-hosted, batch") and explicitly disambiguates against the sibling skill ("see roboflow-api-reference"), minimizing conflict risk. This matches anchor 5 (clear niche with distinct triggers); anchor 4's 'minor overlap risk' understates the explicit boundary drawn here.

5 / 5

Total

16

/

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

relative_links

Relative link issues: 10 missing, 1 suspicious

Warning

Total

15

/

16

Passed

Repository

roboflow/computer-vision-skills

Path

skills/roboflow-inference/SKILL.md

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.