CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

roboflow-batch-processing

Use when running a Roboflow Workflow over many images or videos with batch processing — Asset Library jobs (the platform stages workspace images for you) or staged jobs (you stage external local/cloud files with the inference-cli), plus monitoring jobs, downloading results, and routing imports to datasources (bucket mirror) instead.

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

An exceptionally actionable, well-sequenced operational guide: every step has executable CLI/MCP guidance, the paid batch workflow is gated by explicit ingest and terminal-state validation with concrete error-recovery loops, and structure is easy to navigate. The only improvements are trimming a few redundant/meta passages and moving some long-tail detail (webhook caveats, credential chains) into reference files.

DimensionReasoningScore

Conciseness

Almost every sentence carries non-obvious operational detail (exact commands, env-var chains, limits, error strings, idempotency semantics) with no explanation of concepts Claude already knows, but a few passages could be trimmed — the ETL/ELT framing paragraph, the 'For agents' blockquote about skill provenance, and API-key guidance repeated in both Prerequisites and section 1 — so it fits anchor 4 rather than 'every token earns its place'.

4 / 5

Actionability

Fully executable, copy-paste-ready commands for every step (data-staging create-batch-of-images with --data-source cloud-storage, process-images-with-workflow with real flags, export-batch --target-dir), complete MCP tool signatures with parameter names and valid values, plus exact formats, limits, and batch-id constraints — matches the anchor for fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

Clear numbered sequence (Install → Stage → Start → Monitor → Download) preceded by a three-question routing checklist, with explicit validation before the paid batch job ('Do not start a job while pending is true or failed is true'), terminal-state polling with retryAfterSeconds, a timed single-image test-run to choose cpu/gpu, and feedback loops for failures (logs + restart-job) and 409 conflicts — the batch-operation validation cap does not apply because validation and recovery are present.

5 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers and a clearly signaled one-level cross-skill pointer ('see the cloud-storage skill'); no bundle files exist to reference, but ~330 lines of inline detail (webhook caveats, cloud credential chains, format limits) that could partly live in a separate reference file keep it at anchor 4 rather than a lean overview with well-split references.

4 / 5

Total

18

/

20

Passed

Description

87%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, information-dense description that explicitly covers both what the skill does (both job paths, monitoring, downloads, import routing) and when to use it, with highly distinctive platform-anchored triggers. Its only flaws are second-person phrasing inside the explanatory parentheticals and a few missing natural keyword variations.

DimensionReasoningScore

Specificity

Lists multiple concrete actions covering the full job lifecycle — 'running a Roboflow Workflow over many images or videos', 'Asset Library jobs', 'staged jobs' staged 'with the inference-cli', 'monitoring jobs, downloading results', 'routing imports to datasources (bucket mirror)' — which matches the comprehensive anchor (5), but the second-person parentheticals ('the platform stages workspace images for you', 'you stage external local/cloud files') violate the third-person voice rule and reduce the score by 1.

4 / 5

Completeness

Explicitly answers both 'what' ('Asset Library jobs (the platform stages workspace images for you) or staged jobs..., plus monitoring jobs, downloading results, and routing imports to datasources') and 'when' ('Use when running a Roboflow Workflow over many images or videos with batch processing') with concrete trigger phrases, matching the top anchor; anchor 4's 'when could be more explicit' does not apply since the trigger condition is specific.

5 / 5

Trigger Term Quality

Good natural keyword coverage — 'Roboflow Workflow', 'many images or videos', 'batch processing', 'Asset Library', 'datasources (bucket mirror)' are phrases a Roboflow user would actually say — but a few natural variations are missing (e.g. 'at scale', 'bulk predictions/runs', common media formats), so it fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Roboflow batch processing over many images/videos) with distinct platform-specific triggers, and it actively disambiguates the nearest competing use case ('routing imports to datasources (bucket mirror) instead'), so overlap with import/cloud-storage skills is minimal — matches anchor 5.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

roboflow/computer-vision-skills

Path

skills/roboflow-batch-processing/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.