Tessl • The management layer for AI agent skills

SkillPublic

cli-batches

Submit and monitor batch inference jobs from the CLI. Upload and manage files for batch processing, retrieve results, and integrate batch pipelines with CI/CD workflows.

Quality

70%

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/cli-batches/SKILL.md

Quality

Content

55%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 cleanly structured, token-efficient CLI reference, but it reads as auto-generated documentation rather than actionable guidance: examples are placeholder commands with no flag usage, and the batch workflow (upload → create → wait → retrieve) is never sequenced or validated. Adding one end-to-end worked example and validation steps would lift both actionability and workflow clarity.

Suggestions

Add a short end-to-end workflow (files upload data.jsonl → batches create --input-file <fileId> → batches wait → batches output) showing flags used with real values.

Include validation/verification steps, e.g. check `batches get <batchId>` status or inspect `batches errors <batchId>` before and after retrieving output.

Make each example executable by composing the listed flags instead of repeating the bare subcommand name.

Dimension	Reasoning	Score
Conciseness	The body is lean with zero concept explanations and assumes Claude's competence, but each subcommand's bare "Example" block (e.g. "omniroute batches create") merely restates the header without adding information — minor content that could be trimmed.	4 / 5
Actionability	Commands and flags are named but examples never show real invocations: "omniroute batches create" shows none of its listed flags (--input-file, --endpoint), and no sample .jsonl format is given, so a reader cannot execute the core workflow without guessing key details.	3 / 5
Workflow Clarity	This is a flat subcommand listing with no end-to-end sequence (upload file → create batch → wait → output) and no validation or verification steps anywhere; for a batch-operation skill, the missing feedback loops cap this at 3, and the complete absence of any sequence places it at 2.	2 / 5
Progressive Disclosure	The single file is well organized by command group with clear headers and no nested references, and no external files are needed for this reference-style skill; minor gaps are the missing one-line overview of how subcommands relate and no guidance on which commands matter most.	4 / 5
	Total	13 / 20 Passed

Description

71%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, action-oriented description in third person that clearly communicates what the skill does, but it omits any explicit "when to use" trigger guidance, which both limits completeness and leaves triggering to inference. Adding a "Use when..." clause with natural trigger phrases would address the main gap.

Suggestions

Add a "Use when..." clause, e.g. "Use when the user asks to run, check, or retrieve batch inference jobs from the CLI".

Include natural synonyms and file formats users would mention, such as ".jsonl", "batch API", and "batch results".

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "Submit and monitor batch inference jobs", "Upload and manage files for batch processing, retrieve results", "integrate batch pipelines with CI/CD workflows" — matching the comprehensive-coverage anchor; it names concrete actions throughout in third person voice.	5 / 5
Completeness	The "what" is clear and concrete (submit/monitor batch jobs, manage files, retrieve results), but there is no "Use when..." clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Natural terms like "batch inference jobs", "batch processing", "CLI", and "CI/CD" are present, but common variations users would say such as "batch API", "batch results", or file extensions like ".jsonl" are missing.	4 / 5
Distinctiveness Conflict Risk	"Batch inference jobs from the CLI" carves a fairly distinct niche with limited overlap risk; the generic "files" and "CI/CD" wording leaves minor overlap risk with adjacent CLI or file-management skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: diegosouzapw/OmniRoute
Path: skills/cli-batches/SKILL.md
Revision: 5b3be70

Reviewed: 25 days ago

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.

cli-batches

Table of Contents

Is this your skill?