Name: krillinai-cli
Rating: 71.2 (1 reviews)
Author: krillinai

krillinai-cli

Use when an agent needs to operate KrillinAI through its CLI, choose the right stage command, inspect CLI outputs, or run subtitle, TTS, landscape render, and portrait render tasks from a YouTube/local video input.

Quality

86%

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

Quality

Content

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise, actionable, and well-structured with a verified one-level-deep reference. The main gap is that explicit verification/feedback-loop checkpoints for render stages live only in the reference rather than the SKILL.md workflow.

Suggestions

Inline a brief verify-then-proceed checkpoint for render stages (e.g. confirm the manifest output exists before invoking render-*), rather than relying solely on the reference file.

Add a short validate/retry note in the Minimal Workflow for when a stage's stdout JSON reports ok:false, pointing to the error.kind classification already in the rules.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanations Claude already knows; every section (binary/build fallback, command table, rules, minimal workflow) earns its place, matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands with real flags (subtitle with --origin-lang/--target-lang/--workdir/--caption-source; render-vertical with --video/--subtitle) plus concrete parsing/error rules, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The minimal two-stage workflow (subtitle then render-vertical reusing manifest outputs) is sequenced and dry-run validation plus error-kind classification are mentioned, but explicit verify-then-proceed checkpoints for the batch/expensive render stage are delegated to the reference rather than inlined, which caps workflow clarity at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	The body is a concise overview that clearly signals a single one-level-deep reference ('read: skills/krillinai-cli/references/cli-contract.md'), and that bundle file exists and holds the detailed contract, matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	11 / 12 Passed

Description

85%Weight 40%Scale 1-3

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, complete, and distinctive, with an explicit 'Use when' trigger and named task types. Its only weakness is trigger-term coverage, which omits common user phrasings like 'dubbing' and 'shorts'.

Suggestions

Add common natural-language variations users would actually say, e.g. 'dubbing', 'translate/translate subtitles', 'shorts' or 'short-form video', alongside the existing task terms.

Consider reframing the trigger clause around user phrasing (e.g. 'Use when the user wants to subtitle, dub, or render...') in addition to the agent-oriented wording.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("operate KrillinAI through its CLI", "choose the right stage command", "inspect CLI outputs", and named subtitle/TTS/landscape/portrait render tasks), matching the 'multiple specific concrete actions' anchor rather than a single domain+action at level 2.	3 / 3
Completeness	Explicitly answers both 'what' (run subtitle, TTS, landscape and portrait render tasks) and 'when' via a literal 'Use when an agent needs to...' trigger clause, matching the 'clearly answers both what AND when' anchor.	3 / 3
Trigger Term Quality	Includes relevant natural terms (KrillinAI, CLI, subtitle, TTS, landscape render, portrait render, YouTube/local video) but misses common user variations such as 'dubbing', 'translate subtitles', or 'shorts/short-form video', so it sits at 'some relevant keywords but missing common variations' rather than full coverage at level 3.	2 / 3
Distinctiveness Conflict Risk	Tied to a named product CLI with distinct task triggers (subtitle/TTS/render from YouTube or local video), giving it a clear niche unlikely to conflict with other skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 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: krillinai/KrillinAI
Path: skills/krillinai-cli/SKILL.md
Commit: 22ee064

Reviewed: 7 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.