Name: krillinai-pipeline
Rating: 61.6 (1 reviews)
Author: krillinai

krillinai-pipeline

Use when planning multi-stage KrillinAI CLI workflows such as subtitle plus TTS plus horizontal or vertical render; current pipeline execution is a reserved/planned surface unless implementation is wired in.

Quality

71%

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/krillinai-pipeline/SKILL.md

Quality

Content

75%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 body is concise, actionable, and well-structured with concrete commands and recovery/verification feedback loops; it falls just short of top marks because the external reference is not clearly signaled as navigation and the execution caveat slightly limits actionability.

Suggestions

Promote the cli-contract.md reference into its own 'References' section so cross-skill navigation is clearly signaled rather than buried under Verification.

Add an explicit happy-path checkpoint after the pipeline command (e.g. 'Confirm stdout JSON success before inspecting outputs') so the multi-stage flow has a clear validation step up front.

Clarify how to verify whether pipeline execution is wired in (e.g. the exact probe command) so the execution caveat becomes actionable rather than a guard.

Dimension	Reasoning	Score
Conciseness	Lean ~40-line body that assumes Claude's competence and avoids explaining CLI/pipeline concepts; only minor redundancy between the opening line and the description slightly trims efficiency.	4 / 5
Actionability	Provides a concrete executable command with a real --outputs value and a complete output-value table, plus specific recovery steps (rerun only render with the same --workdir); the caveat that execution may not be wired in introduces a small execution gap.	4 / 5
Workflow Clarity	Recovery Strategy and Verification sections give a clear feedback loop (unsupported_command -> run stages individually; check manifest before rerun; inspect final media) with explicit checkpoints, but the happy path is a single command rather than a multi-step sequence with checkpoints.	4 / 5
Progressive Disclosure	Short, well-sectioned body under 50 lines with a single one-level-deep external reference; it could reach 5 if the cli-contract.md reference were surfaced in a dedicated navigation section rather than buried inside the Verification list.	4 / 5
	Total	16 / 20 Passed

Description

67%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 is specific, explicitly triggers with 'Use when', and occupies a distinct niche, but its trigger terms are somewhat technical and lack natural synonyms a user would actually say.

Suggestions

Add natural-language synonyms users might say, e.g. 'captions' alongside 'subtitle', 'dubbing' alongside 'TTS', and 'landscape/portrait video' alongside 'horizontal/vertical render'.

Consider dropping or relocating the 'reserved/planned surface' caveat from the description so the trigger guidance stays crisp and unambiguous.

Add the file extension or surface name (e.g. 'krillinai-cli pipeline command') to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('planning multi-stage KrillinAI CLI workflows such as subtitle plus TTS plus horizontal or vertical render'), but the actions are planning-oriented rather than a comprehensive enumeration of capabilities, leaving minor gaps.	4 / 5
Completeness	Explicitly answers both what ('planning multi-stage KrillinAI CLI workflows') and when ('Use when planning multi-stage KrillinAI CLI workflows'), with a concrete trigger phrase; the reserved/planned caveat slightly blurs the 'when' rather than weakening it further.	4 / 5
Trigger Term Quality	Includes relevant technical terms (subtitle, TTS, horizontal/vertical render) but misses common natural synonyms a user might say (e.g. 'captions', 'dubbing', 'landscape/portrait video'), so keyword coverage is incomplete.	3 / 5
Distinctiveness Conflict Risk	Scoped to a clearly distinct niche (KrillinAI pipeline multi-stage workflows) with specific triggers, leaving only minor overlap risk with other KrillinAI-related skills.	4 / 5
	Total	15 / 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: krillinai/KrillinAI
Path: skills/krillinai-pipeline/SKILL.md
Commit: 0a16abf

Reviewed: 1 day 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.