Tessl • The management layer for AI agent skills

A lean, highly actionable integration skill: exact CLI commands with flags, explicit env/credential setup, a tightly sequenced draft-then-approve-then-publish workflow with validation on every write path, and appropriate self-contained structure for its size. Only minor trim opportunities (version pin, boilerplate block, repeated approval emphasis) keep it from full marks.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational — no concept explanations (OAuth, YouTube, Linear are assumed known), every section carries task-specific detail. Not 5 because of the version pin "Use Python 3.8 or newer" (time-sensitive version info outside a deprecated/old-patterns section), the kendex boilerplate block that adds no skill-operational value, and approval conditions restated across steps 3, 4, and the Consent section.	4 / 5
Actionability	Fully executable guidance: exact commands with all flags ("draft-upload --issue ID --video PATH --title TEXT --description TEXT --category ID --privacy public\|private\|unlisted --made-for-kids yes\|no", "draft-comment --issue ID --video-id ID --text TEXT", "--target-channel-id ID", "--parent-id ID", "publish --draft PATH"), named env vars, required OAuth scopes, and a real executable path (scripts/youtube-publish exists in the bundle). These cover the common cases copy-paste ready.	5 / 5
Workflow Clarity	The five-step sequence is explicit with validation checkpoints throughout: drafts make no API call and are reviewed with the user; publish runs "only after that yes" and "checks the author, decision, item and digest before any YouTube request"; the token's channel is checked with channels.list before a write; and failure handling is a feedback loop ("Stop and check the channel with the user before any new attempt. Do not repeat a successful request"). This matches the anchor with explicit validation steps and error-recovery loops.	5 / 5
Progressive Disclosure	The body is under 50 lines, needs no external reference files, and is organized into clear sections (Consumer setup, Draft and approval, Consent and spam). Bundle structure matches the body: the referenced executable scripts/youtube-publish exists alongside youtube-publish.py, and links to external Google docs are one level deep and clearly signaled. The simple-skill exception applies.	5 / 5
	Total	19 / 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.

The description is concise, third-person, and names a distinct niche with several concrete actions, but it omits any explicit 'when to use this skill' trigger clause, which caps its completeness and leaves natural trigger coverage slightly thin.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to upload, post, or reply on YouTube, or asks to publish a drafted upload after approval."

Include common user synonyms such as "publish", "post", and "video" to broaden natural trigger coverage.

Reword the opening "Load to draft a YouTube upload..." to a plain third-person verb phrase (e.g. "Drafts a YouTube upload...") for clarity.

Dimension	Reasoning	Score
Specificity	"draft a YouTube upload, comment or reply, or send a draft after the user's recorded approval" lists several concrete actions (draft upload, draft comment, draft reply, send after approval) with minor gaps — the recording of returned ids and the Linear approval mechanism are not surfaced. Not 5 because coverage is not comprehensive and the opening "Load to draft" is awkward; not 3 because more than 1-2 specific actions are named.	4 / 5
Completeness	The "what" is clear (draft uploads/comments/replies and send a draft after recorded approval), but there is no "Use when..." clause or equivalent explicit trigger guidance. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3 even with a clear what.	3 / 5
Trigger Term Quality	Natural terms users would say are present: "YouTube", "upload", "comment", "reply", "approval". Not 5 because common synonyms such as "post", "publish", or "video" are missing, so coverage is good but not comprehensive.	4 / 5
Distinctiveness Conflict Risk	"YouTube upload, comment or reply" pins a clear niche (YouTube publishing with an approval gate) with distinct triggers; minimal conflict risk with other skills. It does not fall to 4 because no closely related skill would plausibly capture these triggers.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vanillagreencom/kendex
Path: .agents/skills/youtube-publish/SKILL.md
Revision: 32d7bc7

Reviewed: 13 hours 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.

youtube-publish

Table of Contents

Is this your skill?