Tessl • The management layer for AI agent skills

An exemplary lean skill body: dense with executable specifics, a clearly sequenced workflow with safety checkpoints, and appropriately scoped external references. The only gap is the absence of a concrete send/DRAFT API request example for the most consequential operation.

Suggestions

Add a one-line example of the send (and draft-create) API request (e.g., POST .../messages/send) so the full loop is copy-paste executable.

Consider a brief note on decoding MIME parts (e.g., base64url bodies) since the read step currently only names the task.

Dimension	Reasoning	Score
Conciseness	Every sentence carries non-obvious operational knowledge (gcloud ADC scope limitation, exact endpoints, scope-request policy, untrusted-content warning) with no concept padding or filler. It assumes Claude's competence throughout, matching the lean anchor 5.	5 / 5
Actionability	Provides a copy-paste gcloud command, exact API endpoints ("GET https://gmail.googleapis.com/gmail/v1/users/me/messages?q=...", "messages/{id}?format=full") and named scopes, but stops short of anchor 5 by omitting a concrete send/draft POST request example. It exceeds anchor 3 because what is given is fully executable rather than pseudocode.	4 / 5
Workflow Clarity	A numbered search → read → draft → send sequence with an explicit validation checkpoint and feedback loop for the risky operation ("Never blindly retry an uncertain send. Check Sent mail or the returned ID"), plus authorization gating before sending. This matches anchor 5's clear sequence with explicit validation and error-recovery guidance.	5 / 5
Progressive Disclosure	The body is under 50 lines, has no bundle files to reference, and is clearly organized into setup guidance, a numbered workflow, and a short footer of one-level external links. Per the rubric's scoring note, such a compact skill with well-organized content and clearly signaled references scores 5.	5 / 5
	Total	19 / 20 Passed

Description

83%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 concise, well-structured description that states four concrete capabilities and an explicit trigger clause. It is strong on completeness and only loses points for a couple of missing natural synonyms and slight overlap risk with other email skills.

Suggestions

Add natural trigger synonyms such as "message(s)" or "send an email" to broaden the natural-phrases coverage toward the top anchor.

Consider mentioning attachment handling or explicitly scoping to Gmail accounts only, to sharpen distinctiveness from other mail skills.

Dimension	Reasoning	Score
Specificity	"Search, read, draft, and send Gmail" lists four specific concrete actions covering the core email loop. It falls short of anchor 5 because coverage has minor gaps (no mention of attachments, labels, or organization) and is not the comprehensive list the top anchor shows.	4 / 5
Completeness	The "what" is explicit ("Search, read, draft, and send Gmail") and the "when" is explicit with concrete trigger phrases ("when the user asks to work with their inbox or email"), matching the anchor-5 pattern of both answers clearly stated. Not 4 because the trigger clause is fully explicit, not merely present.	5 / 5
Trigger Term Quality	"inbox or email" provides two natural user phrases alongside the Gmail domain term. It matches anchor 4 (good coverage, a few natural terms missing) rather than anchor 5 because synonyms like "message(s)", "mail", or "send an email" are absent.	4 / 5
Distinctiveness Conflict Risk	Gmail names a clear niche, but the generic triggers "inbox or email" could match a different mail provider's skill, which is minor overlap with closely related skills (anchor 4) rather than the minimal conflict risk of anchor 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Hmbown/Codewhale
Path: crates/tui/assets/skills/gmail/SKILL.md
Revision: ff466b2

Reviewed: 1 month 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.

gmail

Table of Contents

Is this your skill?