google-gmail

Gmail via gws: send, read, search, label, draft, reply, forward.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/google/google-gmail/SKILL.md

Quality

Content

77%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.

A highly actionable, well-sequenced skill body with executable commands and clear validation/feedback checkpoints, slightly held back by verbatim duplication of the calendar-agenda and scope guidance across sections and by a monolithic structure that could offload detail to reference files.

Suggestions

De-duplicate the full-week calendar-agenda instruction: keep the worked example in 'Preview a meeting change inline' and shorten Rule 9 to a pointer, to tighten conciseness.

Move the detailed email-draft and calendar card grammars (and the prerequisite onboarding flow) into a reference file under references/, keeping SKILL.md an overview, to improve progressive disclosure.

Consolidate the Gmail scope table so the four-trust-boundary guidance appears once rather than in both Prerequisites and Rule 4.

Dimension	Reasoning	Score
Conciseness	Dense and operational with no concept-explaining preamble, but the full-week calendar-agenda instruction is repeated near-verbatim in both the 'Preview a meeting change inline' section and Rule 9, and scope boundaries recur in both Prerequisites and Rule 4 — real padding that could be tightened; not score 3 because of that duplication, not score 1 because nothing is filler.	2 / 3
Actionability	Fully executable, copy-paste-ready commands throughout (e.g. 'gws gmail +send --to alice@example.com --subject 'Hello' --body 'Hi Alice!'', 'gws gmail +read --id <MESSAGE_ID> --headers') with concrete flags; not score 2 because there is no pseudocode or missing key detail.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with validation checkpoints and feedback loops — the numbered onboarding flow, strip-stderr-before-pipe with an explicit re-run-without-redirect recovery, and the draft→email-draft→whole-week-agenda→calendar-preview sequence with a confirmation gate; not score 2 because checkpoints are explicit, not implicit.	3 / 3
Progressive Disclosure	Well-organized into labeled sections but it is a single ~230-line monolithic SKILL.md with no bundle files and no offloading — the detailed email-draft/calendar card grammars and onboarding flow could live in reference files; not score 1 because sections are clearly navigable, not score 3 because content that should be separate is inline and it exceeds the simple-skill threshold.	2 / 3
	Total	10 / 12 Passed

Description

82%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.

A compact, specific description that names the tool and seven concrete Gmail verbs with strong natural trigger terms, but it omits an explicit 'Use when...' trigger clause, capping completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to send, read, search, label, draft, reply to, or forward email' to lift completeness from 2 to 3.

Include common request phrasings like 'inbox', 'triage', or 'email' so trigger-term coverage spans more natural user variations.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "send, read, search, label, draft, reply, forward" — tied to Gmail via gws, matching the score-3 anchor; it is not the score-2 anchor because the verb list is comprehensive rather than partial.	3 / 3
Completeness	Clearly answers "what" (the verb list) but has no "Use when..." clause or explicit trigger guidance, so per the rubric guideline completeness is capped at 2; not score 1 because the "what" half is strong rather than weak.	2 / 3
Trigger Term Quality	Uses natural terms a user would actually say ("Gmail", "send", "read", "search", "label", "draft", "reply", "forward") with good coverage; not score 2 because it does not just name the domain but spans the common request verbs.	3 / 3
Distinctiveness Conflict Risk	"Gmail via gws" names a specific product and CLI, a clear niche unlikely to trigger the wrong skill; not score 2 because the explicit tool scoping prevents overlap with generic mail/calendar skills.	3 / 3
	Total	11 / 12 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Open-Curiosity/gini-agent
Path: skills/google/google-gmail/SKILL.md
Commit: 6c5d85e

Reviewed: 12 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.