add-gmail-tool

Add Gmail as an MCP tool (read, search, send, label, draft) using OneCLI-managed OAuth. The agent gets Gmail tools in every enabled group; OneCLI injects real tokens at request time so no raw credentials are ever in the container or on disk in usable form.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-gmail-tool/SKILL.md

Quality

Content

85%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 strong, highly actionable multi-phase skill with executable commands, explicit validation checkpoints, and well-signaled offloading of the removal procedure. Its only real weakness is length: several explanatory prose blocks and the troubleshooting list could be trimmed for token efficiency.

Suggestions

Compress the "Why..." rationale blocks to one line each, or move the longer ones (e.g. the zod-to-json-schema pin) into a reference note.

Trim the troubleshooting "Common signals" list to the two or three most frequent failure modes, linking the rest.

Consider moving the Notes section's scope/limitation detail into REMOVE.md or a reference to keep the main flow lean.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable commands and avoids explaining concepts Claude already knows, but several multi-sentence "Why..." prose blocks and a lengthy troubleshooting signal list could be tightened, so it is mostly efficient rather than maximally lean.	2 / 3
Actionability	Provides fully executable bash, Dockerfile snippets, and jq pipelines (e.g. the safe-merge secret assignment and the stub-file heredocs) that are specific and copy-paste ready, matching the top anchor.	3 / 3
Workflow Clarity	Five clearly sequenced phases with explicit validation checkpoints — tsc --noEmit, bun test, "All must be clean before proceeding" — plus STOP conditions for stray real credentials and a Phase 5 verification step, matching the anchor for clear sequence with explicit validation and feedback loops.	3 / 3
Progressive Disclosure	Well-organized phased sections keep the cohesive sequential procedure inline while clearly signaling a one-level reference for removal ("See [REMOVE.md](REMOVE.md)"), and no bundle files are present to over-structure.	3 / 3
	Total	11 / 12 Passed

Description

67%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 specific, distinctive description that names concrete Gmail actions and the credential mechanism. It is held back from a top score by the absence of an explicit "Use when..." trigger clause and by jargon-heavy framing that weakens natural trigger-term coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to give an agent Gmail access (read, search, send, label, or draft email)."

Soften the jargon with natural terms users would say ("email", "inbox") alongside "Gmail".

Move the internal implementation detail about tokens/credentials into the body so the description stays a concise capability + trigger statement.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "read, search, send, label, draft" — and names the mechanism ("MCP tool", "OneCLI-managed OAuth"), matching the anchor for several specific concrete actions rather than the single-domain anchor at 2.	3 / 3
Completeness	Clearly states what the skill does, but there is no explicit "Use when..." trigger clause or equivalent, so per the judging guidelines completeness is capped at 2 rather than 3.	2 / 3
Trigger Term Quality	Contains the natural term "Gmail" plus action verbs, but the framing is implementation jargon ("MCP tool", "OneCLI-managed OAuth", "tokens", "raw credentials") and omits common user variations like "email" or "inbox".	2 / 3
Distinctiveness Conflict Risk	The niche — Gmail via OneCLI-managed OAuth MCP — is highly specific with distinct triggers, making it unlikely to fire for unrelated skills like add-vercel or add-atomic-chat-tool.	3 / 3
	Total	10 / 12 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
relative_links	Relative link issues: 1 missing, 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: nanocoai/nanoclaw
Path: .claude/skills/add-gmail-tool/SKILL.md
Commit: 641963c

Reviewed: 6 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.