add-gmail

Add Gmail integration to NanoClaw. Can be configured as a tool (agent reads/sends emails when triggered from WhatsApp) or as a full channel (emails can trigger the agent, schedule tasks, and receive replies). Guides through GCP OAuth setup and implements the integration.

Quality

85%

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

Quality

Content

88%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.

An exemplary procedural skill: fully executable commands, an explicit validation gate before proceeding, verification steps, troubleshooting feedback loops, and rollback instructions. Only minor improvements available — trimming a few over-explanatory asides and offloading Troubleshooting/Removal to a reference file.

Suggestions

Move the Troubleshooting and Removal sections into a reference file (e.g., references/troubleshooting.md) and link to them from a short pointer in SKILL.md.

Trim asides Claude can infer, such as the merge-conflict resolution guidance ('reading the conflicted files and understanding the intent of both sides').

State explicitly what happens if 'npx ... auth' is interrupted partway (e.g., whether credentials.json is partially written) to strengthen the OAuth recovery loop.

Dimension	Reasoning	Score
Conciseness	The body is nearly all executable commands with brief purpose notes and assumes Claude's competence (e.g., 'Verify ~/.gmail-mcp is mounted: check src/container-runner.ts'), but includes minor over-explanations like 'resolve them by reading the conflicted files and understanding the intent of both sides' that could be trimmed.	4 / 5
Actionability	Fully executable throughout: exact bash commands ('git remote add gmail https://github.com/qwibitai/nanoclaw-gmail.git', 'npx -y @gongrzhe/server-gmail-autoauth-mcp auth'), exact file paths, verbatim user prompts, fallback commands for the auth failure case, and copy-paste verification and monitoring commands covering the common cases.	5 / 5
Workflow Clarity	Clear phased sequence (Pre-flight → Apply Code Changes → Setup → Verify) with an idempotency check ('If src/channels/gmail.ts exists, skip to Phase 3'), an explicit validation gate ('All tests must pass... and build must be clean before proceeding'), a verification phase with user-facing tests, and troubleshooting feedback loops plus rollback/removal procedures.	5 / 5
Progressive Disclosure	A single well-sectioned file with clear phase headers and no external references; the length is justified by the multi-step setup process. Minor gap: the Troubleshooting and Removal sections (~60 lines) could live in a reference file to keep SKILL.md a leaner overview.	4 / 5
	Total	18 / 20 Passed

Description

75%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 specific, distinctive description that concretely covers both tool and channel modes plus OAuth setup. Its main weakness is the missing explicit 'when to use' trigger clause, and slightly thin natural-keyword coverage beyond 'Gmail'/'emails'.

Suggestions

Append an explicit trigger clause, e.g., 'Use when the user wants to add Gmail or email access to NanoClaw, set up Gmail tools, or make emails trigger the agent.'

Include natural synonyms users might say, such as 'email integration', 'inbox', or 'connect Gmail', to broaden trigger-term coverage.

Clarify the channel-mode capabilities tersely (e.g., 'polls the inbox for incoming emails') so the polling behavior is an explicit trigger term.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across both configuration modes — 'agent reads/sends emails', 'emails can trigger the agent, schedule tasks, and receive replies', 'Guides through GCP OAuth setup' — giving comprehensive coverage of what the skill does in third-person voice.	5 / 5
Completeness	The 'what' is clearly and concretely answered, but there is no 'Use when...' clause or equivalent explicit trigger guidance; the 'when' is at best weakly implied by 'Add Gmail integration', which caps completeness at 3.	3 / 5
Trigger Term Quality	'Gmail', 'emails', and 'NanoClaw' are the natural terms a user would say, but common variations like 'email integration', 'inbox', or file/brand synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	'Gmail integration to NanoClaw' names a specific platform and capability, creating a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	17 / 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: jbaruch/nanoclaw-telegram
Path: .claude/skills/add-gmail/SKILL.md
Commit: 7454673

Reviewed: 17 hours 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.