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

73%

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 ./.claude/skills/add-gmail/SKILL.md

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.

The body is highly actionable with executable commands, a clearly sequenced phased workflow, and explicit validation plus troubleshooting feedback loops. It is concise and well-organized as a self-contained file with no external bundle references.

Dimension	Reasoning	Score
Conciseness	The body is command-driven and assumes Claude's competence, with only a few justified explanatory asides (e.g., why stale agent-runner copies must be cleared), fitting the 'efficient, minor over-explanation' anchor rather than the fully lean level 5.	4 / 5
Actionability	It provides copy-paste-ready, executable commands throughout (git fetch/merge, npm install/build, npx vitest, launchctl/systemctl) covering both tool-only and channel modes, matching the 'fully executable, copy-paste ready' anchor.	5 / 5
Workflow Clarity	A clear phased sequence (Pre-flight → Apply → Setup → Verify) with explicit validation checkpoints ('All tests must pass… before proceeding', 'Verify with ls ~/.gmail-mcp/credentials.json') and feedback loops (merge-conflict resolution, auth fallback) matches the level-5 anchor; destructive ops have validation so no cap applies.	5 / 5
Progressive Disclosure	No bundle files exist and the skill is a well-sectioned single file (Phases, Troubleshooting, Removal) with no nested references, fitting 'good structure, minor organization gaps'; at over 50 lines the simple-skill exception does not push it to 5.	4 / 5
	Total	18 / 20 Passed

Description

58%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 concretely states what the skill does across both modes but lacks an explicit 'Use when…' trigger clause, which caps trigger quality and completeness. It is distinctive and largely free of fluff.

Suggestions

Add an explicit trigger clause such as 'Use when adding Gmail to NanoClaw, wiring up email read/send tools, or setting up Gmail as an inbound channel.'

Include natural synonyms users might say (e.g. 'inbox', 'OAuth', 'Gmail API') to broaden trigger-term coverage.

Tighten the mode description so the two configurations read as a concise enumeration of capabilities rather than a sentence.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete actions — 'reads/sends emails', 'emails can trigger the agent, schedule tasks, and receive replies', 'GCP OAuth setup', 'implements the integration' — matching the 'several specific actions, minor gaps' anchor rather than the fully comprehensive level 5.	4 / 5
Completeness	The 'what' is clear but there is no 'Use when…' clause, so per the rubric a missing explicit trigger caps completeness at 3 ('clear what, when missing or only weakly implied').	3 / 5
Trigger Term Quality	Only the natural terms 'Gmail' and 'emails' appear; no trigger phrases or synonyms, fitting 'some relevant keywords but missing common variations' rather than the broader coverage at level 4.	3 / 5
Distinctiveness Conflict Risk	The niche 'Add Gmail integration to NanoClaw' is mostly distinct with only minor overlap risk against related email skills, matching anchor 4 rather than the fully conflict-free level 5.	4 / 5
	Total	14 / 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: 1 day 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.