The body is an exemplary lean workflow: executable commands, a safe detect-preview-apply sequence with explicit validation gates, and substantive guardrails against false-positive merges. No changes needed.

Dimension	Reasoning	Score
Conciseness	The ~20-line body is lean and assumes Claude's competence: no explanation of what Google Contacts is, no library comparisons, no padding — every line either commands, guards, or directs. Matches the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	Fully executable copy-paste-ready gog commands with concrete flags (--readonly, --json, --wrap-untrusted, --dry-run, --resource) cover the common cases, and the closing guidance ('Prefer exact normalized email or phone evidence and retain the richest contact as the primary resource') is specific and actionable.	5 / 5
Workflow Clarity	A clearly sequenced 4-step workflow (readonly detection -> present groups with conflict flags -> dry-run preview -> apply only approved groups) with explicit validation checkpoints and a --force guard. The destructive/batch cap at 3 does not apply because verification steps (readonly pass, --dry-run, explicit approval) are present throughout.	5 / 5
Progressive Disclosure	The skill is under 50 lines with a single well-organized workflow and no bundle files; the only references are one-level-deep sibling skills, clearly signaled ('Read ../gog/SKILL.md and ../gog-contacts/SKILL.md first'), so nothing needs splitting out.	5 / 5
	Total	20 / 20 Passed

Description

57%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 is concise, third-person, and highly distinctive, with a clear statement of what the skill does. Its main weakness is the complete absence of 'when to use' trigger guidance and missing natural synonyms like 'merge' or 'dedupe' that users would actually say.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to find, review, or merge duplicate Google Contacts, or mentions cleaning up their contacts.'

Include natural trigger synonyms such as 'merge', 'dedupe', and 'contacts list' so the description matches how users actually phrase the request.

Name the concrete outcome actions (merge duplicate contacts, choose the primary record) instead of the generic 'guarded cleanup' to raise specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('Google Contacts') and 1-2 actions ('duplicate review', 'guarded cleanup'), but does not enumerate what cleanup entails (merge, delete, field matching), matching the 'domain and 1-2 concrete actions' anchor rather than the 'several specific actions' anchor above.	3 / 5
Completeness	The 'what' is clear (duplicate review and guarded cleanup of Google Contacts), but there is no 'Use when...' clause or equivalent trigger guidance, which the rubric explicitly caps at 3. It is not a 4 because the 'when' is entirely missing rather than weakly implied.	3 / 5
Trigger Term Quality	'Google Contacts', 'duplicate', and 'cleanup' are natural user phrases, but common variations users would say — 'merge', 'dedupe', 'contacts list' — are absent, matching 'some relevant keywords but missing common variations' rather than the fuller coverage of a 4.	3 / 5
Distinctiveness Conflict Risk	'Google Contacts duplicate review and guarded cleanup with gog' carves out a clear niche with distinct triggers (contacts, duplicates, gog) and minimal overlap with other skills; it would not fire for the wrong skill.	5 / 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: openclaw/gogcli
Path: .agents/skills/gog-contacts-cleanup/SKILL.md
Commit: 414e2ff

Reviewed: 3 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.