gog-admin

Workspace Admin operations through gog.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/gog-admin/SKILL.md

Quality

Content

86%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 an exemplary lean operational skill: executable safe-start commands, explicit account/readonly/dry-run/confirmation guardrails for destructive writes, and a well-organized command map that defers syntax to machine-readable contracts. Its only gaps are the absence of inline usage examples for the subcommands and any post-write verification step.

Dimension	Reasoning	Score
Conciseness	The 36-line body contains zero concept explanations and no padding: "Use `gog` for Workspace Admin operations" followed by executable commands and terse safety rules — every token earns its place. Not 4 because there are no instances of over-explanation that could be trimmed.	5 / 5
Actionability	The Safe start block is copy-paste-ready ('gog auth list --check --json --no-input', 'gog schema admin --json', 'gog --readonly --account user@example.com admin --help') and the Commands table names concrete subcommands. Not 5 because actual usage examples for groups/orgunits/users are deferred to --help/schema discovery rather than shown inline, so common cases are not directly covered.	4 / 5
Workflow Clarity	A clear sequence is present: read the shared gog skill first, run safe-start checks, select the account explicitly with '--account', inspect the schema contract, use '--dry-run before supported writes', and 'Confirm the exact account, object, and mutation before any write or delete' — validation checkpoints for destructive writes are explicit, so the destructive-operation cap at 3 does not apply. Not 5 because there is no post-write verification or error-recovery feedback loop.	4 / 5
Progressive Disclosure	A simple, under-50-line skill with no bundle files; sections ('Safe start', 'Commands') are well-organized, and the single reference ('../gog/SKILL.md') is clearly signaled at the top and one level deep. Per the simple-skill scoring note this earns 5; not 4 because no organization gaps or buried content exist.	5 / 5
	Total	18 / 20 Passed

Description

48%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 names a clear, distinct niche (Workspace Admin via the gog CLI) but is too thin: it lists no concrete capabilities and provides no 'use when' trigger guidance, leaving both action coverage and activation conditions to inference. It reads as a label rather than a capability statement.

Suggestions

List the concrete capabilities, e.g. "Manage Google Workspace groups, users, and organizational units through the gog CLI" — this lifts specificity from naming the domain to stating actions.

Add an explicit trigger clause, e.g. "Use when the user asks to create, modify, or inspect Workspace groups, users, or org units" — this moves completeness past the missing-'when' cap of 3.

Include natural synonyms users actually say ("Google Workspace", "Google Admin", "admin console") so trigger matching catches common phrasings beyond just 'Workspace Admin'.

Dimension	Reasoning	Score
Specificity	"Workspace Admin operations" names the domain and tool but lists no concrete actions (no mention of managing groups, users, or org units), matching the anchor 'Names the domain but actions are minimal or generic.' It is not 1 because a real domain and tool are named, and not 3 because no specific action is stated at all.	2 / 5
Completeness	The 'what' is fairly clear (admin operations on Workspace via the gog CLI) but the 'when' is entirely absent — no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. Not 4 because no explicit 'when' exists at all.	3 / 5
Trigger Term Quality	"Workspace Admin" is a relevant domain keyword, but common variations and synonyms ("Google Workspace", "Google Admin", groups, users) are missing, matching anchor 3. Not 2 because the keyword is domain-specific rather than generic; not 4 because no natural variations are covered.	3 / 5
Distinctiveness Conflict Risk	The 'gog' tool name and Workspace Admin scope carve a distinct niche, but the body's reference to '../gog/SKILL.md' implies a family of sibling gog skills with minor overlap risk, matching anchor 4. Not 5 due to family overlap; not 3 because the niche is genuinely distinct rather than merely 'somewhat specific'.	4 / 5
	Total	12 / 20 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: openclaw/gogcli
Path: .agents/skills/gog-admin/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.