gog-meet

Google Meet operations through gog.

Quality

68%

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-meet/SKILL.md

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is lean, executable, and well-organized, with strong conciseness, actionability, and progressive disclosure. Its only gap is workflow clarity: destructive operations (end, update) lack an explicit validate→fix→retry feedback loop, keeping it from a perfect score.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no concept explanations, defers details to `--help` and `gog schema ... --json`, and every line earns its place. Not 2 because there is no unnecessary explanation or padding to tighten.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands with concrete flags (e.g., `gog --readonly --account user@example.com meet --help`) and a command table. Not 2 because these are real executable commands, not pseudocode or incomplete guidance.	3 / 3
Workflow Clarity	A Safe start sequence (auth check, schema, readonly help) and pre-write confirmations ("Confirm the exact account, object, and mutation before any write or delete", "--dry-run before supported writes") are present, but there is no explicit validate→fix→retry feedback loop for destructive commands (end, update). Not 1 because steps and verification prompts exist; not 3 because feedback-loop checkpoints for destructive operations are only implicit.	2 / 3
Progressive Disclosure	Under 50 lines with no bundle files, well-organized into Safe start and Commands sections, with one-level-deep references clearly signaled (`../gog/SKILL.md`, `--help`, `gog schema ... --json`). Per the simple-skill scoring note this earns a 3. Not 2 because organization is clear and there are no nested/deep references.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 and names a specific domain, but it relies on the vague word "operations", omits any "Use when" trigger guidance, and does not enumerate concrete actions. It caps out at 2 across all dimensions and would benefit from explicit trigger terms and specific capability verbs.

Suggestions

Add a "Use when..." trigger clause naming natural user phrases (e.g., 'Use when creating or ending Google Meet calls, listing participants, or reviewing call history').

Replace the vague word "operations" with concrete actions (e.g., 'Create and end Google Meet meetings, get space details, list participants and call history').

Include common natural-term variations (meetings, video calls, conference) alongside "Google Meet" to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	"Google Meet operations through gog." names a concrete domain and tool but uses the vague word "operations" rather than listing concrete actions (create, end, get, history). Not 1 because a specific domain/tool is named; not 3 because no multiple concrete actions are enumerated.	2 / 3
Completeness	States what the skill does (Google Meet operations) but has no "Use when..." trigger clause, so per the rubric guideline completeness is capped at 2. Not 1 because the "what" is present; not 3 because the "when" is entirely missing rather than explicit.	2 / 3
Trigger Term Quality	"Google Meet" is a natural term users say, but coverage is thin — no common variations (meetings, video calls, conference) and "gog" is internal tool jargon. Not 1 because a natural keyword is present; not 3 because common variations are missing.	2 / 3
Distinctiveness Conflict Risk	"Google Meet" is a clear niche, but "operations" is generic and the body reveals a sibling gog-family skill, creating overlap risk. Not 1 because the niche is specific; not 3 because the thin, generic trigger language does not make it cleanly distinct from siblings.	2 / 3
	Total	8 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: openclaw/gogcli
Path: .agents/skills/gog-meet/SKILL.md
Commit: 1dbd820

Reviewed: about 23 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.