CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gog

Use the gog CLI when Google connectors lack an operation, shell automation needs stable JSON, or local Google auth needs inspection. Shared account, auth, output, and safety guidance for all gog service skills.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

This is a strong, highly actionable skill body: concrete executable commands dominate, safety guards are woven into examples rather than stated abstractly, and fragile flows include real validation and recovery guidance. The remaining improvements are structural — moving the deep reauth procedure out of the overview — and tightening a few explanatory paragraphs.

DimensionReasoningScore

Conciseness

The body is dense with commands and non-obvious operational gotchas (the mandatory `-J` flag, UTF-16 range resolution, silent scope narrowing) with no padding about concepts Claude already knows. A few sections could still be tightened, such as the `--fields`/`--select` aliasing rules and the length of the browser-reauth walkthrough, matching anchor 4 rather than the lean anchor 5.

4 / 5

Actionability

Nearly every section is copy-paste-ready: Fast Path diagnostics, guarded command invocations, complete read examples across gmail/calendar/drive/docs/sheets/contacts, write commands including tab and range targeting, first-class reply commands, and discovery commands. Placeholders like `<messageId>` are appropriately parameterized and the common cases are covered.

5 / 5

Workflow Clarity

The reauth workflow is explicitly sequenced with validation checkpoints and error-recovery loops (verify `response_type` before using the URL, require both account validity and scope breadth, restart the CLI leg rather than reusing a stale URL). The writes section has protective checkpoints (--dry-run, --readonly, --force discipline, trash over batch delete) but post-write verification for batch/destructive operations is advisory rather than an explicit checkpoint, so it fits anchor 4.

4 / 5

Progressive Disclosure

Flag-level detail is delegated to runtime discovery (`gog schema`, `--help`, generated `docs/commands/`) with a clearly signaled Docs section listing one-level-deep paths, and sections are well organized. However, the ~70-line browser-driven reauth subsection is specialized procedural content inlined in the overview that would fit better in a separate reference file, matching anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

71%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 solid umbrella-skill description with an explicit, well-structured trigger clause and a clearly named tool niche. Its main weakness is that it operates entirely at the meta level — no service names or concrete operations appear, so users phrasing needs as "gmail", "Google Drive", or "sheets" would not naturally match it.

Suggestions

Include the service names users would actually say (Gmail, Drive, Calendar, Docs, Sheets, Contacts) in the description so natural phrases like "search my gmail" or "update a Google Sheet" match the trigger terms.

Add one clause of concrete capabilities (e.g., reading mail and calendar, writing to Docs and Sheets) so the "what" states what can be done, not just that the file holds shared guidance.

DimensionReasoningScore

Specificity

Names the tool and several concrete usage contexts ("Google connectors lack an operation", "shell automation needs stable JSON", "local Google auth needs inspection") plus the skill's contents ("account, auth, output, and safety guidance"), but never enumerates the underlying capabilities (mail, calendar, docs, sheets operations), so it falls short of the comprehensive anchor 5.

4 / 5

Completeness

Both parts are explicit: a concrete three-clause "when" and a "what" ("Shared account, auth, output, and safety guidance for all gog service skills"). The "what" is accurate but stays meta for an umbrella skill, so it does not reach anchor 5's clearly stated concrete capabilities.

4 / 5

Trigger Term Quality

Relevant keywords like "gog CLI", "Google connectors", and "Google auth" are present, but the description omits every service name (Gmail, Drive, Calendar, Docs, Sheets) that a user would naturally say when needing this skill, which is more than the "a few natural terms missing" of anchor 4.

3 / 5

Distinctiveness Conflict Risk

The description is tied to a named niche CLI with distinct triggers (connector feature gaps, stable JSON for automation, auth inspection), giving it a clear niche with minimal conflict risk against generic Google skills.

5 / 5

Total

16

/

20

Passed

Validation

100%

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/SKILL.md

Reviewed

Table of Contents

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.