CtrlK
BlogDocsLog inGet started
Tessl Logo

gog-drive

Google Drive operations through gog.

56

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

The body is an exemplary lean operations index: executable safe-start commands, a compact command table, explicit safety gates for writes and deletes, and disciplined delegation of syntax to --help and gog schema rather than guessing. The only gaps are the absence of per-command usage examples beyond ls, no error-recovery loop, and reliance on an out-of-bundle relative reference.

DimensionReasoningScore

Conciseness

Every line is operational: three safe-start commands, a one-line purpose per command, and delegation of flag details to '--help' and 'gog schema'. No concept explanations or padding exist, matching 'Lean and efficient; assumes Claude's competence; every token earns its place'.

5 / 5

Actionability

The safe-start block is copy-paste ready and the discovery pattern 'gog drive <command> --help' is executable, but only one command (ls) has an actual invocation example; the other 27 commands have purposes without usage. Fits 'Mostly executable guidance; concrete code or commands with minor gaps' rather than level 5, which requires examples covering the common cases.

4 / 5

Workflow Clarity

A clear startup sequence (auth check, schema inspection, read-only ls) with explicit safety checkpoints for the destructive commands offered: '--readonly', '--dry-run before supported writes', and 'Confirm the exact account, object, and mutation before any write or delete'. Not level 3 because validation guidance is explicit despite destructive/batch commands; not level 5 because there is no error-recovery feedback loop (fix-and-retry) for failed operations.

4 / 5

Progressive Disclosure

The body is a well-organized overview that delegates detail to runtime discovery (--help, gog schema) and one clearly signaled reference (../gog/SKILL.md). However, no bundle files exist, the external relative path sits outside the skill directory, and the 28-command table is inline reference material. Fits 'Good structure; most content is appropriately placed; minor organization gaps' rather than level 5's well-signaled bundle references.

4 / 5

Total

17

/

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 is concise and names a distinct domain, but it stops at that: 'operations' is generic, no concrete capabilities are listed, and there is no 'Use when...' trigger guidance. It reads more like a label than a triggerable skill description.

Suggestions

Add a 'Use when...' trigger clause, e.g. 'Use when the user mentions Google Drive, Drive files, shared drives, or asks to upload, download, share, or search Drive content.'

Replace the generic 'operations' with 3-5 concrete actions (upload, download, search, share, move files) so the 'what' is explicit.

Include natural synonyms and product vocabulary users actually say (e.g., 'Google Drive', 'Drive', 'shared drive') to strengthen trigger coverage and distinctiveness.

DimensionReasoningScore

Specificity

The description names the domain ("Google Drive") but the only action word is the generic "operations"; no concrete capabilities like upload, share, search, or download are stated. This matches the anchor 'Names the domain but actions are minimal or generic' rather than level 3, which requires 1-2 concrete actions.

2 / 5

Completeness

There is a clear domain-level 'what' (Google Drive operations via gog) but no 'when' clause whatsoever, which caps completeness at 3 per the judging guidelines. Not level 4 because no trigger guidance is present even weakly.

3 / 5

Trigger Term Quality

"Google Drive" is a specific, natural phrase users would say, but it is essentially the only trigger term; common variations like "Drive files", "upload to Drive", or "shared drive" are missing. Not level 2 because the keyword is specific and natural, unlike the generic 'Works with files'.

3 / 5

Distinctiveness Conflict Risk

"Google Drive" carves a clear niche with minimal conflict risk, but the terse phrasing provides no disambiguating triggers against closely related sibling skills (e.g., other gog-backed Google services). Fits 'Mostly distinct; minor overlap risk with closely related skills' rather than level 5, whose example earns distinctiveness through explicit trigger phrases.

4 / 5

Total

12

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
openclaw/gogcli
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.