CtrlK
BlogDocsLog inGet started
Tessl Logo

gog-gmail

Gmail operations through gog.

55

Quality

69%

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-gmail/SKILL.md
SKILL.md
Quality
Evals
Security

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 CLI-wrapper skill: copy-paste safe-start commands, explicit safety gates for writes, a complete command overview, and disciplined deferral of syntax detail to --help and the machine-readable schema. Its only soft spots are the absence of a worked write-operation example and any error-recovery guidance when the auth check fails.

DimensionReasoningScore

Conciseness

The body is entirely lean: three executable safe-start commands, five one-line safety rules, a compact command table, and a pointer to --help/schema. It never explains what Gmail is or how the tool works; every token earns its place, matching anchor 5.

5 / 5

Actionability

The safe-start block ("gog auth list --check --json --no-input", "gog --readonly --account user@example.com gmail search 'newer_than:7d' --max 10 --json --wrap-untrusted") is copy-paste ready, and "Run `gog gmail <command> --help`" plus "gog schema gmail <command> --json" give exact paths to every command contract. The minor gap keeping it below anchor 5 is that no write operation (e.g. send or trash) has a worked example.

4 / 5

Workflow Clarity

The safe start sequences validation-on-entry (auth "--check" -> schema -> readonly search) and the rules "use `--dry-run` before supported writes" and "Confirm the exact account, object, and mutation before any write or delete" supply checkpoints for the destructive and batch commands — so the ≤3 cap for missing validation does not apply. It sits below anchor 5 only because there is no error-recovery loop (e.g. what to do when the auth check fails).

4 / 5

Progressive Disclosure

The body is ~55 lean, well-organized lines (Safe start, Commands) with no bundle files to split; its single reference — "Read `../gog/SKILL.md` first" — is one level deep and clearly signaled, and the command table defers per-command detail to `--help`/`schema`. This matches the simple-skill pattern that scores 5 on well-organized sections alone.

5 / 5

Total

18

/

20

Passed

Description

40%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 extremely terse: it identifies the domain and tool but lists no concrete capabilities and provides zero trigger guidance for when the skill should be used. It is distinct as a Gmail skill, but as a routing description it is under-specified.

Suggestions

List 3-4 concrete capabilities in the description, e.g. "Search, read, send, reply, forward, label, and trash Gmail messages and threads through gog."

Add an explicit trigger clause, e.g. "Use when the user asks to read, search, send, or organize email in Gmail."

Include natural user vocabulary beyond the product name — "email", "inbox", "send email", "drafts" — so the description matches how users actually phrase requests.

DimensionReasoningScore

Specificity

"Gmail operations through gog" names the domain and tool, but the only action word is the generic "operations" — no concrete actions (send, search, label, trash) are listed. This matches anchor 2 ("Names the domain but actions are minimal or generic"), not anchor 3, which requires 1-2 concrete actions.

2 / 5

Completeness

The description gives only a vague 'what' ("Gmail operations") with no 'when' — there is no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3, and the vague 'what' pulls it to anchor 2 ("Has a vague 'what' and no 'when'").

2 / 5

Trigger Term Quality

"Gmail" is a strong natural keyword and "gog" names the tool, but common phrases users would actually say — "email", "send email", "inbox", "search mail", "labels" — are missing. Anchor 3 ("some relevant keywords but missing common variations or synonyms") is the closest fit.

3 / 5

Distinctiveness Conflict Risk

"Gmail" carves out a clear niche that is unlikely to trigger the wrong skill; the only overlap risk is with sibling gog-* skills (e.g. gog-drive, gog-calendar). Anchor 4 ("Mostly distinct; minor overlap risk") fits better than anchor 5, whose exemplar includes explicit distinct triggers.

4 / 5

Total

11

/

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.