CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gog-calendar

Google Calendar operations through gog.

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-calendar/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 skill: executable safe-start commands, pre-write safety checkpoints, a scannable command table, and a well-signaled one-level reference to shared gog rules. Its only gaps are the absence of a demonstrated write operation and any post-write verification for destructive commands.

DimensionReasoningScore

Conciseness

The body is lean with zero padding: a 3-command 'Safe start' block, flag guidance as terse bullets, a purpose-per-row command table, and a one-line discovery pointer ('Run gog calendar <command> --help... Do not guess command syntax.'). It assumes Claude's competence and never explains concepts Claude already knows, matching anchor 5.

5 / 5

Actionability

The 'Safe start' commands are concrete and copy-paste ready (e.g. 'gog --readonly --account user@example.com calendar events --today --json --wrap-untrusted'), and the mandated --help/schema discovery path is fully executable. Not 5 because no example of an actual write operation (e.g. a 'create' or 'update' invocation) is shown, leaving the most common cases covered only via discovery rather than example — anchor 4 (minor gaps).

4 / 5

Workflow Clarity

There is a clear sequenced start (auth check → schema contract → read-only events) with explicit pre-write checkpoints: '--dry-run before supported writes' and 'Confirm the exact account, object, and mutation before any write or delete.' Not 5 because destructive commands (delete, delete-calendar) lack a post-write verification step or error-recovery loop; the validation present is pre-write only, matching anchor 4 (most checkpoints, minor validation gaps).

4 / 5

Progressive Disclosure

Well-organized sections ('Safe start', 'Commands') with shared rules factored into a clearly signaled one-level-deep reference ('Read ../gog/SKILL.md first for shared auth, output, safety, and live-write rules.') and flag details delegated to on-demand --help/schema output instead of being inlined. No bundle files exist to nest, and the single external reference is purpose-labeled — anchor 5.

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 names a distinct domain and tool but is a bare stub: it lists no concrete capabilities, includes no "Use when..." trigger guidance, and relies on jargon ("gog") plus one natural phrase ("Google Calendar"). It would rarely be selected on natural user language alone.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when the user mentions Google Calendar, events, meetings, appointments, invites, or scheduling/free-busy times.'

Enumerate 3-4 concrete operations instead of the generic word 'operations', e.g. 'Create, update, and delete events; check free/busy and conflicts; respond to invitations; manage calendars.'

Include common user synonyms (events, meetings, scheduling) so the description matches how users actually phrase calendar requests rather than only the product name.

DimensionReasoningScore

Specificity

"Google Calendar operations through gog" names the domain and tool but "operations" is generic — no concrete actions like create/update/delete events or free/busy checks are listed. This matches anchor 2 (domain named, actions minimal or generic); it is not 3 because no concrete action is enumerated, and not 1 because the domain and tool are explicitly named.

2 / 5

Completeness

The description provides only a domain-level "what" ("Google Calendar operations") with no "when" guidance at all — the "Use when..." clause is entirely missing. It sits between anchor 2 (vague what, no when) and anchor 3 (clear what, no when): the what is more informative than pure fluff but names no concrete operation, so per boundary guidance it scores the even value 2; the missing "Use when..." clause also caps it below 4.

2 / 5

Trigger Term Quality

"Google Calendar" is a natural phrase users would say, but "gog" is tool-specific jargon and common synonyms (events, meetings, appointments, schedule, invites) are absent. Matches anchor 3 (some relevant keywords, missing common variations); not 4 because keyword coverage is thin rather than merely missing a few terms.

3 / 5

Distinctiveness Conflict Risk

"Google Calendar" carves a clear, distinct niche with a specific tool, so overlap risk is minor — mainly with sibling gog module skills (e.g., Gmail, Drive). Not 5 because there are no explicit trigger phrases and "operations" is broad enough to brush against other calendar/scheduling skills.

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

Path

.agents/skills/gog-calendar/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.