CtrlK
BlogDocsLog inGet started
Tessl Logo

gog-maps

Google Maps operations through gog.

58

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/gog-maps/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 a model of a thin wrapper skill: a validated safe-start sequence, a precise command table, and disciplined deferral of detail to --help, the JSON schema, and the parent gog skill. The only gaps are the absence of a single worked example of an actual operation and of explicit error-recovery guidance after a failed check or dry-run.

DimensionReasoningScore

Conciseness

The body is lean and every token earns its place: a short safe-start code block, five one-line bullets, a five-row command table, and a closing pointer to '--help' and 'gog schema ... --json'. It explains nothing Claude already knows and never pads. It clearly matches anchor 5 rather than 4, which would require some over-explanation to trim — none is present.

5 / 5

Actionability

The safe-start block gives copy-paste-ready commands ('gog auth list --check --json --no-input', 'gog schema maps --json', 'gog --readonly --account user@example.com maps --help') and the table pairs each command with its purpose. It stops short of anchor 5 only because no example invocation of an actual operation is shown (e.g. 'gog maps geocode "1600 Amphitheatre Pkwy"'), leaving real-usage syntax to --help; this is 'mostly executable guidance ... with minor gaps' (4), not vague or pseudocode.

4 / 5

Workflow Clarity

The 'Safe start' section gives a clear sequence (verify auth with '--check', read the schema, inspect help) plus explicit pre-write checkpoints: '--readonly' when mutation is forbidden, '--dry-run before supported writes', and 'Confirm the exact account, object, and mutation before any write or delete'. This matches anchor 4 ('clear sequence with most checkpoints present; minor validation gaps'); it misses 5 because there is no error-recovery feedback loop (e.g. what to do when auth --check fails or a dry-run surfaces a problem) and post-write verification is only implied by the shared-rules pointer.

4 / 5

Progressive Disclosure

At roughly 38 lines this is a simple skill with well-organized sections and no bundle files to disclose, so per the simple-skill scoring note it can score 5 on organization alone. It also pushes detail to clearly-signaled, one-level-deep surfaces: 'Read ../gog/SKILL.md first' for shared rules, 'gog maps <command> --help' and 'gog schema maps <command> --json' for per-command contracts — nothing that belongs in a separate file is inlined.

5 / 5

Total

18

/

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 correctly identifies the domain and tool but is bare-bones: it names no concrete operations, includes no 'use when' trigger guidance, and misses natural phrasings like directions, geocoding, or places search. It is clear but under-sells the skill to both discovery and the model deciding when to load it.

Suggestions

Add a 'Use when...' clause naming concrete trigger situations, e.g. 'Use when the user asks about Google Maps, needs directions or travel times, wants to geocode or reverse-geocode an address, or wants to search for places.'

List the concrete operations in the description itself (directions, distance matrices, geocoding, reverse geocoding, places search) instead of the generic phrase 'Google Maps operations', matching the command table already present in the body.

Include natural trigger keywords users would actually say — 'directions', 'route', 'travel time', 'geocode', 'address to coordinates', 'nearby places' — so the skill surfaces on phrased requests rather than only on explicit 'Google Maps' mentions.

DimensionReasoningScore

Specificity

The description "Google Maps operations through gog" names the domain but lists no concrete actions — no geocoding, directions, places search, or distance matrix appear, matching the anchor 'Names the domain but actions are minimal or generic' (e.g. 'Processes PDF files'). A score of 3 would require naming 1-2 concrete operations, which this lacks; a 1 would mean entirely vague language with no domain named, which understates it.

2 / 5

Completeness

The 'what' is present and reasonably clear (Google Maps operations performed through the gog CLI), but there is no 'Use when...' clause or any equivalent trigger guidance, so completeness is capped at 3 per the judging guidelines. It does not reach 4, which requires both 'what' and 'when' with the 'when' merely needing more specificity; and it is above 2 because the 'what' is not vague.

3 / 5

Trigger Term Quality

"Google Maps" is a natural keyword a user would actually say, giving some relevant trigger coverage, but the description misses common variations and synonyms users would phrase requests with — 'directions', 'routes', 'geocoding', 'address to coordinates', 'nearby places', 'maps'. Anchor 3 ('some relevant keywords but missing common variations or synonyms') is the best fit; it is above 2 ('one or two generic keywords') because 'Google Maps' is specific and natural rather than generic.

3 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche — Google Maps, specifically via the 'gog' tool — that is unlikely to trigger for unrelated skills, satisfying 'mostly distinct; minor overlap risk with closely related skills'. It falls short of 5 because the shared 'gog' tool name creates minor overlap with sibling gog-* skills (e.g. other Google services through the same CLI), and without explicit trigger phrases the boundary is drawn only by domain mention.

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.