CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

govisit-get-place-overview

Read the published overview fields for the selected place. Use when an agent needs this published GoVisit evidence through HTTP for an integration or travel decision.

Quality

73%

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 ./skills/govisit-get-place-overview/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured, actionable overview: an exact endpoint with example body, detailed error semantics, and a clean one-level reference to the contract bundle. Its main weaknesses are a metadata-heavy tail (duplicated version digests, licensing) that dilutes token efficiency and a few confusing or non-concrete spots, notably the pagePath sentence and the vague Browser WebMCP invocation.

Suggestions

Trim the "Source and updates" section to a pointer and remove the version digest and canonical-URL duplication already present in the frontmatter, keeping time-sensitive metadata out of the operational body.

Fix the confusing instruction "The HTTP body requires pagePath plus the tool arguments" by stating plainly that the JSON body is the tool arguments, with pagePath as the required field.

Add a concrete request example (e.g., a curl command) or a short Browser WebMCP invocation snippet so both call paths are copy-paste executable.

DimensionReasoningScore

Conciseness

The core sections (Call the tool, Interpret the response) are dense and efficient, but "Source and updates" inlines version digests and release URLs already present in the frontmatter, the intro repeats the description verbatim, and time-sensitive version metadata sits outside any deprecated/old-patterns section. Anchor 3 fits (mostly efficient, some unnecessary content); it is not 2 because no space is spent explaining concepts Claude already knows, and not 4 because the duplicated metadata and licensing tail could be trimmed.

3 / 5

Actionability

The HTTP path is executable: exact endpoint and content type, a copy-paste JSON body, and per-status-code recovery guidance ("429 requires waiting for `Retry-After`"). Anchor 4 fits; it is not 5 because there is no complete request example (e.g., a curl command) and the Browser WebMCP section mentions document.modelContext without a concrete invocation, and not 3 because the primary path is concrete and executable.

4 / 5

Workflow Clarity

The sequence (call the tool, interpret the response, handle errors) is clear with explicit error checkpoints ("`invalid-input` means correct the arguments", Retry-After on 429, avoid unbounded retries). Anchor 4 fits; it is not 5 because the sentence "The HTTP body requires pagePath plus the tool arguments" is confusing (pagePath is itself a tool argument) and there is no final validation checkpoint on the parsed response, and not 3 because error-recovery checkpoints are explicit and the operation is neither destructive nor batch.

4 / 5

Progressive Disclosure

The body is a well-sectioned overview that delegates schemas and defaults to references/contract.json, which exists in the bundle and contains the promised input/output schemas. The reference is one level deep and clearly signaled with a link and a description of its contents, matching anchor 5.

5 / 5

Total

16

/

20

Passed

Description

62%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 clearly states what the skill does and includes an explicit Use-when clause, with strong niche distinctiveness from generic skills. Its weaknesses are limited action coverage (only one named action) and trigger phrasing that leans on jargon ("published GoVisit evidence through HTTP") rather than natural user terms like place details or place information.

Suggestions

Enumerate the concrete capabilities or fields returned (e.g., operating status, opening hours, freshness) so the what-clause lists several specific actions instead of one.

Add natural trigger phrases users would actually say, such as "place details", "place information", or "GoVisit place page", to the Use-when clause.

Reword "needs this published GoVisit evidence through HTTP" into concrete triggering scenarios, e.g., "Use when checking a place's overview, status, or hours before a travel decision."

DimensionReasoningScore

Specificity

"Read the published overview fields for the selected place" names the domain and one concrete action, but lists only that single action rather than several specific capabilities. This matches anchor 3 (domain and 1-2 concrete actions, not comprehensive); it is not 4 because no list of specific actions or covered fields is given, and not 2 because the action and domain are concrete rather than generic.

3 / 5

Completeness

Both parts are explicit: what ("Read the published overview fields for the selected place") and when ("Use when an agent needs this published GoVisit evidence through HTTP for an integration or travel decision"). It is not 5 because the when-triggers are abstract scenarios rather than concrete trigger phrases users would mention, and not 3 because the when is explicitly present, not merely implied.

4 / 5

Trigger Term Quality

The when-clause contains relevant keywords ("GoVisit", "place", "overview", "travel decision") but misses natural variations a user would say, such as "place details" or "place information". Anchor 3 fits (some relevant keywords, missing common variations); it is not 4 because "published GoVisit evidence through HTTP" is jargon-heavy rather than natural user phrasing.

3 / 5

Distinctiveness Conflict Risk

The GoVisit-specific framing ("published GoVisit evidence", place overview) carves a clear niche with low conflict risk against generic skills. It is not 5 because it overlaps with closely related sibling GoVisit tools (e.g., search_places or other page-section tools referenced in the body), matching anchor 4 (mostly distinct, minor overlap risk with closely related skills).

4 / 5

Total

14

/

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

inhotel-io/govisit-toolkit

Path

skills/govisit-get-place-overview/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.