CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

govisit-get-collection-overview

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

Quality

75%

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 ./skills/govisit-get-collection-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.

A well-structured, highly actionable skill body that correctly offloads schemas to a real one-level-deep reference and spells out error handling with feedback loops. Its main weakness is redundancy — the repeated description and duplicated provenance/version metadata consume tokens without adding guidance.

Suggestions

Delete the verbatim re-statement of the frontmatter description under the title and trim 'Source and updates' to the canonical URL and update instruction, dropping the version/digest details already in frontmatter.

Replace 'The HTTP body requires pagePath plus the tool arguments' with a single complete request example (e.g. a curl command with headers and body) and move the Browser WebMCP comparison out of the 'Call the tool' section.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes competence, but pads with repetition: the frontmatter description is restated verbatim, version/digest/canonical-URL are duplicated from frontmatter in 'Source and updates', and 'The HTTP body requires pagePath plus the tool arguments' restates the example. It fits anchor 3 (mostly efficient, some tightening possible) rather than anchor 2 since no section explains concepts Claude already knows.

3 / 5

Actionability

Concrete, executable guidance throughout: exact endpoint and content type, a ready JSON body, and per-status error actions (400/413/415 correct the request, 429 wait for Retry-After, 503 temporarily unavailable). It stops short of anchor 5 because there is no complete copy-paste request example (e.g. a curl or fetch snippet) and response handling is described rather than shown.

4 / 5

Workflow Clarity

The single-task workflow is clearly sequenced (call the tool, then interpret the response) with error-recovery feedback loops (invalid-input means correct the arguments; avoid unbounded retries; wait on Retry-After). Minor gaps keep it below anchor 5: the confusing sentence 'The HTTP body requires pagePath plus the tool arguments' and the Browser WebMCP digression inside the HTTP-call section blur the primary path.

4 / 5

Progressive Disclosure

The body is a concise, well-sectioned overview, and all schema detail is appropriately split into references/contract.json, which exists in the bundle, is clearly signaled ('Read [references/contract.json] for the exact input and output JSON schemas'), and is exactly one level deep. This matches the clear-overview, one-level-deep-references anchor.

5 / 5

Total

16

/

20

Passed

Description

66%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.

A distinct, correctly-scoped description with an explicit use-when clause, but it names only a single capability and offers few natural trigger variations. The when-clause is explicit yet phrased in integration jargon rather than concrete situations a user would voice.

Suggestions

List the concrete capabilities of the tool call (e.g. returns collection title, description, destination, and item count) so the 'what' covers more than one action.

Rewrite the 'Use when' clause with concrete, natural trigger phrases such as 'Use when a task needs a GoVisit destination collection's published overview, item count, or freshness for a travel decision', adding synonyms users would actually say.

DimensionReasoningScore

Specificity

The description names a specific domain and one concrete action ("Read the published overview for the selected destination collection page"), but does not list multiple concrete actions, matching the 1-2-actions anchor. It is above anchor 2 because the action is concrete and domain-locked rather than generic.

3 / 5

Completeness

Both "what" ("Read the published overview for the selected destination collection page") and an explicit "Use when..." clause are present. It falls short of anchor 5 because the when-clause ("needs this published GoVisit evidence through HTTP for an integration or travel decision") is abstract rather than a concrete user-side trigger phrase.

4 / 5

Trigger Term Quality

Relevant keywords like "destination collection page", "published overview", and "GoVisit" are present, but there are no natural synonyms or variations (e.g. "collections page", "destination guide", "collection details"). It fits anchor 3 (some relevant keywords, missing common variations) rather than anchor 4's fuller coverage.

3 / 5

Distinctiveness Conflict Risk

The description is tightly scoped to GoVisit destination collection pages and published-overview reads, giving it a clear niche with distinct triggers and minimal conflict risk with other skills. It clearly matches the anchor 5 example's level of niche specificity.

5 / 5

Total

15

/

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-collection-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.