CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

govisit-list-destination-categories

Read the published category projection shown on the destination page. Use when an agent needs this published GoVisit evidence through HTTP for an integration or travel decision.

Quality

76%

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-list-destination-categories/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 gives fully executable call instructions with explicit error-recovery guidance and cleanly offloads schemas to an existing one-level reference file. The main weakness is token efficiency: duplicated metadata (version, digest, canonical URL, description) and a few convoluted, overlapping sentences about pagePath and browser context could be trimmed without losing information.

Suggestions

Remove duplicated metadata from the body — the canonical URL, version string, and source digest already appear in the frontmatter and need not be restated in prose in 'Source and updates'.

Delete the verbatim repeat of the frontmatter description as the opening paragraph, and merge the pagePath rules scattered across the intro paragraph and the first bullet into one statement.

Replace the fuzzy sentence "The HTTP body requires pagePath plus the tool arguments" with a single precise statement, e.g., "The JSON body is the tool's input; pagePath is the only required field."

DimensionReasoningScore

Conciseness

The operational guidance is dense and assumes competence (no explanation of what HTTP or JSON is), but there is noticeable redundancy: the frontmatter description is repeated verbatim as the body intro, the canonical URL and version/source-digest each appear twice, and sentences like "The HTTP body requires pagePath plus the tool arguments" and "Browser WebMCP obtains this context from the loaded page and does not take pagePath" are convoluted restatements. This fits 'mostly efficient but could be tightened' better than 4's 'minor instances'.

3 / 5

Actionability

The call is concretely specified — "Make one HTTPS POST request to https://govisit.ai/api/tools/v1/list_destination_categories with Content-Type: application/json" plus a copy-paste-ready example body — and error handling maps each code to an action (400/413/415 correct the request, 429 wait for Retry-After). It falls short of 5 because there is no example response, no complete request command (e.g., curl), and input/output details are delegated entirely to the contract file.

4 / 5

Workflow Clarity

This is a simple single-task skill (one HTTP call then interpretation) and the single action is unambiguous: exact endpoint, content type, and body, followed by explicit per-error feedback loops ("invalid-input means correct the arguments", "429 requires waiting for Retry-After", "Avoid unbounded retries"). Per the simple-skill guideline this earns 5; the operation is read-only so no validation checkpoint is required.

5 / 5

Progressive Disclosure

The body is a well-sectioned overview (call, interpret, browser variant, updates, licensing) that delegates the input/output schemas to a real, clearly signaled one-level-deep reference: "Read [references/contract.json](references/contract.json) for the exact input and output JSON schemas" — the file exists in the bundle. This matches 'clear overview with well-signaled one-level-deep references; content appropriately split'.

5 / 5

Total

17

/

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 answers what the skill does and when to use it, with a distinct GoVisit niche. Its weaknesses are thin action coverage (a single read action) and trigger language that leans on internal jargon ("published category projection", "published GoVisit evidence") rather than natural user phrases.

Suggestions

List the concrete capabilities more fully, e.g., "Lists the published destination categories (name, id, ordering, count) for a GoVisit destination page and reads them over HTTPS" — this moves specificity from one action to several.

Replace jargon triggers with natural phrases users would say, e.g., "Use when the user mentions GoVisit, destination categories, or needs category data for a travel-planning integration."

Tighten the when-clause to concrete trigger contexts (integration building, travel decision support) and drop the abstract "published GoVisit evidence" phrasing.

DimensionReasoningScore

Specificity

"Read the published category projection shown on the destination page" names the domain and one concrete action, but no additional actions or capabilities are listed. It matches the anchor 'names domain and 1-2 concrete actions, but not comprehensive' and falls short of 4, which expects several specific actions.

3 / 5

Completeness

Both parts are explicit: the what ("Read the published category projection shown on the destination page") and an explicit when ("Use when an agent needs this published GoVisit evidence through HTTP for an integration or travel decision"). It does not reach 5 because the when-clause's triggers are abstract ("needs this published GoVisit evidence") rather than concrete phrases a user would say.

4 / 5

Trigger Term Quality

Relevant terms like "destination page", "categories", "GoVisit", and "travel decision" are present, but jargon phrases such as "published category projection", "published GoVisit evidence", and "through HTTP" are not natural user phrasings, and common variations (e.g., "destination categories", "things to do", "list categories") are missing. This sits at 'some relevant keywords but missing common variations or synonyms' rather than 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

The GoVisit/destination-page framing carves out a clear niche with minimal conflict against unrelated skills. It stops short of 5 because "integration or travel decision" is a broad trigger that could overlap with sibling GoVisit tool skills or general travel-planning 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-list-destination-categories/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.