CtrlK
BlogDocsLog inGet started
Tessl Logo

webshop-initial-search

Performs the first search on an e-commerce platform using keywords derived from parsed user requirements. Use when starting product discovery from a user instruction or when previous search results are insufficient and a new query is needed. It formulates a search query from the criteria (e.g., '24 pack of 7.5 ounce bottles of non-gmo classic tonic') and executes the search[] action, returning the initial result page.

71

Quality

89%

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

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.

A lean, highly actionable instruction body for a simple agent skill: it gives exact parsing categories, query-construction rules, the concrete action format, and a complete traced example. The only tightening opportunities are the duplicated example query and the absence of an empty-results recovery path, neither of which materially hurts usability.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence — no concept explanations, just directives — but the example query from step 2 is repeated verbatim in the Example section, and the 'Next Steps' narration ('proceed to evaluate the search results...') could be trimmed or folded into step 4.

4 / 5

Actionability

Fully executable guidance: exact criteria-extraction categories with worked examples, the precise action syntax `search[<keywords>]`, an explicit rule to exclude the price constraint, and a copy-paste-ready traced example (`search[24 pack of 7.5 ounce bottles of non-gmo classic tonic]`).

5 / 5

Workflow Clarity

Clear four-step sequence (parse → formulate → execute → next steps) with the price-constraint handling explicitly deferred to later validation, but there are no explicit checkpoints or feedback loops (e.g., what to do if the search returns no results) to reach the score-5 anchor.

4 / 5

Progressive Disclosure

A sub-50-line, single-purpose skill with no bundle files and no need for external references; the '# Instructions' / '## Example' sections are well-organized and the single example is appropriately placed, which per the rubric's simple-skill guidance merits full marks.

5 / 5

Total

18

/

20

Passed

Description

87%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 strong description: third-person, concrete, with an explicit 'Use when...' clause covering both the primary trigger and the retry case. It clearly scopes the skill to the first search action and includes a worked example of the query formulation. Only minor gains available from broader trigger synonyms.

DimensionReasoningScore

Specificity

Lists several concrete third-person actions — 'formulates a search query from the criteria', 'executes the search[] action, returning the initial result page' — but they all describe a single narrow action chain rather than the multiple distinct capabilities of the score-5 anchor.

4 / 5

Completeness

Explicitly answers both what ('Performs the first search... formulates a search query... executes the search[] action, returning the initial result page') and when ('Use when starting product discovery from a user instruction or when previous search results are insufficient and a new query is needed') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage — 'first search', 'starting product discovery', 'user instruction', 'previous search results are insufficient' — phrases a user or agent would plausibly say, though common variants like 'shopping', 'online store', or 'find products' are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — the initial search on an e-commerce platform — and explicitly distinguishes itself from related situations ('previous search results are insufficient'), minimizing conflict with sibling skills like result-clicking or search-refinement.

5 / 5

Total

18

/

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
zjunlp/SkillNet
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.