CtrlK
BlogDocsLog inGet started
Tessl Logo

webshop-product-evaluator

Evaluates product listings against user requirements such as price limits and feature matches to identify viable options. Use when you are on a search results page containing multiple products and need to select the most promising candidate for detailed inspection. The skill analyzes product titles, prices, and brief descriptions to rank and choose the best match.

65

Quality

77%

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 ./experiments/src/skills/webshop/webshop-product-evaluator/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 concise, actionable instruction skill with a clear sequenced workflow and a concrete worked example. The main gap is an unlinked reference file whose parsing and selection logic would benefit from being surfaced in the body.

Suggestions

Add a one-line pointer in the Core Process or a References section, e.g. 'See [evaluation_logic.md](references/evaluation_logic.md) for parsing rules and product-scoring heuristics', so the existing reference is discoverable.

Show a brief fallback example (e.g. a Thought/Action pair using search[new keywords] or click[Next >]) so the no-match branch is as concrete as the match branch.

State the tie-break explicitly in the body (sort suitable products by price ascending and pick the cheapest) rather than only in the reference, since it drives the final selection.

DimensionReasoningScore

Conciseness

The body is lean and avoids explaining concepts Claude already knows, presenting only task-specific steps and a worked example; the example somewhat duplicates the process narrative, keeping it just shy of a 5.

4 / 5

Actionability

Provides concrete executable actions (click[B09NYFDNVX], search, Next >) and a fully worked Thought/Action example, but the fallback paths (search refinement, Next) are mentioned rather than exemplified.

4 / 5

Workflow Clarity

A clear four-step sequence (Parse -> Extract -> Evaluate -> Act) with the evaluation step acting as an implicit checkpoint and tie-breaking decision rule; no explicit validation step, but the operation is non-destructive so the destructive-cap does not apply.

4 / 5

Progressive Disclosure

Sections are well organized, but references/evaluation_logic.md contains complementary parsing rules and scoring heuristics that elaborate on the body yet are never linked or signaled from SKILL.md, matching the 'references present but not clearly signaled' anchor.

3 / 5

Total

15

/

20

Passed

Description

83%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 well-crafted description that clearly states both capability and trigger conditions in third person, with concrete actions and natural trigger language. Minor room for improvement in keyword synonym coverage and niche distinctiveness.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Evaluates product listings against user requirements', 'analyzes product titles, prices, and brief descriptions to rank and choose the best match') rather than generic phrasing, but coverage is not exhaustive enough for a 5.

4 / 5

Completeness

Explicitly states both what the skill does ('Evaluates product listings... to identify viable options', 'analyzes... to rank and choose') and when to use it ('Use when you are on a search results page containing multiple products and need to select the most promising candidate'), matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural phrases a user would say ('search results page', 'multiple products', 'select the most promising candidate', 'price limits', 'feature matches') with good coverage, though common synonyms like 'shopping' or 'buy' are absent.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (web shopping search-result product evaluation) with distinct triggers, leaving only minor overlap risk with general browsing/search skills; not quite a 5 because the niche could brush against broader product-search skills.

4 / 5

Total

17

/

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.

Validation16 / 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.