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.

69

Quality

87%

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

85%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 tight, actionable, well-sequenced instruction skill whose body earns nearly every token and whose worked example is genuinely instructive. The main defect is structural: a useful reference file ships in the bundle but is orphaned — never referenced from SKILL.md — so its parsing heuristics and deterministic tiebreak rule are undiscoverable, and the body's vaguer 'most relevant or cost-effective' guidance silently diverges from it.

Suggestions

Add a one-line pointer in the body (e.g., under Core Process: 'See [evaluation_logic.md](references/evaluation_logic.md) for observation parsing rules and the deterministic product-selection algorithm') so the bundled reference is discoverable.

Reconcile the selection rule: the body says 'choose the one that appears most relevant or cost-effective' while the reference specifies sort-by-price ascending — state the tiebreak explicitly in the body or defer clearly to the reference.

Show the exact fallback syntax (`search[<new keywords>]`) and, ideally, a brief no-match example so the fallback branch is as executable as the success path.

DimensionReasoningScore

Conciseness

The ~45-line body is lean and assumes Claude's competence: no concept explanations, no padding, and every section (process, output format, worked example) is functional. It matches anchor 5; anchor 4's 'minor instances of over-explanation' does not apply since nothing explains what Claude already knows — the brief 'When to Use' section is a restatement, not over-explanation.

5 / 5

Actionability

Gives exact executable action syntax ("click[B09NYFDNVX]", "click[Next >]") plus a fully worked Thought/Action example, matching anchor 4's 'mostly executable guidance with minor gaps'. Not anchor 5: the fallback branch only says 'consider using the `search` action with refined keywords' without the concrete `search[...]` syntax, and no example covers the no-match case.

4 / 5

Workflow Clarity

The Core Process is a clear four-step sequence (parse observation, extract requirements, evaluate each product against price/keyword criteria, act) with an explicit error-recovery branch ('If no suitable product is found... use the `search` action... or clicking `Next >`'). This matches anchor 5's clear sequence with explicit validation (per-product criteria checks) and a feedback loop; anchor 4 would require missing checkpoints, which are present.

5 / 5

Progressive Disclosure

The body itself is well-sectioned, but the bundle contains references/evaluation_logic.md — with substantive, non-duplicated guidance ([SEP] parsing rules, keyword extraction heuristics, sort-by-price tiebreak) — that the body never mentions or links. Per the rubric guideline to score against the actual bundle structure, this matches anchor 3 ('references present but not clearly signaled'); anchor 4 would require the reference to be mostly clearly signaled, and it is not signaled at all.

3 / 5

Total

17

/

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 strong description that explicitly states both capability and trigger context in third person with no fluff or over-claims. Trigger terms are natural and the niche is well-scoped, though broader synonym coverage and a slightly sharper domain declaration would make it airtight.

DimensionReasoningScore

Specificity

Quotes several concrete actions — "Evaluates product listings against user requirements such as price limits and feature matches", "analyzes product titles, prices, and brief descriptions to rank and choose the best match" — which matches anchor 4 (several specific actions, minor gaps). It falls short of anchor 5 because verbs like "evaluates"/"analyzes" are moderately generic and the action list is not comprehensive (e.g., no mention of fallback actions like refining a search).

4 / 5

Completeness

Clearly answers both questions: what — "Evaluates product listings against user requirements such as price limits and feature matches to identify viable options" — and when — "Use when you are on a search results page containing multiple products and need to select the most promising candidate for detailed inspection." This matches anchor 5 (explicit what AND when with concrete trigger phrases); anchor 4's 'when could be more explicit' does not apply since the trigger context is fully spelled out.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "search results page", "product listings", "price limits", "feature matches", "multiple products" — terms a user would plausibly say when needing this skill. Not anchor 5 because common synonyms and variations (e.g., "shopping", "e-commerce", "buy", "webshop") are absent.

4 / 5

Distinctiveness Conflict Risk

The scope is well-defined to product selection on search results pages, making it mostly distinct as in anchor 4. It stops short of anchor 5 because the phrasing does not name the web-shopping domain explicitly, leaving minor overlap risk with generic search/browse or product-comparison 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.

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.