CtrlK
BlogDocsLog inGet started
Tessl Logo

webshop-search-formulator

This skill generates effective search keywords based on parsed product criteria. It is triggered after query parsing, when the agent needs to perform an initial product search on an e-commerce platform. The skill takes structured attributes (e.g., 'women's size 5 patent-beige high heel') and produces a concise, platform-appropriate search string designed to return relevant results, balancing specificity with recall.

64

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 ./experiments/src/skills/webshop/webshop-search-formulator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 is concise and well-organized with a useful worked example, but it has two real defects: the Action Format section is truncated — it promises 'the exact format' and then shows nothing — and the bundled references/search_strategy_guide.md is never linked from the body, leaving its content undiscoverable and partly duplicated. Fixing the missing format template and adding an explicit reference pointer would raise actionability and progressive disclosure substantially.

Suggestions

Complete the Action Format section: after 'must be a single action in the exact format:', include the literal template (e.g., search[<keywords>]) so the required output is unambiguous.

Link the bundled guide from the body (e.g., 'Attribute priorities, common pitfalls, and platform assumptions: See [references/search_strategy_guide.md](references/search_strategy_guide.md)') and trim the 'Key Principles' bullets that duplicate its hierarchy.

Remove the persona framing ('You are an expert at...') and fold its content into the Purpose statement to tighten the body further.

DimensionReasoningScore

Conciseness

The ~25-line body is generally lean with clear sections, but includes minor padding: the 'You are an expert at...' persona framing and 'Key Principles' bullets that duplicate the attribute-priority hierarchy already detailed in references/search_strategy_guide.md. This matches anchor 4 (efficient, minor instances that could be trimmed) rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

There is a concrete worked example ('Effective Search: search[size 5 patent-beige high heel]') and specific principles, but the Action Format section ends 'Your final output must be a single action in the exact format:' with no format actually shown — the single most important executable detail is missing. This matches anchor 3 (some concrete guidance but incomplete, missing key details); it is above anchor 2 because the example and principles are concrete, but below anchor 4 because the promised exact output template is absent.

3 / 5

Workflow Clarity

As a simple single-purpose skill, the Core Workflow gives a clear Input → Process → Output sequence, which under the simple-skill note could merit a 5; however the output action's exact format is undefined, leaving the single action not fully unambiguous. Anchor 4 (clear sequence, minor gaps) is the best fit.

4 / 5

Progressive Disclosure

The body itself is well-sectioned, but the bundle contains references/search_strategy_guide.md (attribute priority hierarchy, pitfalls table, workflow integration) that is never referenced or linked anywhere in the body — a buried reference — and its attribute-priority content is partly duplicated inline in 'Key Principles'. Scoring against the actual bundle structure, this matches anchor 3 (references present but not clearly signaled; content that should be separate is inline) rather than anchor 4, whose references are mostly clearly signaled.

3 / 5

Total

14

/

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: it explicitly covers what the skill does, when it triggers, includes a concrete input example, and defines a narrow, distinct niche. Third-person voice is used correctly and there is no filler. Only minor improvement is possible in trigger-term synonym coverage.

DimensionReasoningScore

Specificity

The description states a concrete input-to-output transformation ('takes structured attributes (e.g., women's size 5 patent-beige high heel) and produces a concise, platform-appropriate search string'), with only minor softness in 'generates effective search keywords'. It lists specific actions with an example rather than the 1-2 minimal actions of anchor 3, but is single-action so not comprehensive enough for anchor 5.

4 / 5

Completeness

Both 'what' ('generates effective search keywords... produces a concise, platform-appropriate search string') and 'when' ('It is triggered after query parsing, when the agent needs to perform an initial product search on an e-commerce platform') are explicitly and concretely stated, matching the anchor 5 example with explicit trigger guidance.

5 / 5

Trigger Term Quality

Natural trigger terms are present: 'product search', 'search keywords', 'search string', 'e-commerce platform', 'query parsing'. Coverage is good but misses common variations or synonyms (e.g., 'search query', 'shopping', 'webshop'), matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche — initial search-string formulation on an e-commerce platform after query parsing — with trigger conditions unlikely to fire for unrelated skills, matching anchor 5 (clear niche with distinct triggers, minimal conflict risk).

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.

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.