webshop-product-detail-navigator

Navigates to and interacts with a specific product's detail page. This skill is triggered after a candidate product ID is selected from search results. It performs the click action to load the product page and then identifies available interactive elements (like flavor or size selectors) that need to be configured to match the user's requirements.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./experiments/src/skills/webshop/webshop-product-detail-navigator/SKILL.md

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 content is well-organized and concise with a clear sequenced workflow and useful validation notes, but its actionability is undermined by a missing referenced script and poor bundle linkage. Wiring the existing reference and providing the script would materially lift the score.

Suggestions

Either add the referenced configure_product.py under scripts/ or replace the 'Key Logic (Handled by Script)' section with the concrete selection logic inline.

Link the existing references/action_protocol.md from the 'Action Format' section (e.g. 'See [action_protocol.md](references/action_protocol.md)') instead of duplicating its content.

Promote the validation notes into explicit numbered checkpoints within the Core Workflow (e.g. a 'Validate' sub-step after Configure) to make the feedback loop structural rather than incidental.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — sections like Core Workflow and Important Notes are direct with little padding, with only minor over-explanation such as 'The typical order is to select the correct flavor first, then the correct size'.	4 / 5
Actionability	The action format ('click[<exact_value>]', 'search[<keywords>]') is concrete, but the core deterministic logic is offloaded to a bundled 'configure_product.py' that is referenced yet absent from the bundle (no scripts/ directory), leaving a key executable gap.	3 / 5
Workflow Clarity	The 5-step Core Workflow (Navigate, Parse, Match, Configure, Finalize) is clearly sequenced with validation notes ('Do not click an option if it does not appear', 'Always read the full observation after each action'), but the validation reads as caveats rather than explicit inline checkpoints, sitting just below the 5.	4 / 5
Progressive Disclosure	The body is well-sectioned but references a non-existent configure_product.py script while the existing references/action_protocol.md is never linked from the body, and the 'Action Format' section duplicates that reference's content rather than pointing to it.	3 / 5
	Total	14 / 20 Passed

Description

67%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 is specific and clearly communicates a distinct niche with an explicit trigger, but the trigger is framed as internal state rather than natural user-facing keywords. Strengthening it with concrete 'Use when...' phrasing and natural synonyms would raise completeness and trigger-term quality.

Suggestions

Rewrite the trigger as a natural 'Use when...' clause, e.g. 'Use when a candidate product has been selected from search results and you need to load its detail page and configure options like flavor or size.'

Add common user-facing synonyms (e.g. 'product page', 'select options', 'configure product') to broaden trigger-term coverage.

Tighten the opening to lead with the core action ('Loads a product's detail page and configures its options to match the user's request') before the trigger clause.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'performs the click action to load the product page', 'identifies available interactive elements (like flavor or size selectors)', 'configured to match the user's requirements' — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	It explicitly answers both 'what' (navigate, click, identify, configure) and 'when' ('triggered after a candidate product ID is selected from search results'); the 'when' is explicit but situational rather than a natural trigger phrase, so it sits below the concrete-trigger 5.	4 / 5
Trigger Term Quality	The trigger is state-based ('triggered after a candidate product ID is selected from search results') with domain terms like 'flavor or size selectors', but it lacks the natural keyword variations a user would actually say, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche — post-search product-detail navigation and option configuration — with minimal conflict risk, though its situational trigger leaves minor overlap with a generic search skill, fitting 'mostly distinct' rather than the fully distinct 5.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

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
Path: experiments/src/skills/webshop/webshop-product-detail-navigator/SKILL.md
Commit: cce11c3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.