webshop-action-executor

This skill executes a specific interface action, such as clicking a button or selecting an option, within a web shopping environment. It should be triggered when a decision has been made (e.g., to choose a color or proceed to purchase). The input is the target action identifier (e.g., 'white' or 'buy now'), and the output is the corresponding formatted action command (e.g., click[white]).

Quality

79%

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-action-executor/SKILL.md

Quality

Content

65%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 compact and well organized for a simple single-purpose skill, but it is critically incomplete: the Core Instruction stops mid-sentence before specifying the exact output format, leaving the reader without the formatting rule, worked examples, or a click-vs-search selection criterion. Progressive disclosure and conciseness are fine; actionability and workflow clarity suffer from the truncation and duplicated input/output statements.

Suggestions

Complete the truncated 'Format Output' step with the explicit format template (e.g., output click[<target_action>] for page actions and search[<keywords>] for searches) and worked examples such as 'white' -> click[white] and 'buy now' -> click[buy now].

Add a one-line rule for choosing between click[value] and search[keywords] so the single action is unambiguous.

Deduplicate the input/output contract between the 'When to Use' section and the 'Core Instruction' steps to tighten token usage.

Dimension	Reasoning	Score
Conciseness	The body is lean with no explanations of concepts Claude already knows, but the input and output contract is stated twice (the 'When to Use' bullets and the 'Core Instruction' steps), so a little trimming is possible.	4 / 5
Actionability	The format patterns 'click[value]' and 'search[keywords]' appear in 'When to Use', but the Core Instruction is cut off mid-sentence ('output the action in the exact format required by the WebShop environment:') without ever showing the format rule, a worked example, or how to choose between click and search. Concrete guidance exists but is incomplete with key details missing, matching the score-3 anchor rather than 4 (major gaps) or 2 (no concrete patterns at all).	3 / 5
Workflow Clarity	The receive-input then format-output sequence is present, but the decisive formatting step is truncated, so the single action is not unambiguous and the simple-skill exception to score 5 does not apply; it is above score 2 because a rough two-step sequence with inputs is defined. No destructive/batch validation cap applies.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references (no references/, scripts/, or assets/ directories exist and none are cited), and its sections (Purpose, When to Use, Core Instruction) are well organized, satisfying the simple-skill guideline for a top score.	5 / 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.

The description is strong: it uses third person, clearly states what the skill does, when to trigger it, and the input/output contract with concrete examples. Trigger phrasing leans on agent-internal state ('a decision has been made') rather than natural user utterances, which slightly limits trigger-term quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names several concrete actions ('executes a specific interface action, such as clicking a button or selecting an option') and gives a concrete output example ('the corresponding formatted action command (e.g., click[white])'), with only minor gaps in coverage of the action space.	4 / 5
Completeness	It explicitly answers both what ('This skill executes a specific interface action... the output is the corresponding formatted action command') and when ('It should be triggered when a decision has been made (e.g., to choose a color or proceed to purchase)') with concrete trigger phrases and input/output specification.	5 / 5
Trigger Term Quality	Natural terms like 'clicking a button', 'selecting an option', 'to choose a color or proceed to purchase', and 'buy now' give good keyword coverage, but the core trigger condition ('when a decision has been made') is agent-internal phrasing rather than a phrase a user would naturally say, and synonyms are limited.	4 / 5
Distinctiveness Conflict Risk	'within a web shopping environment' plus the WebShop-specific command format (click[white]) carves a mostly distinct niche, though 'executes an action after a decision has been made' could still overlap with other decision-execution or browser-action skills.	4 / 5
	Total	17 / 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-action-executor/SKILL.md
Commit: 358ec82

Reviewed: 8 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.