Name: yardstik
Rating: 63.2 (1 reviews)
Author: membranedev

yardstik

Yardstik integration. Manage data, records, and automate workflows. Use when the user wants to interact with Yardstik data.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/yardstik/SKILL.md

Quality

Content

76%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 a strong, actionable CLI usage guide with executable commands and a well-validated connection workflow. Its main gaps are missing verification steps for destructive action/proxy operations and a couple of minor structural/trim issues.

Suggestions

Add a verification step after running actions and proxy write/DELETE requests (e.g., re-fetch the affected record or check the response status field) to satisfy the destructive/batch validation requirement.

Fix the dangling 'skip to Step 2' reference by explicitly labeling the workflow steps (Step 1: connect, Step 2: search/run actions) so the navigation is coherent.

Trim the three-sentence Yardstik marketing opener and the 'Use action names and parameters as needed.' filler to improve token efficiency, and either populate 'Popular actions' with named examples or remove that empty heading.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and command-driven with minor over-explanation that could be trimmed (the three-sentence marketing opener about Yardstik and the filler line 'Use action names and parameters as needed.').	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands across install, login, connection, action search/run, and proxy, plus a flags table, covering the common cases.	5 / 5
Workflow Clarity	The connection flow has explicit state-polling validation and a poll-after-action feedback loop, but action execution and proxy requests (which support DELETE and data writes) lack verification steps; the destructive/batch cap applies, and the 'skip to Step 2' reference points to no labeled Step 2.	3 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections with cohesive inline CLI documentation and no external bundle files; at ~140 lines it exceeds the simple-skill threshold so it does not reach 5.	4 / 5
	Total	16 / 20 Passed

Description

73%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 well-formed: it names a distinct product, lists a few actions, and includes an explicit 'Use when' trigger clause. Its main weakness is generic action verbs ('manage data/records') that keep specificity and completeness below the top anchors.

Suggestions

Replace generic verbs ('Manage data, records') with concrete Yardstik capabilities such as 'run background checks, manage candidates, and retrieve assessment results'.

Broaden the trigger phrase to mention natural synonyms users would say, e.g. 'Use when the user wants to run background checks, screen candidates, or interact with Yardstik data'.

Tighten the what/when pairing so the when clause references the concrete actions rather than the generic 'interact with Yardstik data'.

Dimension	Reasoning	Score
Specificity	Names the Yardstik domain plus two-to-three actions ('Manage data, records, and automate workflows'), but the actions are generic rather than concrete like 'extract/fill/merge', matching the score-3 anchor.	3 / 5
Completeness	It states both what ('Manage data, records, and automate workflows') and an explicit when ('Use when the user wants to interact with Yardstik data'); the when could be more specific, fitting the score-4 anchor rather than 5.	4 / 5
Trigger Term Quality	'Yardstik' and 'interact with Yardstik data' are natural terms a user would say, giving good keyword coverage; a few natural synonyms (screening, background checks) are absent so it does not reach 5.	4 / 5
Distinctiveness Conflict Risk	Yardstik is a uniquely-named product with a distinct trigger ('interact with Yardstik data'), giving a clear niche with minimal conflict risk.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/yardstik/SKILL.md
Commit: f484c82

Reviewed: ~22 hours 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.