Name: cradl-ai
Rating: 59.2 (1 reviews)
Author: membranedev

cradl-ai

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

Quality

68%

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/cradl-ai/SKILL.md

Quality

Content

75%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 a well-structured, actionable CLI integration guide with executable commands, a clear workflow, and a connection-readiness feedback loop. Its main weaknesses are minor padding in the intro, an undefined 'Step 2' reference, and no error-recovery loop for failed action runs.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable commands and a flag table that earn their place, though the opening product overview and occasional editorializing ('so you can focus on the integration logic rather than auth plumbing') could be trimmed, fitting the 'efficient; minor instances of over-explanation' anchor.	4 / 5
Actionability	It provides concrete, copy-pasteable commands throughout (install, login, connection ensure, action run with --input JSON) plus a flag table, with only minor gaps such as the unresolved CONNECTION_ID placeholder, matching the 'mostly executable guidance' anchor just below fully copy-paste ready.	4 / 5
Workflow Clarity	The install→auth→connect→search→run sequence is clear with a readiness feedback loop (--wait polling, CLIENT_ACTION_REQUIRED handling, re-poll), but the referenced 'Step 2' is never defined and run-action failures lack a fix/retry loop, keeping it at the 'clear sequence with most checkpoints, minor gaps' anchor.	4 / 5
Progressive Disclosure	The single self-contained SKILL.md is well-organized with clear section headers and no nested references, though the detailed clientAction handling and proxy flag table could arguably move to a reference file, fitting the 'good structure; most content appropriately placed' anchor rather than the ideal split of anchor 5.	4 / 5
	Total	16 / 20 Passed

Description

62%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 functional and includes both capability and trigger guidance, but its action verbs are generic and its trigger phrasing is narrow. Tightening the actions and broadening the 'when' clause would lift it toward the top anchors.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Cradl AI operations (e.g., 'extract data points, train models, label documents, and run workflows').

Broaden the trigger clause with natural variations, e.g., 'Use when the user wants to extract, label, or model Cradl AI documents and data.'

Mention key Cradl AI entities (Projects, Documents, Models, Label Sets) in the description to improve specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the Cradl AI domain and two-to-three actions ('Manage data, records, and automate workflows'), but the verbs are generic rather than concrete operations, matching the 'names domain and 1-2 concrete actions but not comprehensive' anchor.	3 / 5
Completeness	It states both the 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Cradl AI data'), though the 'when' is broad rather than concrete and varied, so it sits at the 'has both but when could be more specific' anchor.	4 / 5
Trigger Term Quality	The phrase 'interact with Cradl AI data' surfaces the product name as a trigger but relies on the generic term 'data' and lacks common synonyms or variations, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Naming the specific product 'Cradl AI' gives a clear niche and distinct triggers with only minor overlap risk against other data-integration skills, matching the 'mostly distinct' anchor rather than the fully distinctive anchor 5.	4 / 5
	Total	14 / 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/cradl-ai/SKILL.md
Commit: f484c82

Reviewed: 4 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.