Name: winston-ai
Rating: 55.2 (1 reviews)
Author: membranedev

winston-ai

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

Quality

62%

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 ./skills/winston-ai/SKILL.md

Quality

Content

67%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 tight, executable command reference with a clear state-aware connection workflow, but it carries some promotional fluff and lacks a Winston-AI-specific end-to-end action example.

Suggestions

Trim promotional filler ('so you can focus on the integration logic rather than auth plumbing', 'burn less tokens') and the duplicated 'pre-built actions with built-in auth, pagination, and error handling' phrasing.

Add one concrete end-to-end Winston AI example, e.g. an actual scan action id and an `action run` invocation that submits text and reads the originality report from `output`.

Consider moving the detailed clientAction state spec to a short reference section or file so the core workflow stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is mostly a lean command reference, but it includes unnecessary padding ('so you can focus on the integration logic rather than auth plumbing', 'burn less tokens'), repeats 'pre-built actions with built-in auth, pagination, and error handling', and opens with context Claude largely already knows, fitting the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	It provides concrete, executable commands throughout (install, login, connection ensure/get, action list/run, request proxy) plus a flags table, with only a minor gap — no Winston-AI-specific end-to-end example, just generic <actionId> placeholders — matching the 'mostly executable guidance with minor gaps' anchor.	4 / 5
Workflow Clarity	The install→auth→connection→poll→search→run→proxy sequence is clear with state-based branching (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a poll-act-repoll feedback loop, matching the 'clear sequence with most checkpoints present; minor validation gaps' anchor.	4 / 5
Progressive Disclosure	With no bundle files, the single-file skill is well-organized into clearly headed sections and signals the external docs URL; the detailed clientAction spec is inline rather than in a reference file, a minor organization gap matching the 'good structure; most content appropriately placed' anchor.	4 / 5
	Total	15 / 20 Passed

Description

57%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 covers both what and when and is brand-anchored for distinctiveness, but its capability list is generic ('manage data, records, automate workflows') and it omits the natural trigger terms (AI content detection, plagiarism, originality) that users would actually say.

Suggestions

Replace generic verbs with concrete Winston AI actions, e.g. 'Scan text for AI-generated content, generate originality reports, and manage scan records.'

Add natural trigger phrases users actually say, e.g. 'Use when the user wants to detect AI-generated content, check originality, or run Winston AI scans.'

Tie the 'when' clause to specific outcomes (content detection, plagiarism/originality checks) rather than the vague 'interact with Winston AI data'.

Dimension	Reasoning	Score
Specificity	The description names the domain (Winston AI) but its actions — 'Manage data, records, and automate workflows' — are generic rather than concrete AI-content-detection tasks, fitting the 'names domain but actions minimal/generic' anchor and falling short of the concrete-actions anchor above.	2 / 5
Completeness	It states both what it does ('Manage data, records, and automate workflows') and when to use it ('Use when the user wants to interact with Winston AI data'), but the 'when' clause is generic rather than specific, matching the anchor where both are present yet 'when' could be more explicit.	4 / 5
Trigger Term Quality	It includes some relevant keywords ('Winston AI', 'data', 'records') but omits the natural phrases users would actually say for this tool (AI content detection, plagiarism, originality, AI-generated), matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The Winston AI brand anchor keeps conflict risk low, though the generic 'manage data/records' language creates minor overlap with related data skills, matching the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	13 / 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/winston-ai/SKILL.md
Commit: f484c82

Reviewed: 3 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.