Name: async-interview
Rating: 55.2 (1 reviews)
Author: membranedev

async-interview

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/async-interview/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 well-structured, executable integration guide with concrete CLI commands and a clearly sequenced connection workflow including state-based feedback loops. Its main weakness is mild verbosity in the introductory framing and a few incomplete table entries.

Suggestions

Trim the opening background paragraph ("Async Interview is a platform for conducting asynchronous video interviews...") and the filler line "Use action names and parameters as needed." to assume Claude's knowledge.

Fill the empty Description column in the Popular actions table so each action's purpose is clear without a separate lookup.

Add a brief validation note before destructive actions (delete-interview, update-interview), e.g. confirming the target id or re-fetching the record, to satisfy the destructive-operation checkpoint guidance.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient and command-focused, but the opening paragraph explaining what Async Interview is and who uses it, plus filler like "Use action names and parameters as needed.", are unnecessary explanation that could be trimmed, matching the mostly-efficient-but-could-be-tighter anchor.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands throughout (install, login, connection ensure, action list/run, request with flags), with only minor gaps such as the empty Description column in the Popular actions table and placeholder CONNECTION_ID values.	4 / 5
Workflow Clarity	The connect-and-authenticate workflow is clearly sequenced with an explicit state machine (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a polling feedback loop, giving strong checkpoints; the brief action-running section lacks validation for destructive actions like delete-interview, a minor gap.	4 / 5
Progressive Disclosure	With no bundle files, all content lives in SKILL.md but is organized into clear, well-labeled sections (Install, Authentication, Connecting, Searching, Popular actions, Running actions, Proxy, Best practices), giving good structure and easy navigation without needing external references.	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 is product-specific and includes an explicit trigger clause, but its action language is generic and its trigger terms lack natural synonyms. It answers both what and when, just not with maximal concreteness.

Suggestions

Replace generic verbs with concrete Async Interview actions, e.g. "Create interviews, invite candidates, and list interview responses" instead of "Manage data, records, and automate workflows".

Add natural trigger terms users would actually say, such as "video interviews", "candidate screening", or "interview responses", to improve trigger matching.

Sharpen the Use-when clause to reference specific intents, e.g. "Use when the user wants to create or review async video interviews and candidate responses."

Dimension	Reasoning	Score
Specificity	The description names the domain ("Async Interview integration") but the actions — "Manage data, records, and automate workflows" — are generic rather than concrete domain actions (e.g. create interviews, invite candidates, list responses), matching the anchor that names the domain with minimal/generic actions.	2 / 5
Completeness	It explicitly answers both "what" (manage data, records, automate workflows) and "when" ("Use when the user wants to interact with Async Interview data"), and the presence of an explicit Use-when clause keeps it above the cap of 3; the when could be more specific, matching the anchor with both present but a less-than-explicit trigger.	4 / 5
Trigger Term Quality	It includes the product name and terms like "data", "records", and "workflows", but the trigger "interact with Async Interview data" misses natural synonyms users would say (video interviews, candidates, screening, responses), so coverage is partial rather than comprehensive.	3 / 5
Distinctiveness Conflict Risk	Tying the skill to a specific named product ("Async Interview") gives it a clear niche with minimal conflict risk, though the broad trigger phrasing keeps it just short of the clearest-distinctiveness 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/async-interview/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.