Name: assemblyai
Rating: 56.00000000000001 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

assemblyai

AssemblyAI integration. Manage Transcripts, Speakers, Jobs. Use when the user wants to interact with AssemblyAI data.

Quality

63%

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/assemblyai/SKILL.md

Quality

Content

61%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, action-oriented guide to driving AssemblyAI via the Membrane CLI, with strong command examples and a clear connection workflow. Its main gaps are redundant overview padding and missing validation/confirmation around destructive actions like delete-transcript.

Suggestions

Remove the 17-item AssemblyAI Overview bullet list or fold it into the Popular actions table to eliminate redundancy with the coverage already shown there.

Add a validation/confirmation checkpoint before destructive actions, e.g. "Before running delete-transcript, confirm the transcript ID with the user and verify the returned status".

Trim the introductory tutorial sentence about call centers and subtitles, since Claude already knows what speech-to-text is used for.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with tables and code blocks, but it includes notable padding: a 17-item Overview bullet list that duplicates the actions table and an introductory tutorial ("transcribe audio and video... like analyzing call center conversations"), matching anchor 3 rather than 4.	3 / 5
Actionability	It provides concrete, copy-pasteable membrane commands and a clear proxy-flags table, but several examples rely on placeholders (CONNECTION_ID, <actionId>) and result handling is only a one-liner, sitting at anchor 4 not 5.	4 / 5
Workflow Clarity	The connection flow is well sequenced with polling/error checkpoints, but the "Running actions" guidance includes a destructive action (delete-transcript) with no validation or confirmation step, which caps workflow clarity at 3 per the destructive-operation rule.	3 / 5
Progressive Disclosure	It is a single-file skill with well-organized section headers and reasonably placed content, but the Overview bullet list duplicates the actions table and some bulk (proxy flags) could be split out, so it is anchor 4 rather than 5.	4 / 5
	Total	14 / 20 Passed

Description

66%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 short, third-person, and clearly names the AssemblyAI niche with an explicit Use-when clause, scoring well on completeness and distinctiveness. Its main weaknesses are a generic action verb and missing natural trigger synonyms like "transcribe" or "transcript".

Suggestions

Replace the generic "Manage" with concrete actions, e.g. "Create and list transcripts, generate subtitles, redact PII, and run analytics".

Expand the Use-when clause with natural trigger phrases users actually say, e.g. "Use when the user wants to transcribe audio, generate subtitles, or work with transcripts, speaker labels, or AssemblyAI data".

Add common synonyms/file formats (transcription, speech-to-text, SRT, VTT) to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	"Manage Transcripts, Speakers, Jobs" names the domain and concrete managed entities but only a single generic action verb ("Manage"); it does not enumerate several specific actions, so it matches anchor 3 rather than 4.	3 / 5
Completeness	It has both a clear "what" ("Manage Transcripts, Speakers, Jobs") and an explicit "when" ("Use when the user wants to interact with AssemblyAI data"), but the when-clause is generic rather than tied to concrete trigger phrases, so it sits at anchor 4 not 5.	4 / 5
Trigger Term Quality	The "AssemblyAI" brand keyword and "interact with AssemblyAI data" give some relevant triggers, but common natural phrasings users would actually say (transcribe, transcript, speech-to-text, subtitles) are missing, matching anchor 3.	3 / 5
Distinctiveness Conflict Risk	The description anchors on the specific named service "AssemblyAI", giving it a clear niche with distinct triggers and minimal conflict risk with other skills, matching anchor 5.	5 / 5
	Total	15 / 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/assemblyai/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.