Name: happy-scribe
Rating: 57.599999999999994 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

happy-scribe

Happy Scribe integration. Manage Recordses. Use when the user wants to interact with Happy Scribe data.

Quality

66%

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/happy-scribe/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 body is an efficient, actionable integration guide built around concrete Membrane CLI commands and a clear connection state machine with polling checkpoints. Its main weaknesses are minor padding, placeholder parameters in examples, and the lack of a validation step before the destructive delete-transcription action.

Suggestions

Add a brief validation/confirmation checkpoint before destructive actions (e.g. "Before delete-transcription, confirm the ID with the user and verify via get-transcription").

Trim the introductory sentence about who uses Happy Scribe and the "auth plumbing" aside to reclaim tokens.

Include at least one fully-filled action run example (with a concrete transcription ID and input JSON) so the common case is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is dominated by executable commands and tight state descriptions with only minor trimmable padding (the user-base intro and the "focus on the integration logic rather than auth plumbing" aside), matching the score-4 anchor of efficient content with minor over-explanation; it is not 5 because a few sentences explain context Claude already has.	4 / 5
Actionability	It provides concrete, copy-paste-ready commands for every phase (login, connection ensure/get, action list/run, request) plus a popular-actions table with real keys, matching score 4; it is not 5 because parameters use placeholders (CONNECTION_ID, actionId) and the run examples do not show a fully filled realistic call.	4 / 5
Workflow Clarity	The connect→wait→search→run sequence is clearly laid out with explicit state-checkpoint polling (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a re-poll feedback loop, matching score 4; it is not 5 because destructive actions (delete-transcription) appear in the action table without an explicit verify-before-delete checkpoint.	4 / 5
Progressive Disclosure	The skill is a single self-contained file with well-organized sections (Overview, Install, Auth, Connecting, Searching, Popular actions, Running, Proxy, Best practices) and no nested references, giving good structure and easy navigation per the score-4 anchor; it is not 5 only because there are no one-level-deep references to signal, which the score-5 anchor centers on.	4 / 5
	Total	16 / 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 correctly pairs a what/when structure with an explicit "Use when" trigger and a distinct brand niche, but its capability statement is thin (the odd, generic "Manage Recordses") and it omits the natural synonyms (transcription, subtitling, audio/video) that users would actually say. Tightening the action list and adding concrete trigger terms would lift specificity and trigger quality.

Suggestions

Replace the vague "Manage Recordses" with concrete capabilities, e.g. "Create and manage transcriptions, exports, and translation orders".

Add natural trigger synonyms users would say, e.g. "Use when the user wants to transcribe audio/video, generate subtitles, or export transcripts from Happy Scribe."

Fix the apparent templating artifact "Recordses" to a clean resource name to avoid confusing the model at trigger time.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Happy Scribe integration") but the only action offered is the minimal/generic "Manage Recordses", matching the score-2 anchor "Names the domain but actions are minimal or generic"; it does not reach score 3 because there is no second concrete action.	2 / 5
Completeness	Both "what" ("Happy Scribe integration. Manage Recordses.") and "when" ("Use when the user wants to interact with Happy Scribe data.") are explicitly present, but the "when" is generic rather than concrete, matching the score-4 anchor; it is not 5 because the trigger lacks specific concrete phrases and not 3 because the "when" clause is explicit, not missing.	4 / 5
Trigger Term Quality	It includes the brand keyword "Happy Scribe" repeated in a "Use when...interact with Happy Scribe data" trigger, but lacks the natural synonyms a user would say (transcription, subtitling, audio, video), fitting the score-3 anchor of relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	The trigger is tied to a specific named platform ("Happy Scribe"), giving it a clear niche with low conflict risk, matching score 4; it stops short of 5 because the description is thin and the trigger phrasing ("interact with Happy Scribe data") is broad rather than sharply distinct.	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/happy-scribe/SKILL.md
Commit: f484c82

Reviewed: 5 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.