Name: speakeasy
Rating: 61.6 (1 reviews)
Author: membranedev

speakeasy

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

Quality

72%

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/speakeasy/SKILL.md

Quality

Content

82%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 highly actionable, with copy-paste-ready Membrane CLI commands and explicit polling/state feedback loops for the connection workflow. Its main weaknesses are minor verbosity in the intro/best-practices prose and a dangling 'Step 2'/'1b' numbering scheme that slightly muddies the workflow sequence.

Suggestions

Fix the dangling step numbering: label a 'Step 1a' (connection ensure) and 'Step 2' (search/run actions), or remove the 'skip to Step 2' references entirely.

Trim marketing-style filler such as 'so you can focus on the integration logic rather than auth plumbing' and 'This will burn less tokens'.

Remove or differentiate the 'Popular actions' section, which repeats the action-list command already shown under 'Searching for actions'.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with copy-paste commands throughout, but has minor over-explanation ('so you can focus on the integration logic rather than auth plumbing', 'This will burn less tokens') that could be trimmed, matching the 'efficient; minor instances of over-explanation' anchor.	4 / 5
Actionability	Fully executable, copy-paste-ready commands cover the common cases end-to-end: install, login, connection ensure/get with --wait, action list/run with --input, and the request proxy with a complete flag table, matching the top anchor.	5 / 5
Workflow Clarity	The connection flow has explicit validation via polling and state-based feedback loops (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but the 'Step 2' and '1b' numbering dangles with no labeled Step 1a or Step 2, a minor clarity gap that keeps it just below a 5.	4 / 5
Progressive Disclosure	Content is well-organized into clear self-contained sections with no need for external references, but the 'Popular actions' section duplicates the earlier action-list command and the overall structure has minor organization gaps rather than being perfectly clean.	4 / 5
	Total	17 / 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 correctly covers both what the skill does and when to use it with a clear brand trigger, but its action language is generic and it misses the natural Speakeasy-domain terms users would say. Tightening the actions to concrete Speakeasy capabilities and adding domain trigger phrases would raise it.

Suggestions

Replace generic verbs with concrete Speakeasy actions, e.g. 'Generate API documentation, SDKs, and governance policies from OpenAPI specs.'

Add natural trigger phrases users say, such as 'Use when the user wants to generate an SDK, API docs, or governance policies from an OpenAPI specification.'

Drop the filler 'Speakeasy integration.' lead-in to make the opening action-oriented.

Dimension	Reasoning	Score
Specificity	Names the Speakeasy domain and several action phrases ('Manage data, records, and automate workflows'), but those actions are generic rather than concrete Speakeasy capabilities like SDK/API-doc generation, so it sits between the generic-actions anchor (2) and the concrete-actions anchor (3).	3 / 5
Completeness	Both 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Speakeasy data') are present, but the trigger clause is generic rather than listing concrete trigger phrases, so it does not reach a 5.	4 / 5
Trigger Term Quality	Includes the brand keyword 'Speakeasy' plus generic terms ('data', 'records', 'workflows'), but omits the natural domain phrases users would actually say (SDK, API documentation, OpenAPI), matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The 'Speakeasy' brand name gives a clear, distinct niche with low conflict risk, but the generic 'manage data, records, workflows' verbs create minor overlap with other data-management skills.	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/speakeasy/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.