Name: leexi
Rating: 64 (1 reviews)
Author: membranedev

leexi

Leexi integration. Manage Leads, Persons, Organizations, Deals, Projects, Pipelines and more. Use when the user wants to interact with Leexi data.

Quality

76%

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/leexi/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 content is a lean, highly actionable integration guide built around executable Membrane CLI commands and a clear connect-then-act workflow with state-machine feedback. Its main gaps are minor prose padding and a lack of validation guidance for the destructive actions it advertises.

Suggestions

Trim filler sentences such as 'so you can focus on the integration logic rather than auth plumbing' and 'This is the fastest way to get a connection' to tighten conciseness.

Add a validation/confirmation checkpoint before destructive actions (e.g., 'Confirm the UUID before running delete-meeting-event') to close the workflow-clarity gap.

Consider moving the Popular actions table into a references file linked from the body to improve progressive disclosure now that the file is ~150 lines.

Dimension	Reasoning	Score
Conciseness	The body is largely command- and table-driven with executable bash blocks, matching 'Efficient; minor instances of over-explanation that could be trimmed.' It is not a 5 because of padding like 'so you can focus on the integration logic rather than auth plumbing' and 'This is the fastest way to get a connection', and not a 3 because the bulk is lean, actionable content rather than noticeably verbose explanation.	4 / 5
Actionability	Concrete copy-paste commands cover the common cases ("npm install -g @membranehq/cli@latest", "membrane connection ensure", "membrane action run <actionId> --input '{\"key\": \"value\"}' --json", "membrane request CONNECTION_ID /path"), matching 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases.' It is not a 4 because examples are complete and parameterized rather than having notable gaps.	5 / 5
Workflow Clarity	A clear sequence (install -> login -> connection ensure -> poll until READY -> search actions -> run/proxy) with a state-machine and feedback loop (poll again after CLIENT_ACTION_REQUIRED, check error field) matches 'Clear sequence with most checkpoints present; minor validation gaps.' It is not a 5 because destructive actions like 'Delete Meeting Event' appear without validation/confirmation guidance, leaving a minor checkpoint gap.	4 / 5
Progressive Disclosure	The single SKILL.md (~150 lines, no references/scripts/assets bundle) is well-organized into clear sections (Overview, Install, Authentication, Connecting, Searching, Popular actions, Running actions, Proxy, Best practices) with no nested references, matching 'Good structure; most content is appropriately placed; minor organization gaps.' It is not a 5 because the Popular actions table and proxy flag reference are inlined in one file rather than split into a one-level-deep reference, and not a 3 because navigation is clear and structure is sound.	4 / 5
	Total	17 / 20 Passed

Description

71%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 clearly names the Leexi product, lists several concrete entities, and includes an explicit 'Use when' trigger, so it answers both what and when. Its main weakness is narrow trigger-term coverage that omits natural user phrases like calls, meetings, and conversations.

Suggestions

Expand the trigger phrase beyond 'interact with Leexi data' to include natural user terms such as 'Leexi calls', 'meeting analysis', or 'conversation recordings'.

Replace the single generic verb 'Manage' with a few distinct concrete actions (e.g., 'List, create, and analyze calls and meetings') to lift specificity.

Align the entity list (Leads, Persons, Organizations, Deals, Projects, Pipelines) with the body's actual Leexi objects (Conversations, Messages, Calls, Meetings, Teams, Users) to avoid a mismatched CRM-style schema.

Dimension	Reasoning	Score
Specificity	Quotes "Manage Leads, Persons, Organizations, Deals, Projects, Pipelines and more" name the domain plus several concrete entities, matching the anchor 'Lists several specific actions; minor gaps in coverage.' It is not a 5 because the single generic verb 'Manage' covers all nouns rather than multiple distinct concrete actions, and not a 3 because six+ named entities exceed '1-2 concrete actions'.	4 / 5
Completeness	Both halves are present: what ("Leexi integration. Manage Leads, Persons, Organizations, Deals, Projects, Pipelines and more") and when ("Use when the user wants to interact with Leexi data"), matching 'Has both what and when; when could be more explicit or specific.' It is not a 5 because the when-clause 'interact with Leexi data' is generic rather than concrete trigger phrases, and not a 3 because an explicit when is stated rather than merely implied.	4 / 5
Trigger Term Quality	Keywords are limited to "Leexi integration" and "Leexi data" with the trigger "Use when the user wants to interact with Leexi data"; this matches 'Some relevant keywords but missing common variations or synonyms.' It is not a 4 because natural terms a user would say (calls, meetings, conversations, call analysis) are absent, and not a 2 because 'Leexi' is the correct product keyword rather than fully generic language.	3 / 5
Distinctiveness Conflict Risk	The description is product-specific ("Leexi integration", "interact with Leexi data"), giving it a clear niche with minimal conflict risk, matching 'Clear niche with distinct triggers; minimal conflict risk.' It is not a 4 because the trigger is uniquely tied to a named product rather than a broad category with minor overlap.	5 / 5
	Total	16 / 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/leexi/SKILL.md
Commit: f484c82

Reviewed: ~20 hours 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.