Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

bizzon

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

Quality

65%

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/bizzon/SKILL.md

Quality

Content

57%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 strong on executable commands and includes a solid connection-state feedback loop, but it is undermined by broken internal references (a nonexistent "Step 2" and an orphaned "1b"), marketing-style padding, and an empty overview section. Fixing the step numbering alone would move workflow clarity and overall usefulness up a level.

Suggestions

Fix the dangling references: define the numbered steps (1. Connect, 2. Discover actions) so "skip to Step 2" resolves, and either add a 1a section or drop the 1b numbering.

Trim padding — the marketing overview paragraph, "This is the fastest way to get a connection", and the sentence about agent types — and either populate the "Bizzon Overview" list with per-entity guidance or delete it.

Move reference-style material (the proxy flags table, clientAction schema details, agent-types list) into a single reference file linked from SKILL.md to reduce baseline token load.

Dimension	Reasoning	Score
Conciseness	The command documentation is mostly efficient, but padded passages remain: "Bizzon is a SaaS application used by businesses to manage and automate their sales processes…", "This is the fastest way to get a connection", and the awkward "Those will be used to adjust tooling to be used best with your harness". It is not 4 because several such passages could be trimmed without losing guidance.	3 / 5
Actionability	Guidance is mostly executable with copy-paste commands ("npm install -g @membranehq/cli@latest", "membrane connection ensure \"https://www.bizzon.com/\" --json", "membrane action run <actionId> --connectionId=CONNECTION_ID --input '{\"key\": \"value\"}' --json") and a flags table. It is not 5 because placeholders like CONNECTION_ID and QUERY are never concretely resolved and the "Bizzon Overview" section is a near-empty bullet list that instructs nothing.	4 / 5
Workflow Clarity	A sequence exists (install → login → ensure connection → poll → search/run actions) with explicit state checkpoints (READY, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR), but "skip to Step 2" is referenced twice with no Step 2 defined, and "#### 1b. Wait for the connection" has no corresponding 1a. These dangling references break the sequence beyond the minor gaps allowed by anchor 4.	3 / 5
Progressive Disclosure	The single file is well-sectioned with clear headings and no bundle files exist to navigate, but reference-style material — the proxy flags table, the clientAction schema details, and the agent-types list — is inlined in SKILL.md where a one-level-deep reference file would be more appropriate. It is not 2 because the structure is genuinely good and nothing is buried.	3 / 5
	Total	13 / 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 follows the what + "Use when" pattern and is anchored to a distinct app name, but it wastes its action list on generic phrases. Concretizing the capabilities with Bizzon's actual entities (customers, invoices, leads, products) would raise specificity and trigger quality substantially.

Suggestions

Replace "Manage data, records, and automate workflows" with concrete actions drawn from the entities documented in the body, e.g. "Create and update customers, invoices, and products; search and run Bizzon sales actions".

Add natural trigger synonyms users would actually say, e.g. "Use when the user mentions Bizzon, their Bizzon CRM, leads, invoices, or sales-pipeline data".

State the integration mechanism briefly (via the Membrane CLI) so the what-clause tells Claude how the interaction happens, not just that it exists.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Bizzon integration") but its actions — "Manage data, records, and automate workflows" — are generic, with no concrete sales-domain actions like leads, invoices, customers, or deals. It is not 3 because no concrete, specific action is actually stated.	2 / 5
Completeness	Both parts are present: a what ("Manage data, records, and automate workflows") and an explicit when ("Use when the user wants to interact with Bizzon data"), so it is not capped at 3. It is not 5 because the when-clause is generic and the what lacks concrete trigger phrases tied to specific capabilities.	4 / 5
Trigger Term Quality	It contains the relevant primary trigger terms "Bizzon" and "interact with Bizzon data", but misses common variations or synonyms a user might naturally say (CRM, sales, leads, invoices, customers). Not 4 because keyword coverage beyond the app name is essentially absent.	3 / 5
Distinctiveness Conflict Risk	Being tied to a specific application name ("Bizzon") makes it mostly distinct and unlikely to trigger the wrong skill when the app is named. It is not 5 because the generic tail "Manage data, records, and automate workflows" creates minor overlap risk with other data/automation integration skills when Bizzon is not explicitly mentioned.	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/bizzon/SKILL.md
Revision: f484c82

Reviewed: 16 days ago

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.

bizzon

Table of Contents

Is this your skill?