Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

brick

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

Quality

69%

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/brick/SKILL.md

Quality

Content

63%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 a solid, command-driven getting-started guide with genuinely executable CLI snippets and a well-handled connection state machine. Its main weaknesses are padding (contentless overview bullets, vague agent-type prose), a 'skip to Step 2' reference to a step that is never labeled, and reference material kept inline in a single file.

Suggestions

Delete the contentless 'Brick Overview' bullet outline and the vague 'Agent Types' sentence, and either label the 'Searching for actions' section as Step 2 (with 'Connecting to Brick' as Step 1) or drop the step references entirely.

Move the clientAction state schema and the `membrane request` flag table into a references/ file (e.g. references/connection-states.md), keeping SKILL.md as a concise overview that links to it.

Populate 'Popular actions' with two or three concrete example action invocations, or remove the section since it currently only repeats the action-list command.

Dimension	Reasoning	Score
Conciseness	Command sections are lean, but the contentless 'Brick Overview' bullet outline (Dataset/Schema/Model/Inference), the marketing-style intro, and the vague 'Agent Types' sentence are padding that could be trimmed.	3 / 5
Actionability	Concrete copy-paste CLI commands cover install, login, connection, action discovery/execution, and proxying, with a full flag table; minor gaps include the undefined 'Step 2' reference and the value-less '--tenant' flag in the login command.	4 / 5
Workflow Clarity	A clear install→login→connect→discover→run sequence with an explicit polling feedback loop and per-state handling (READY, BUILDING, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR); minor gaps include the dangling 'Step 2' reference and a '1b' heading with no labeled '1a'.	4 / 5
Progressive Disclosure	A single-file skill with reasonable section headers, but reference material (the clientAction state schema, the request flag table) is inlined, and dead structure like the empty 'Brick Overview' outline and a 'Popular actions' section listing no actions weakens organization.	3 / 5
	Total	14 / 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 answers both what and when and is anchored by a distinctive app name, keeping conflict risk low. However, its capability list is generic buzzword-level ('manage data', 'automate workflows') and its trigger coverage depends on the single word 'Brick' with no natural synonyms.

Suggestions

Replace 'Manage data, records, and automate workflows' with concrete capabilities, e.g. 'Create, update, and query Brick records, manage construction projects, and run Brick actions via the Membrane CLI'.

Expand the 'Use when' clause with natural trigger variations: 'Use when the user mentions Brick, onebrick.io, construction projects, contractors, or subcontractors'.

Dimension	Reasoning	Score
Specificity	'Manage data, records, and automate workflows' names the domain and lists actions, but the verbs and objects are generic buzzwords rather than concrete operations (e.g. no 'create records', 'sync projects', 'run actions').	3 / 5
Completeness	Both are explicitly present — what ('Manage data, records, and automate workflows') and when ('Use when the user wants to interact with Brick data') — but the when-clause is a single circular phrase and the what is generic, so it falls short of concrete trigger phrases.	4 / 5
Trigger Term Quality	'Use when the user wants to interact with Brick data' relies almost entirely on the single proper noun 'Brick'; natural domain synonyms like construction management, contractors, projects, or onebrick.io are missing.	3 / 5
Distinctiveness Conflict Risk	Naming the Brick app gives a clear niche with minimal wrong-skill trigger risk; only the generic 'manage data, records' phrasing leaves 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/brick/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.

brick

Table of Contents

Is this your skill?