CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

brass

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

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/brass/SKILL.md
SKILL.md
Quality
Evals
Security

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 delivers a genuinely actionable Membrane CLI workflow with executable commands, thoughtful state handling, and a proxy fallback. Its weaknesses are structural: a dangling 'Step 2' reference, misnumbered headers, a duplicated/empty 'Popular actions' section, and inconsistent CLI invocation styles. Tightening the section structure and removing redundancy would lift it substantially.

Suggestions

Fix the dangling "skip to Step 2" reference — there is no Step 2 in the document; renumber the Connecting-to-Brass steps coherently (1a/1b/2 or named steps).

Fill the empty "Popular actions" section with actual example actions, or remove it since it repeats the `action list` command already documented.

Standardize on one CLI invocation form (`membrane` vs `npx @membranehq/cli`) and delete filler lines like "Use action names and parameters as needed."

DimensionReasoningScore

Conciseness

The body is mostly command-dense and efficient, but includes removable redundancy: the "Popular actions" section repeats the action-list command already shown, "Use action names and parameters as needed." is filler, and `membrane` and `npx @membranehq/cli` invocations are used interchangeably without explanation. Fits 'Mostly efficient but includes some unnecessary explanation or could be tightened'; not 4 because of the duplicated empty section and inconsistent CLI forms.

3 / 5

Actionability

Concrete executable commands cover the common cases: install, login with a headless `login complete <code>` branch, `connection ensure`, state polling with `--wait`, `action run` with `--input` JSON, and a proxy flag table. Fits 'Mostly executable guidance; concrete code or commands with minor gaps'; not 5 because `membrane login --tenant --clientName=<agentType>` leaves the --tenant value unspecified and "Popular actions" promises examples but lists none.

4 / 5

Workflow Clarity

The install → auth → connect → search → run → proxy sequence is present with real checkpoints (poll until READY, handle CLIENT_ACTION_REQUIRED via clientAction fields, check error on CONFIGURATION_ERROR). Fits 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit'; not 4 because "skip to Step 2" references a nonexistent Step 2 and a "1b" header appears with no 1a or numbering, undermining sequence coherence.

3 / 5

Progressive Disclosure

A single ~140-line file with section headers and a reasonable overview-first layout, but no bundle files and organizational gaps: an empty "Popular actions" section, incoherent step numbering, and the inline clientAction state-machine detail that would sit better in a reference file. Fits 'Some structure but could be better organized'; not 4 because the header structure is internally inconsistent and some inline content (connection-state handling) is a candidate for a separate reference.

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 has an explicit 'Use when' trigger and a clear Brass anchor, but describes the skill in generic data-management terms that understate the actual product (financial planning, expense tracking, budgeting). Trigger vocabulary misses the natural financial terms users would say. It is serviceable but leaves discovery and capability clarity on the table.

Suggestions

Replace the generic "Manage data, records, and automate workflows" with Brass's concrete capabilities from the body (e.g., expense tracking, budgeting, spend and cash-flow reporting).

Add natural trigger terms users would actually say — expenses, spend, budget, transactions, cash flow — alongside "Brass".

State what Brass is (a financial planning and spend management platform for SMBs) so the skill is distinguishable from generic data/workflow tools.

DimensionReasoningScore

Specificity

"Manage data, records, and automate workflows" names the Brass domain but the actions are generic — no concrete capabilities like expense tracking or budgeting are stated. Fits the anchor 'Names the domain but actions are minimal or generic'; not 3 because no concrete action is enumerated, not 1 because the domain is explicitly named.

2 / 5

Completeness

Both parts are present: a (weak) what ("Manage data, records, and automate workflows") and an explicit when ("Use when the user wants to interact with Brass data"). Fits 'Has both what and when; when could be more explicit or specific'; not 5 because the what lacks concrete capabilities and the when is narrow, not 3 because the Use-when clause is explicit.

4 / 5

Trigger Term Quality

"Brass" and "Brass data" are relevant natural keywords, but the phrases finance users would actually say (expenses, spend, budget, cash flow) are entirely missing. Fits 'Some relevant keywords but missing common variations or synonyms'; not 2 since Brass is a specific natural keyword, not 4 since the most common user phrasings are absent.

3 / 5

Distinctiveness Conflict Risk

The description is gated on the distinct app name Brass ("interact with Brass data"), giving minimal conflict risk, but the generic "automate workflows" phrase could overlap with workflow-automation skills. Fits 'Mostly distinct; minor overlap risk with closely related skills'; not 5 because the generic workflow phrasing is not fully fenced off.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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/brass/SKILL.md

Reviewed

Table of Contents

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.