CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

brex-automation

Automate Brex tasks via Rube MCP (Composio). Always search tools first for current schemas.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./composio-skills/brex-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 tight, actionable workflow: concrete tool-call patterns with parameters, an explicit connection checkpoint with auth-link error recovery, and a pitfalls section covering schema drift, session reuse, and pagination. Its only weaknesses are mild redundancy around the "search first" rule and the absence of a concrete worked example or post-execution error handling.

DimensionReasoningScore

Conciseness

The body is lean — commands, code blocks, and bullet pitfalls with no explanations of concepts Claude already knows. Minor trimming is possible: "Always search first" is repeated in Prerequisites, Tool Discovery, Core Workflow Step 1, and Known Pitfalls, and the Tool Discovery section duplicates Core Workflow Step 1.

4 / 5

Actionability

Concrete tool names, parameter structures, and a specific endpoint URL ("Add https://rube.app/mcp as an MCP server") make the guidance mostly executable. The placeholder arguments ("{/* schema-compliant args from search results */}") are justified by the explicit "schemas change, never hardcode" design, but no worked example with a real tool slug is shown.

4 / 5

Workflow Clarity

A clear 3-step sequence (discover → check connection → execute) with an explicit validation checkpoint and error-recovery loop: "If connection is not ACTIVE, follow the returned auth link... Confirm connection status shows ACTIVE before running any workflows." Minor gap: no guidance on handling execution failures or unexpected responses after RUBE_MULTI_EXECUTE_TOOL.

4 / 5

Progressive Disclosure

No bundle files exist and none are needed: the ~85-line body is self-contained with well-organized sections (Prerequisites, Setup, Workflow, Pitfalls, Quick Reference), a clearly signaled one-level-deep external link, and a quick-reference table for navigation.

5 / 5

Total

17

/

20

Passed

Description

48%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 identifies a distinct niche (Brex automation via Rube MCP) but is thin: it states a generic "what" with no concrete capabilities and completely omits "when to use it" trigger guidance. Adding 1–2 concrete actions and a "Use when..." clause with natural trigger terms would move it substantially closer to the good examples.

Suggestions

List 2–3 concrete capabilities in the description, e.g., "Automate Brex operations — manage corporate cards, expenses, transactions, and reconciliations via Rube MCP (Composio)"

Append an explicit trigger clause such as "Use when the user mentions Brex, corporate cards, expense management, or asks to automate Brex workflows"

Keep the "Always search tools first" behavior guidance in the body; replace it in the description with natural keywords users would actually say

DimensionReasoningScore

Specificity

"Automate Brex tasks" names the domain but "tasks" is generic — no concrete capabilities (e.g., cards, expenses, transactions, reconciliation) are listed. The companion sentence "Always search tools first for current schemas" is a behavior instruction, not a capability, so it cannot count as a concrete action.

2 / 5

Completeness

The "what" is present ("Automate Brex tasks via Rube MCP") but the "when" is missing entirely — there is no "Use when..." clause or equivalent trigger guidance, which caps this dimension at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"Brex" and "automate" are natural user terms, but coverage stops there — common variations like expenses, corporate cards, receipts, or transactions are absent, and "Rube MCP (Composio)" is technical jargon a user would not naturally say.

3 / 5

Distinctiveness Conflict Risk

"Brex" plus the specific Rube MCP/Composio stack is a clear niche with minimal conflict risk, but the broad "Automate Brex tasks" phrasing without reinforcing trigger phrases leaves minor overlap risk with adjacent finance- or automation-oriented skills, so it sits at anchor 4 rather than 5.

4 / 5

Total

12

/

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

ComposioHQ/awesome-claude-skills

Path

composio-skills/brex-automation/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.