CtrlK
BlogDocsLog inGet started
Tessl Logo

make-automation

Automate Make (Integromat) tasks via Rube MCP (Composio): operations, enums, language and timezone lookups. Always search tools first for current schemas.

56

1.07x
Quality

37%

Does it follow best practices?

Impact

87%

1.07x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/all-skills/skills/make-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

40%

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 clear and distinctive niche (Make/Integromat automation via specific MCP tooling), which reduces conflict risk. However, it lacks an explicit 'Use when...' clause, uses somewhat vague capability terms like 'operations', and misses common user trigger terms like 'automation', 'workflow', or 'scenarios'. The procedural instruction to 'search tools first' is better suited for the skill body than the description.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Make/Integromat automations, scenarios, modules, or workflow configuration.'

Replace vague terms like 'operations' with specific actions such as 'create scenarios', 'configure modules', 'list connections', or 'manage webhooks'.

Include natural user trigger terms like 'automation', 'workflow', 'scenarios', 'modules', and 'integrations' to improve discoverability.

DimensionReasoningScore

Specificity

Names the domain (Make/Integromat via Rube MCP/Composio) and mentions some actions (operations, enums, language and timezone lookups), but these are somewhat vague and not fully concrete—'operations' is generic, and the instruction to 'search tools first' is procedural rather than capability-describing.

2 / 3

Completeness

Describes what it does at a high level but has no explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is entirely missing, which per the rubric should cap completeness at 2, and the 'what' is also weak enough to warrant a 1.

1 / 3

Trigger Term Quality

Includes relevant keywords like 'Make', 'Integromat', 'Composio', 'Rube MCP', 'timezone', and 'language lookups', but misses common user-facing variations (e.g., 'automation', 'workflow', 'scenarios', 'modules', 'connections') that users would naturally say when needing this skill.

2 / 3

Distinctiveness Conflict Risk

The combination of 'Make (Integromat)', 'Rube MCP', and 'Composio' creates a very specific niche that is unlikely to conflict with other skills. The tooling stack is distinctive enough to clearly differentiate this skill.

3 / 3

Total

8

/

12

Passed

Implementation

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is significantly over-engineered for what amounts to 3 simple API tools. It spends excessive tokens on caching strategies, alternative approaches, rate limit advice, and authentication details that Claude already understands or that aren't specific enough to be actionable. The core value — tool names, when to use them, and the setup flow — is buried in verbose surrounding content.

Suggestions

Reduce content by 60%+: Remove sections on caching strategy, rate limits, authentication details, response parsing, and alternative approaches — these are either common knowledge for Claude or too vague to be actionable.

Add concrete executable examples showing exact RUBE_SEARCH_TOOLS and MAKE_GET_OPERATIONS calls with real parameter values instead of pseudocode numbered lists.

Move the 'Alternative Approaches' and 'Known Pitfalls' sections to a separate ADVANCED.md file and link to it, keeping SKILL.md focused on the quick reference table and core 3-tool workflows.

Add a validation step after MAKE_GET_OPERATIONS showing how to check for pagination and handle incomplete results.

DimensionReasoningScore

Conciseness

Extremely verbose for a skill covering only 3 simple tools (get operations, list languages, list timezones). Extensive sections on caching strategies, alternative approaches, rate limits, authentication details, and response parsing are largely things Claude already knows or could infer. The content could be reduced by 60-70% without losing actionable value.

1 / 3

Actionability

Provides tool names and general sequences but no executable code or concrete parameter examples. Instructions like 'check current schema via RUBE_SEARCH_TOOLS for available filters' are vague. The pseudocode-style numbered lists describe what to do abstractly rather than showing exact tool calls with parameters.

2 / 3

Workflow Clarity

Steps are listed in sequence for each workflow, but validation checkpoints are weak. The setup section has a good connection verification flow, but the core workflows lack explicit validation/error-recovery steps. For operations monitoring (which could involve large data), there's no feedback loop for handling pagination or errors.

2 / 3

Progressive Disclosure

Content is organized with headers and a quick reference table, which helps navigation. However, it's monolithic — the alternative approaches table, known pitfalls, and common patterns sections could be split into separate files. The single external link to Composio docs is helpful but the skill itself contains too much inline content that should be separated.

2 / 3

Total

7

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
davepoon/buildwithclaude
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.