Automate Adobe tasks via Rube MCP (Composio). Always search tools first for current schemas.
69
Quality
53%
Does it follow best practices?
Impact
99%
7.07xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./composio-skills/adobe-automation/SKILL.mdQuality
Discovery
22%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is too vague to effectively guide skill selection. It mentions Adobe and the integration mechanism (Rube MCP/Composio) but fails to specify concrete capabilities or provide trigger guidance. Users searching for help with specific Adobe products or tasks may not match this skill.
Suggestions
Add a 'Use when...' clause specifying trigger scenarios, e.g., 'Use when the user mentions Photoshop, Illustrator, InDesign, or Adobe automation tasks'
Replace 'Automate Adobe tasks' with specific actions like 'Edit Photoshop layers, export Illustrator files, batch process images, run Adobe scripts'
Include natural user terms and file extensions users would mention: '.psd', '.ai', 'Photoshop', 'image editing', 'design automation'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'Automate Adobe tasks' without specifying what tasks (e.g., edit images, create PDFs, manipulate layers). 'Always search tools first' is procedural guidance, not a capability description. | 1 / 3 |
Completeness | Partially addresses 'what' (automate Adobe tasks) but very weakly. Completely missing a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Contains 'Adobe' and 'Rube MCP' and 'Composio' as keywords, but lacks natural user terms like specific Adobe products (Photoshop, Illustrator, Acrobat), file types (.psd, .ai), or common actions users would request. | 2 / 3 |
Distinctiveness Conflict Risk | 'Adobe' and 'Rube MCP (Composio)' provide some distinctiveness, but 'automate tasks' is generic enough to potentially conflict with other automation skills. Lacks specific Adobe product or action triggers. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that efficiently teaches Adobe automation via Rube MCP. It excels at workflow clarity with explicit connection verification steps and comprehensive pitfall documentation. The main weakness is that the tool call examples use generic placeholders rather than concrete Adobe-specific operations, which reduces immediate actionability.
Suggestions
Add at least one concrete Adobe operation example with real arguments (e.g., 'Create PDF from image' with actual field values) to demonstrate schema compliance
Include an example of what a successful RUBE_SEARCH_TOOLS response looks like for Adobe tools, so users know what to expect
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding explanations of basic concepts. Every section serves a purpose with no padding or unnecessary context about what Adobe or APIs are. | 3 / 3 |
Actionability | Provides concrete tool call patterns with specific parameters, but the examples are more template-like than fully executable. The arguments sections use placeholders rather than real Adobe operation examples. | 2 / 3 |
Workflow Clarity | Clear 3-step workflow with explicit validation checkpoint (Step 2: Check Connection). The Known Pitfalls section provides error prevention guidance, and the sequence is unambiguous. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections progressing from prerequisites to setup to workflow to pitfalls. External reference to Composio docs is one level deep. Quick reference table aids navigation. | 3 / 3 |
Total | 11 / 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
2790447
Table of Contents
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.