Abstract integration. Manage data, records, and automate workflows. Use when the user wants to interact with Abstract data.
Install with Tessl CLI
npx tessl i github:membranedev/application-skills --skill abstract68
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
57%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 suffers from vague, generic capability statements that fail to differentiate Abstract from other data management tools. While it includes the required 'Use when...' clause, the lack of specific actions (what exactly can you do with Abstract?) and the generic nature of 'data, records, workflows' makes it difficult for Claude to confidently select this skill over similar integrations.
Suggestions
Replace generic terms with specific Abstract capabilities (e.g., 'Create and manage design version branches, inspect layer properties, export assets from Abstract design files')
Add Abstract-specific trigger terms users would naturally say (e.g., 'design versioning', 'Sketch files', 'design handoff', 'Abstract branches', 'design system')
Clarify what type of 'data' and 'records' Abstract manages to distinguish it from generic database or CRM integrations
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'Manage data, records, and automate workflows' without specifying concrete actions. These are generic terms that could apply to almost any integration tool. | 1 / 3 |
Completeness | The description does answer both 'what' (manage data, records, automate workflows) and 'when' (Use when the user wants to interact with Abstract data), with an explicit trigger clause present. | 3 / 3 |
Trigger Term Quality | Includes 'Abstract' as a keyword which users would say, but lacks variations or specific feature terms. 'Data, records, workflows' are too generic to serve as effective triggers. | 2 / 3 |
Distinctiveness Conflict Risk | 'Abstract' as a product name provides some distinctiveness, but 'manage data, records, and automate workflows' is extremely generic and could overlap with dozens of other integration skills. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, actionable CLI commands for integrating with Abstract via Membrane, with good coverage of common operations. However, it includes unnecessary introductory content about what Abstract is, has an incomplete overview section, and lacks validation checkpoints in the workflow. The structure is adequate but could be tightened.
Suggestions
Remove the introductory paragraph explaining what Abstract is - Claude already knows this and it wastes tokens
Either complete the 'Abstract Overview' bullet list with actionable information or remove it entirely
Add validation steps after key operations (e.g., 'Verify connection succeeded by running `membrane connection list --json` and confirming the connection appears')
Integrate the 'Getting list of existing connections' section into the main connection workflow as a first step to check before creating new connections
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanation (e.g., 'Abstract is a design collaboration platform for designers and developers' and general descriptions of what Abstract does). The overview section listing entities without context adds little value. However, the CLI commands are reasonably concise. | 2 / 3 |
Actionability | Provides fully executable CLI commands throughout with clear syntax examples. Commands for installation, login, connection, action discovery, and proxy requests are all copy-paste ready with proper flags and parameters documented. | 3 / 3 |
Workflow Clarity | Steps are listed for setup and connection but lack explicit validation checkpoints. The workflow doesn't specify how to verify a connection succeeded or what to do if commands fail. The 'Getting list of existing connections' section is awkwardly placed and could be better integrated into the workflow. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but the 'Abstract Overview' section with bullet points (Task, Project, Section, etc.) is incomplete and unhelpful. No references to external files for advanced topics. The proxy requests section could be split out for complex use cases. | 2 / 3 |
Total | 9 / 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 | |
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.