abstract
Abstract integration. Manage data, records, and automate workflows. Use when the user wants to interact with Abstract data.
73
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/abstract/SKILL.mdQuality
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 follows the correct structural pattern with a 'Use when...' clause, but the actual content is extremely vague and generic. The capabilities listed ('manage data, records, and automate workflows') could describe virtually any integration tool. Without specific actions tied to Abstract's actual functionality, this description provides little value for skill selection among many similar integration skills.
Suggestions
Replace generic actions with specific Abstract capabilities (e.g., 'manage design versions, browse collections, review branches, export design assets').
Add natural trigger terms that users would actually say when needing this skill, such as specific Abstract concepts like 'design files', 'branches', 'commits', 'collections', or file types.
Differentiate from other integration skills by specifying what makes Abstract unique (e.g., 'design version control platform') rather than using generic 'manage data' language.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The actions listed ('manage data, records, and automate workflows') are extremely vague and generic. There are no concrete, specific actions like 'create records', 'sync projects', or 'export design assets'. 'Abstract' as a product name is mentioned but the capabilities described could apply to almost any integration. | 1 / 3 |
Completeness | It 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. While the content is vague, the structure is complete. | 3 / 3 |
Trigger Term Quality | It includes 'Abstract' as a keyword which is the product name, and 'data', 'records', 'workflows' are somewhat relevant but very generic. It lacks specific terms users might say like 'design versions', 'branches', 'collections', or 'Abstract API' depending on what Abstract actually does. | 2 / 3 |
Distinctiveness Conflict Risk | 'Abstract' as a product name provides some distinctiveness, but 'manage data, records, and automate workflows' is so generic it could overlap with dozens of other integration skills. Only the word 'Abstract' prevents this from being a 1. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with clear CLI commands and well-defined state-handling workflows for the Membrane integration pattern. Its main weaknesses are some unnecessary introductory explanation about Abstract that Claude doesn't need, and the entity overview section that lists concepts without actionable guidance or links. The workflow clarity is strong with explicit polling loops and error state handling.
Suggestions
Remove or drastically shorten the introductory paragraph about what Abstract is — Claude already knows this, and the description field covers it.
Either flesh out the Abstract entity overview section with actionable guidance (e.g., example action queries for each entity type) or remove it entirely, as the bare list adds little value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanation (e.g., 'Abstract is a design collaboration platform for designers and developers. It helps teams manage, version, and document their design files...') that Claude already knows. The Membrane CLI workflow sections are reasonably efficient but could be tightened — for instance, the overview section listing Abstract entities adds little value without actionable detail. | 2 / 3 |
Actionability | The skill provides concrete, copy-paste-ready CLI commands for every step: installation, authentication, connection management, action discovery, action creation, and action execution. Input parameters and flags are clearly specified with executable examples. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced: install CLI → authenticate → ensure connection → handle connection states (with explicit state machine: BUILDING, READY, CLIENT_ACTION_REQUIRED, errors) → search for actions → create if needed → run. Validation checkpoints and polling/retry loops are explicitly documented for both connections and actions. | 3 / 3 |
Progressive Disclosure | The content is reasonably structured with clear section headers, but it's a monolithic file with no references to external files for advanced topics. The Abstract entity overview section (Task, Project, Section, etc.) is listed but provides no actionable detail or links to further documentation, making it feel incomplete rather than well-disclosed. | 2 / 3 |
Total | 10 / 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 | |
- Repository
- membranedev/application-skills
- Commit
88db8c5
- 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.