ai21-labs
AI21 Labs integration. Manage data, records, and automate workflows. Use when the user wants to interact with AI21 Labs data.
58
67%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/ai21-labs/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.
The description benefits from naming a specific vendor (AI21 Labs) and including an explicit 'Use when' clause, but it is severely lacking in specificity about what concrete actions the skill performs. The generic terms 'data', 'records', and 'workflows' provide almost no useful information for distinguishing this skill from other integration skills.
Suggestions
Replace vague terms like 'manage data, records, and automate workflows' with specific AI21 Labs capabilities (e.g., 'Generate text using Jurassic models, paraphrase content with Wordtune, summarize documents via AI21 APIs').
Add more natural trigger terms users might say, such as specific AI21 product names, API endpoints, or common use cases like 'Jurassic', 'text generation', 'paraphrasing', 'AI21 API'.
Expand the 'Use when' clause with more specific trigger scenarios, e.g., 'Use when the user mentions AI21 Labs, Jurassic models, or wants to call AI21 APIs for text generation or paraphrasing.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'manage data, records, and automate workflows' without specifying any concrete actions. There are no specific capabilities listed—what kind of data? What workflows? What records? | 1 / 3 |
Completeness | It does answer both 'what' (manage data, records, automate workflows) and 'when' (when the user wants to interact with AI21 Labs data) with an explicit 'Use when' clause, even though both parts are vague in substance. | 3 / 3 |
Trigger Term Quality | It includes 'AI21 Labs' as a trigger term which is relevant and specific to the vendor, but 'data', 'records', and 'workflows' are extremely generic terms that would overlap with many other skills. Missing natural terms users might say like specific AI21 product names (Jurassic, Wordtune, etc.) or API-related terms. | 2 / 3 |
Distinctiveness Conflict Risk | 'AI21 Labs' provides some distinctiveness as a vendor-specific trigger, but 'manage data, records, and automate workflows' is so generic it could easily conflict with dozens of other integration or data management skills. | 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 integration skill with excellent actionability and workflow clarity — every step has concrete CLI commands and the connection setup flow handles edge cases well with explicit state-based branching. The main weaknesses are some unnecessary introductory explanation that Claude doesn't need and a monolithic structure that could benefit from splitting detailed reference material into separate files.
Suggestions
Remove the introductory paragraph explaining what AI21 Labs is — Claude already knows this. Start directly with the overview of available capabilities.
Consider moving the proxy request options table and detailed CLIENT_ACTION_REQUIRED handling into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes some unnecessary explanation (e.g., 'AI21 Labs provides advanced language AI models. Developers and businesses use these models for text generation, summarization, and other natural language processing tasks.' is something Claude already knows). The Membrane CLI instructions are mostly efficient but could be tightened — the proxy request options table and some repeated patterns add bulk. | 2 / 3 |
Actionability | The skill provides concrete, executable CLI commands for every step: installation, authentication, connection setup, action discovery, action execution, and proxy requests. Commands are copy-paste ready with clear parameter placeholders. | 3 / 3 |
Workflow Clarity | The multi-step connection workflow is clearly sequenced with explicit state checks (READY, BUILDING, CLIENT_ACTION_REQUIRED, error states) and feedback loops (poll until ready, handle client actions, then proceed). The numbered steps and conditional branching are well-defined. | 3 / 3 |
Progressive Disclosure | The content is a single monolithic file with no references to supporting documents. While the sections are reasonably organized with headers, the proxy request options table and detailed connection state handling could be split into separate reference files. For a skill of this length (~100+ lines), some progressive disclosure would improve navigability. | 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
f484c82
- 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.