Tessl • The management layer for AI agent skills

SkillPublic

ai21-labs

AI21 Labs integration. Manage data, records, and automate workflows. Use when the user wants to interact with AI21 Labs data.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ai21-labs/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

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

The body is an actionable, command-driven guide with concrete CLI examples covering auth, connection lifecycle, action discovery/execution, and a proxy fallback. Its main weaknesses are broken step references ('Step 2', '1b' with no '1a'), a duplicated action-list command, and an empty 'Popular actions' section.

Suggestions

Fix the dangling workflow references: 'skip to Step 2' points to a nonexistent step and '#### 1b' has no '1a' — either number the full sequence (install → login → connect → search → run) or drop the step labels.

Remove the duplicate action-list command in 'Popular actions' (it repeats 'Searching for actions' with slightly different syntax) and either list concrete popular actions there or delete the header.

Add one worked example of an action run with a real action id and a realistic --input payload so the <actionId>/CONNECTION_ID placeholders have a concrete model.

Dimension	Reasoning	Score
Conciseness	The body is command-focused and efficient, with only minor trimmable content: the action-list command appears twice ('Searching for actions' and 'Popular actions'), 'Use action names and parameters as needed' is filler, and the intro paragraph about what AI21 Labs is adds little. It matches 'Efficient; minor instances of over-explanation' rather than the lean anchor 5.	4 / 5
Actionability	Concrete executable commands throughout — install, login with headless fallback, 'membrane connection ensure', polling with --wait, action run with --input JSON, and a proxy options table. Minor gaps keep it below anchor 5: the 'Popular actions' section lists no actual actions, and placeholders like <actionId> and QUERY never get a concrete worked example.	4 / 5
Workflow Clarity	The overall sequence (install → auth → connect → handle states → search → run → proxy) is present with polling-based checkpoints for connection states, but the structure is broken: 'skip to Step 2' references a step that does not exist and '#### 1b' has no '1a'. Steps are listed with real gaps, matching anchor 3 rather than 4's well-formed sequence.	3 / 5
Progressive Disclosure	A single well-sectioned file with clear headers and no nested or dangling file references; the proxy flag table and connection-state handling are reasonably placed inline. Minor organization gaps (the Membrane boilerplate and proxy details could live in reference files) keep it below anchor 5.	4 / 5
	Total	15 / 20 Passed

Description

57%Weight 40%Scale 1-5

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 correctly names the AI21 Labs domain and includes an explicit 'Use when' trigger, but its capability statements are generic ('manage data, records, automate workflows') rather than concrete, and the trigger phrase is circular. It distinguishes itself mainly through the brand name.

Suggestions

Replace generic verbs with concrete AI21 capabilities, e.g. 'Generate and summarize text with AI21 Labs language models, manage records and datasets' instead of 'Manage data, records, and automate workflows'.

Add natural trigger terms users would actually say — e.g. 'Use when the user mentions AI21, Jurassic models, text generation, or summarization' — instead of the circular 'interact with AI21 Labs data'.

Tie the 'when' clause to concrete tasks (generating text, summarizing documents, managing AI21 datasets) to strengthen both completeness and specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain (AI21 Labs) but its actions — 'Manage data, records, and automate workflows' — are minimal and generic, with no concrete capability like text generation or model completions. This matches the anchor 'Names the domain but actions are minimal or generic' rather than level 3, which requires 1-2 concrete actions.	2 / 5
Completeness	Both a what ('Manage data, records, and automate workflows') and an explicit when ('Use when the user wants to interact with AI21 Labs data') are present, so it clears the missing-trigger cap at 3. The when-clause is circular and could be more specific, so it falls short of anchor 5's concrete trigger phrases.	4 / 5
Trigger Term Quality	'AI21 Labs' is a relevant keyword users would say, but 'data', 'records', and 'workflows' are generic, and natural variations users might use (e.g., text generation, summarization, Jurassic models) are missing. It has some relevant keywords but misses common variations, sitting between anchors 2 and 3.	3 / 5
Distinctiveness Conflict Risk	Being brand-scoped to 'AI21 Labs' data makes it mostly distinct with only minor overlap risk against other app-integration skills. The generic action verbs keep it from anchor 5's clear niche with distinct triggers.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/ai21-labs/SKILL.md
Revision: f484c82

Reviewed: 16 days ago

Discovery Implementation Validation

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.

ai21-labs

Table of Contents

Is this your skill?