Name: witai
Rating: 61.6 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

witai

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

Quality

72%

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/witai/SKILL.md

Quality

Content

82%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 a strong, actionable reference: concrete CLI commands, a clear connection workflow with state-based validation, and well-organized sections. The main gaps are a brief unnecessary intro paragraph and lack of validation guidance around the destructive delete actions.

Suggestions

Trim or remove the opening paragraph explaining what Wit.ai is, since Claude already knows this; start directly with how to use the skill.

Add a short validation/feedback note for destructive actions (delete-app, delete-intent, delete-entity, delete-trait), e.g. confirming the target ID before running and checking the response for success.

Consider moving the full popular-actions table into a separate reference file (e.g. ACTIONS.md) and keeping only the most common actions inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with executable commands and tight tables, but the opening paragraph ("Wit.ai is a natural language processing platform that allows developers to build conversational interfaces...") explains what Wit.ai is — knowledge Claude largely already has. Not a 5 because of that minor over-explanation; not a 3 because the rest is efficient and not padded.	4 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection ensure/get, action list/run, and proxy requests, plus a flags table covering the common cases. Not a 4 because the examples are complete and executable rather than having minor gaps.	5 / 5
Workflow Clarity	The connection workflow is clearly sequenced with checkpoints: poll --wait, branch on READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR, and re-poll after user action. Not a 5 because destructive actions (delete-app, delete-intent, etc.) appear only in the actions table with no validation/feedback guidance; not a 3 because the primary workflow does have explicit validation via state polling.	4 / 5
Progressive Disclosure	The content is well-organized into clear sections (Install, Authentication, Connecting, Searching, Popular actions, Proxy, Best practices) with no nested references and no bundle files to misuse. Not a 5 because the large popular-actions table is inlined where a separate reference file could offload it; not a 3 because structure and navigation are good rather than merely present.	4 / 5
	Total	17 / 20 Passed

Description

62%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 uses third person and includes an explicit "Use when..." trigger, satisfying the what/when requirement. Its main weakness is generic action verbs and thin trigger-term coverage rather than concrete Wit.ai capabilities.

Suggestions

Replace generic verbs with concrete Wit.ai capabilities, e.g. "Manage Wit.ai apps, intents, entities, traits, and utterances, and analyze messages for NLP extraction."

Broaden trigger terms to natural synonyms users say, such as "Wit.ai, NLP, intents, entities, chatbot training, or message analysis."

Make the "when" clause more specific than "interact with Wit.ai data" by naming the actual operations that should trigger the skill.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Wit.ai domain and a few action categories, but the verbs are generic rather than concrete capabilities. Not a 2 because it lists multiple actions rather than a single minimal one; not a 4 because none of the actions are specific (e.g. no mention of intents, entities, utterances, or NLP analysis).	3 / 5
Completeness	It states both what ("Wit.ai integration. Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Wit.ai data"). Not a 5 because the trigger phrase is generic and could be more specific; not a 3 because an explicit "Use when..." clause is present.	4 / 5
Trigger Term Quality	"Wit.ai" and "interact with Wit.ai data" are relevant natural terms, but coverage is thin with no synonyms or related phrasings users might say. Not a 4 because common variations (e.g. "NLP", "intents", "chatbot training") are absent; not a 2 because "Wit.ai" itself is a genuine natural keyword.	3 / 5
Distinctiveness Conflict Risk	"Wit.ai integration" carves a clear niche tied to a specific platform, so conflict risk with other skills is low. Not a 5 because the supporting actions ("manage data, records") are broad and could overlap with generic data skills; not a 3 because the Wit.ai binding makes it clearly distinguishable.	4 / 5
	Total	14 / 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/witai/SKILL.md
Commit: f484c82

Reviewed: 3 days ago

Table of Contents

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.