CtrlK
BlogDocsLog inGet started
Tessl Logo

llm-application-dev-ai-assistant

You are an AI assistant development expert specializing in creating intelligent conversational interfaces, chatbots, and AI-powered applications. Design comprehensive AI assistant solutions with natur

33

Quality

28%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/llm-application-dev-ai-assistant/SKILL.md

The canonical home for this skill is llm-application-dev-ai-assistant in rmyndharis/antigravity-skills

SKILL.md
Quality
Evals
Security

Quality

Content

25%Scale 1-5

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

This skill is a generic template with no domain-specific content for AI assistant development. It contains no concrete code, no specific frameworks or tools, no examples, and no actionable guidance—just abstract meta-instructions that could apply to any topic. The referenced implementation playbook is missing from the bundle, leaving the skill essentially hollow.

Suggestions

Add concrete, executable code examples for at least one AI assistant framework (e.g., LangChain, OpenAI Assistants API, or Rasa) with copy-paste ready snippets for common tasks like conversation management and context handling.

Replace the generic instructions ('Clarify goals,' 'Apply best practices') with specific, actionable steps for AI assistant development, such as defining intents, designing conversation flows, implementing context management, and testing with sample dialogues.

Either provide the referenced `resources/implementation-playbook.md` bundle file or inline the essential patterns and examples directly in the SKILL.md.

Add a concrete workflow with validation checkpoints, e.g., steps for building a basic assistant from scratch with testing/verification at each stage.

DimensionReasoningScore

Conciseness

The skill has some unnecessary boilerplate (e.g., 'Use this skill when' / 'Do not use this skill when' sections that are generic and add little value, the Context section restates what's already in the description). However, it's not excessively verbose—it's relatively short but could be tightened significantly.

3 / 5

Actionability

The instructions are entirely vague and abstract: 'Clarify goals,' 'Apply relevant best practices,' 'Provide actionable steps and verification.' There is no concrete code, no specific commands, no examples, no frameworks mentioned, and no executable guidance whatsoever. The skill delegates everything to a referenced file that doesn't exist in the bundle.

1 / 5

Workflow Clarity

There is a rough sequence implied (clarify goals → apply best practices → provide steps → verify), but the steps are so generic they could apply to any domain. No validation checkpoints, no specific workflow for AI assistant development, and no concrete process to follow.

2 / 5

Progressive Disclosure

The skill references `resources/implementation-playbook.md` for detailed patterns, which is a reasonable progressive disclosure strategy. However, no bundle files are provided, so the referenced file doesn't exist, making the reference a dead link. The main content itself is too thin to serve as a useful overview—it's essentially empty, delegating everything to a missing file.

2 / 5

Total

8

/

20

Passed

Description

32%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.

This description is truncated and incomplete, which severely undermines its utility. Even the visible portion is vague, using buzzword-heavy language ('comprehensive AI assistant solutions') without concrete actions. It also uses second-person framing ('You are an AI assistant development expert') which is inappropriate for a skill description, and lacks any 'Use when...' trigger guidance.

Suggestions

Complete the truncated description and add a clear 'Use when...' clause with specific trigger phrases like 'Use when the user asks to build a chatbot, design a conversational interface, or create an AI assistant application.'

Replace vague language with concrete actions such as 'Designs dialog flows, implements intent recognition, configures NLU pipelines, builds chatbot integrations with messaging platforms.'

Rewrite in third person voice ('Designs conversational interfaces...') instead of second person ('You are an expert...').

DimensionReasoningScore

Specificity

The description names the domain ('AI assistant development', 'conversational interfaces', 'chatbots') but the actions are vague and generic ('Design comprehensive AI assistant solutions'). No concrete actions like specific tasks or outputs are listed.

2 / 5

Completeness

The description appears truncated and provides only a vague 'what' ('Design comprehensive AI assistant solutions with natur...'). There is no 'when' clause or trigger guidance at all, and the description is incomplete, which caps completeness severely.

2 / 5

Trigger Term Quality

Includes some relevant keywords like 'chatbots', 'conversational interfaces', 'AI-powered applications', and 'AI assistant', but misses natural user phrases and synonyms like 'virtual assistant', 'dialog system', 'voice bot', 'NLP', or specific frameworks/tools.

3 / 5

Distinctiveness Conflict Risk

The description is very broad — 'AI assistant development' and 'AI-powered applications' could overlap with numerous other skills related to coding, NLP, software development, or general AI tasks. It lacks a clear niche.

2 / 5

Total

9

/

20

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.