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

Quality

37%

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/llm-application-dev-ai-assistant/SKILL.md

Quality

Content

35%Weight 40%Scale 1-3

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 short, well-sectioned but generic scaffold: abstract directives with no concrete examples or real validation steps, and a referenced playbook whose path does not exist. It reads as boilerplate rather than actionable, domain-specific guidance for AI assistant development.

Suggestions

Replace abstract directives with concrete, domain-specific guidance (e.g., specific steps for drafting system prompts, defining tool/function-calling schemas, and designing context-management and conversation flows).

Add explicit validation checkpoints with feedback loops (e.g., 'review the drafted prompt for missing edge cases', 'simulate a sample conversation to test context handling before finalizing').

Create the referenced `resources/implementation-playbook.md` with real patterns and examples, or remove the dangling reference, since no bundle file currently exists.

Dimension	Reasoning	Score
Conciseness	The body is short and free of concept-explanation padding, but it leans on generic boilerplate ('Apply relevant best practices and validate outcomes', 'Provide actionable steps and verification') that adds little Claude does not already know, so it is efficient but not fully lean and high-value.	2 / 3
Actionability	The instructions are abstract directives ('Clarify goals, constraints, and required inputs', 'Apply relevant best practices') with no concrete code, commands, or specific examples — it describes rather than instructs, matching the 'vague or abstract; no concrete code/commands' anchor.	1 / 3
Workflow Clarity	A loose sequence is present ('Clarify goals' -> 'Apply best practices' -> 'Provide actionable steps and verification'), but validation checkpoints are only vaguely implied ('validate outcomes') with no explicit feedback loop, matching 'steps listed but validation gaps'.	2 / 3
Progressive Disclosure	The body is organized into clear sections and signals a one-level-deep reference (`resources/implementation-playbook.md`), but no `resources/`, `references/`, `scripts/`, or `assets/` directory or bundle file actually exists, so the reference is dangling and prevents a higher rating.	2 / 3
	Total	7 / 12 Passed

Description

40%Weight 40%Scale 1-3

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 is a generic, second-person mission statement that names a domain and a few natural keywords but lists only abstract actions, provides no explicit 'when to use' triggers, and is truncated mid-word. It is only weakly distinguishable from broad AI/LLM application-development skills.

Suggestions

Switch to third-person voice and replace the broad mission statement with concrete, specific actions (e.g., 'Drafts system prompts, designs conversation flows, defines tool/function-calling schemas, and plans context-management strategies for chatbots and AI assistants').

Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when building a chatbot, designing an AI assistant, or planning conversation flows and prompt strategies').

Fix the truncated text so the description reads as a complete sentence rather than ending mid-word at 'with natur'.

Dimension	Reasoning	Score
Specificity	It names a domain and some actions ('creating intelligent conversational interfaces, chatbots, and AI-powered applications', 'Design comprehensive AI assistant solutions'), but the actions are abstract rather than multiple concrete granular ones (base 2); the description uses second-person voice ('You are an AI assistant development expert'), which the rubric penalizes by reducing specificity by 1.	1 / 3
Completeness	It states what the skill does (design AI assistant/chatbot solutions) but never states when to use it, and the rubric caps completeness at 2 when an explicit 'Use when...' trigger clause is missing; the truncation ('with natur') prevents a higher rating.	2 / 3
Trigger Term Quality	It contains some natural terms a user would say ('chatbots', 'AI assistant', 'AI-powered applications'), but it omits common variations and has no 'Use when...' clause, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	It is somewhat specific to AI assistants and chatbots, but 'AI-powered applications' and 'AI assistant solutions' are broad enough to overlap with general LLM/app-development sibling skills, matching 'somewhat specific but could still overlap'.	2 / 3
	Total	7 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/llm-application-dev-ai-assistant/SKILL.md
Commit: e63f7dd

Reviewed: 13 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.