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

36%

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

28%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 skill body is short and well-sectioned but almost entirely generic: it reprints the description, gives abstract process advice Claude already knows, provides no executable or domain-specific guidance, and points to a resource file that is missing from the bundle. It reads as a template skeleton rather than a working skill.

Suggestions

Replace the generic Instructions bullets with concrete, AI-assistant-specific steps (e.g., define intent schema, implement tool-calling handlers, add context-window pruning, validate with eval prompts).

Remove the duplicated description opener and the generic Context restatement so every remaining token earns its place.

Either add the missing 'resources/implementation-playbook.md' bundle file or drop the reference, so progressive disclosure points to real, one-level-deep material.

Dimension	Reasoning	Score
Conciseness	The body reprints the frontmatter description verbatim as its opener and fills the Instructions with generic process platitudes ('Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes') that Claude already knows and that carry no AI-assistant-specific information, matching the anchor for noticeably verbose, padded sections.	2 / 5
Actionability	Guidance is almost entirely high-level hints with no code, commands, or concrete steps specific to assistant development; the only concrete element is a pointer to 'resources/implementation-playbook.md', giving minimal concrete guidance but missing the specific steps to execute.	2 / 5
Workflow Clarity	Instructions are a generic three-bullet list (clarify, apply best practices, provide steps) with a rough implied sequence but poorly defined steps and only abstract mention of validation ('validate outcomes', 'verification') rather than explicit checkpoints, fitting the anchor for rough sequence with many gaps and absent validation.	2 / 5
Progressive Disclosure	The body is well sectioned (Use when / Do not use / Context / Requirements / Instructions / Resources) and signals a one-level-deep reference ('resources/implementation-playbook.md') clearly, but that referenced file does not exist in the bundle (references/, scripts/, assets/, resources/ are all absent), so organization is only partially effective.	3 / 5
	Total	9 / 20 Passed

Description

45%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 conveys the domain and a few capabilities but relies on buzzwords, uses second-person voice (penalized), and omits any explicit trigger guidance, capping completeness. It is serviceable but generic and would benefit from concrete actions plus a 'Use when...' clause.

Suggestions

Rewrite in third person and replace generic verbs ('Design comprehensive solutions') with concrete actions (e.g., 'Design dialog flows, wire up tool-calling, manage multi-turn context, integrate retrieval-augmented generation').

Add an explicit trigger clause: 'Use when building chatbots, AI assistants, conversational interfaces, or LLM-powered applications with natural language understanding.'

Include natural synonyms users actually say ('bot', 'virtual assistant', 'LLM app') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('intelligent conversational interfaces, chatbots, and AI-powered applications') and lists a few capabilities ('natural language understanding, context management, and seamless integrations'), but the actions are generic and buzzword-heavy; the second-person voice ('You are an AI assistant development expert') triggers the mandatory -1 specificity penalty, dropping it from a base of 3 to 2.	2 / 5
Completeness	It gives a clear 'what' (design AI assistant solutions with NLU, context management, integrations) but provides no 'Use when...' clause or equivalent trigger guidance, so per the rubric cap completeness is held at 3 — the anchor for clear-what with missing-when.	3 / 5
Trigger Term Quality	It includes some relevant natural keywords ('AI assistant', 'chatbots', 'conversational interfaces') a user might say, but misses common variations and synonyms like 'bot', 'virtual assistant', or 'LLM app', matching the anchor for some-but-incomplete keyword coverage.	3 / 5
Distinctiveness Conflict Risk	'AI assistant development' is a somewhat specific niche thanks to 'chatbots' and 'conversational interfaces', but the domain is broad enough to overlap with general app-development, LLM-application, and ML skills, fitting the 'somewhat specific but could still overlap' anchor.	3 / 5
	Total	11 / 20 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: 3eff4af

Reviewed: 24 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.