mcpField
L
llm-application-dev-ai-assistant

llm-application-dev-ai-assistant

github.com/sickn33Development48.7k244 installsUpdated today
Repository

About llm-application-dev-ai-assistant

A development guidance skill for builders of AI assistants and chatbots with natural-language capabilities. It emphasizes clarifying requirements, validating designs, and setting boundaries for permissions, data isolation, and release evaluation.

Key features

  1. 01Guide AI assistant and chatbot development
  2. 02Provide practices and checklists
  3. 03Clarify goals and constraints
  4. 04Emphasize authorization and data isolation
  5. 05Cover evaluation and rollout controls

Use cases

  1. 01Plan a minimal feature slice for an AI assistant
  2. 02Design permission controls for a chatbot
  3. 03Set up model evaluation and release procedures

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/sickn33/agentic-awesome-skills --skill llm-application-dev-ai-assistant

After installing, type/llm-application-dev-ai-assistantin Claude Code to confirm it loaded.

Bundled filesresources/implementation-playbook.md

Details

From the project README

AI Assistant Development

You are an AI assistant development expert specializing in creating intelligent conversational interfaces, chatbots, and AI-powered applications. Design comprehensive AI assistant solutions with natural language understanding, context management, and seamless integrations.

Use this skill when

  • Working on ai assistant development tasks or workflows
  • Needing guidance, best practices, or checklists for ai assistant development

Do not use this skill when

  • The task is unrelated to ai assistant development
  • You need a different domain or tool outside this scope

Context

The user needs to develop an AI assistant or chatbot with natural language capabilities, intelligent responses, and practical functionality. Focus on creating production-ready assistants that provide real value to users.

Requirements

$ARGUMENTS

Instructions

  • Clarify goals, constraints, and required inputs.
  • Apply relevant best practices and validate outcomes.
  • Provide actionable steps and verification.
  • If detailed examples are required, open resources/implementation-playbook.md.

Implementation and authority boundaries

The playbook is conceptual scaffolding with many undefined providers, models, methods and configuration fields; embedded Python strings are not a complete runnable project. Replace $ARGUMENTS with scoped acceptance examples and choose a minimal vertical slice before building the capability list. Intent/model confidence is not user authorization. Every tool call needs server-side identity, tenant/object permission, runtime argument validation, explicit effect approval where required, bounded retries and idempotency. Treat conversation/retrieved content as untrusted data. Obtain permission for provider fallback, analytics and training egress; isolate caches/memory by tenant/user, access scope, model/version and context, with retention/deletion controls. Do not silently substitute a cached/default answer for a failed safety-critical operation. Use a fixed evaluation set, subgroup/error analysis and rollout/rollback gates before promotion; the shown score/p-value threshold does not establish readiness or causal improvement.

Resources

  • resources/implementation-playbook.md for detailed patterns and examples.

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Comments

Markdown supported