llm-application-dev-ai-assistant — Claude Code skill: what it does
llm-application-dev-ai-assistant — a skill for designing conversational AI assistants: dialogue context, integration boundaries, validation. Fits projects where the bot calls tools and keeps memory of a user.
MIT ★ 50,109 updated 2026-10-29
npx skills add sickn33/agentic-awesome-skills --skill llm-application-dev-ai-assistant -a claude-codeWhat llm-application-dev-ai-assistant does
The skill sets an order of work on a conversational assistant: goals and constraints first, then one narrow slice, then checks. It ships instructions plus resources/implementation-playbook.md with patterns. Treat that playbook as a sketch — providers, models and config fields stay open, and its Python snippets will not run as a project.
On safety the text is blunt. A model's confidence about what the user wants does not authorise the action. Each tool call needs an identity check on the server, object and tenant permissions, argument validation at runtime, approval for anything with a side effect, capped retries and idempotency. Dialogue text and retrieved content count as untrusted.
Before promotion, run a fixed evaluation set, break errors down by subgroup, and gate the rollout with a rollback path. A failed safety-critical step must not be answered from cache. The skill is tagged risk: critical, and it tells you to stop and ask when permissions or success criteria are missing.
What it helps with
- Map out dialogue context and per-user memory for an assistant
- Define who may call which tool, down to tenant and object
- Build a fixed evaluation set before shipping a prompt change
- Decide what happens when the model provider fails
- Separate the playbook's sketch from code you would run in production
Example prompts for the agent
- Design an assistant for support tickets: context retention, argument checks before each tool call, a rollback path on failure.
- Read
resources/implementation-playbook.mdand turn it into an acceptance checklist for the chatbot. - Review the tool access model: tenant scoping, idempotency, retry limits.
How to install llm-application-dev-ai-assistant
1Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill llm-application-dev-ai-assistant -a claude-code2Manually: put the files in place
~/.claude/skills/llm-application-dev-ai-assistant/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llm-application-dev-ai-assistant/
1Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill llm-application-dev-ai-assistant -a codex2Manually: put the files in place
.agents/skills/llm-application-dev-ai-assistant/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill llm-application-dev-ai-assistant -a cursor2Manually: put the files in place
.cursor/skills/llm-application-dev-ai-assistant/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sickn33/agentic-awesome-skills skills/llm-application-dev-ai-assistant2Manually: put the files in place
.github/skills/llm-application-dev-ai-assistant/SKILL.md1Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill llm-application-dev-ai-assistant -a gemini-cli2Platform CLI
gemini skills install https://github.com/sickn33/agentic-awesome-skills --path skills/llm-application-dev-ai-assistantManually: put the files in place
.devin/skills/llm-application-dev-ai-assistant/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill llm-application-dev-ai-assistant -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about llm-application-dev-ai-assistant
How do I install llm-application-dev-ai-assistant in Claude Code?
Run npx skills add sickn33/agentic-awesome-skills --skill llm-application-dev-ai-assistant -a claude-code. The skill lands at ~/.claude/skills/llm-application-dev-ai-assistant/SKILL.md.
What does llm-application-dev-ai-assistant do?
It walks through building a conversational assistant: keeping dialogue context, deciding who may call which tool, and validating answers against a fixed evaluation set.
Does the skill generate a working assistant on its own?
No. The playbook is scaffolding with open provider and config fields, and the embedded Python is not a runnable project. You still write the code and set the permissions.
Source text
SKILL.md · MIT
--- name: llm-application-dev-ai-assistant description: "Design and implement conversational AI assistants with context management, integration boundaries, and validation." risk: critical source: community date_added: "2026-02-27" --- # 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.
© sickn33 · MIT · sickn33/agentic-awesome-skills