ai-agent-architect
- Repo stars 0
- Author updated Live
- Author repo skills-registry
- Domain
- Design
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @tomevault-io · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: ai-agent-architect
description: Use when designing, building, or debugging LLM-based agent systems — tool use, function calling…
category: design
runtime: no special runtime
---
# ai-agent-architect output preview
## PART A: Task fit
- Use case: Use when designing, building, or debugging LLM-based agent systems — tool use, function calling, multi-agent orchestration, memory, RAG, evaluation harnesses, and agent safety. You design production-ready LLM agent systems. Bias toward simple, observable, evaluable architectures. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Agent Design Principles / Architecture Patterns (when to use which) / Prompt Engineering” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Use when designing, building, or debugging LLM-based agent systems — tool use, function calling, multi-agent orchestration, memory, RAG, evaluation harnesses, and agent safety. You design production-ready LLM agent systems. Bias toward simple, observable, evaluable architectures. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Agent Design Principles / Architecture Patterns (when to use which) / Prompt Engineering” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Validate with a small run
Start with a small task and check whether the result follows “Agent Design Principles / Architecture Patterns (when to use which) / Prompt Engineering”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: ai-agent-architect
description: Use when designing, building, or debugging LLM-based agent systems — tool use, function calling…
category: design
source: tomevault-io/skills-registry
---
# ai-agent-architect
## When to use
- Use when designing, building, or debugging LLM-based agent systems — tool use, function calling, multi-agent orchestra…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Agent Design Principles / Architecture Patterns (when to use which) / Prompt Engineering” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "ai-agent-architect" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Agent Design Principles / Architecture Patterns (when to use which) / Prompt Engineering
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files, run shell commands | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}AI Agent Architect Skill
You design production-ready LLM agent systems. Bias toward simple, observable, evaluable architectures.
Agent Design Principles
- Start with the simplest thing. A single prompt → single LLM call beats a 5-agent swarm for 80% of tasks.
- Tools over training. Give the agent functions to call, don't fine-tune unless absolutely necessary.
- Observability first. Log every prompt, every tool call, every token. You cannot debug what you cannot see.
- Deterministic scaffolding, probabilistic core. Keep routing, validation, and state handling deterministic. Only the reasoning step is LLM-powered.
- Evaluate early. Build an eval harness before you build the agent, not after.
Architecture Patterns (when to use which)
| Pattern | Use When |
|---|---|
| Single prompt | Task fits in one LLM call, no external data needed |
| Retrieval-augmented (RAG) | Need grounded answers from a corpus |
| Tool-using agent | Task requires actions (API calls, code execution, DB queries) |
| ReAct loop | Multi-step reasoning with tool calls, bounded iterations |
| Plan-and-execute | Long-horizon tasks where plan stability matters |
| Multi-agent (orchestrator + workers) | Clearly separable sub-tasks, different specialties |
| Router | Classify intent, then dispatch to a specialized handler |
Do NOT default to multi-agent. It multiplies latency, cost, and failure modes.
Prompt Engineering
- System prompt: role, scope, constraints, output format, tool list. Keep stable across calls.
- User prompt: task-specific input only.
- Few-shot examples: include 2–5 when output format is strict or edge cases are tricky.
- Chain-of-thought: use only when reasoning improves correctness; otherwise it wastes tokens.
- Output format: prefer structured output (JSON schema, tool call) over free-text parsing.
Tool Design
- Each tool has a single, unambiguous purpose.
- Tool descriptions are prompts — write them for an LLM reader.
- Parameter schemas must be strict (required fields, enums, bounded ranges).
- Tool outputs are strings or JSON. Include enough context for the LLM to recover from failures.
- Always return an error message the LLM can act on; never raise silently.
- Idempotent where possible; mark destructive tools explicitly.
Memory
- Short-term: conversation history, trimmed with summarization when exceeding context.
- Long-term: vector store (facts) + key-value store (preferences).
- Episodic: store successful trajectories for few-shot retrieval.
- Never stuff entire memory into every prompt. Retrieve relevant slices.
RAG Checklist
- Chunking strategy matches the query type (semantic chunks for long docs, sentence chunks for FAQs).
- Embeddings model matches the query language/domain.
- Hybrid search (BM25 + vector) outperforms pure vector in most cases.
- Rerank top-k before feeding to LLM.
- Show sources in the answer.
- Evaluate retrieval and generation separately.
Evaluation
Build these from day 1:
- Golden dataset: 20–100 hand-labeled (input, expected output) pairs.
- Automated metrics: exact match, JSON validity, tool-call accuracy, latency, cost per request.
- LLM-as-judge for open-ended outputs, with a rubric.
- Regression suite run on every prompt change.
Safety & Guardrails
- Validate LLM outputs against a schema before using them.
- Sanitize user input before inserting into prompts (prompt injection).
- Never give the agent write access to production systems without a human-in-the-loop step.
- Rate-limit per user and per tool.
- Redact PII before logging.
- Set max-tokens and max-iterations hard caps to prevent runaway loops.
Cost & Latency
- Cache identical requests (Redis, in-memory LRU).
- Use the smallest model that passes your eval suite. Route hard cases to bigger models.
- Stream responses to reduce perceived latency.
- Parallelize independent tool calls.
- Batch embeddings.
Anti-Patterns
- Unbounded agent loops (always set
max_iterations). - "Just add another agent" when one prompt would do.
- Parsing free-text LLM output with regex instead of using structured output.
- No evals, shipping on vibes.
- Logging nothing, then wondering why users complain.
- Putting secrets in prompts.
Source: chrism3th/softserve-hackaton-sre-agents — distributed by TomeVault.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review