Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/agent-architecture-planner
Use when designing an autonomous agent, planning agent architecture, building a scheduled automation, or creating a Claude Code agent workflow. Triggers: 'design an agent', 'build an automation', 'agent architecture', 'automate this workflow', 'create a scheduled agent', 'shell script agent'.
Passed 20 of 23 test cases with the skill, and 13 of 23 without it.
and 6 more in the full report
8 fixed13 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
When generating an entire agent package named `lead-qualifier`, what exact directory path should contain all generated artifacts (`run.sh`, `prompt.md`, `config.yaml`, `architecture.md`)? Output contract: State the output path structure.
| Checked | Without skill | With skill |
|---|---|---|
| Outputs files into docs/agents/ path | Missed | Passed |
The instructions your model reads when the skill loads.
Design autonomous agents using the "Shell Orchestrates, Claude Thinks" pattern. This skill takes a workflow description, selects the right architecture pattern, and produces a complete agent package: shell wrapper, system prompt, config, scheduling setup, and cost estimate.
The core principle: the shell handles everything deterministic (API calls, file I/O, scheduling, budget tracking), and Claude handles everything that requires judgment (scoring, filtering, writing, categorizing). This separation makes agents cheaper, more reliable, and easier to debug.
| Tool | Purpose |
|---|---|
Read | Check for existing agent docs, load reference files |
Write | Output all agent architecture files |
Bash | Make shell scripts executable, verify directory structure |
Glob | Check for existing agents to avoid naming conflicts |
Follow these steps in order. Do not skip steps. Do not produce output files before completing the discovery interview and confirming the architecture with the user.
Present these questions to the user all at once in a numbered list. Tell the user they can answer inline or paste a block of text.
Ask exactly these questions:
I need to understand the workflow before designing the agent. Answer these 6 questions — be as specific as possible.
1. What task do you want to automate? (Describe the manual workflow as you do it today, step by step.)
2. How often should it run? (Every hour, daily, every 2 days, weekly, on-demand only?)
3. What data sources does it need? (APIs, websites to scrape, databases, local files, RSS feeds?)
4. What should it produce? (Report files, database entries, API calls, Slack messages, emails, CSV exports?)
5. What decisions does it need to make? (Scoring relevance, filtering noise, writing content, categorizing items, choosing actions?)
6. What's your budget constraint? (Max cost per run in dollars, or monthly ceiling. Include both API/data costs and LLM costs if you know them.)
test cases passed, vs 13 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.