Pack 310 · AI · 15 items
AI Agent Design Pack
15 prompts for designing reliable AI agents — real jobs from the week, with the steps, rules and output an expert would ask for.
€6one-time · 15 prompts & skills · ≈ €0.40 each
- Instant download
- Yours to keep
- Works in ChatGPT, Claude, Gemini
What's inside
Made for designing reliable AI agents
15 prompts- PromptAgent Clarifying-Question Gate Before Action
Forces an agent to detect underspecified requests and ask the minimum high-value questions before taking irreversible action.
- PromptAgent Evaluation Rubric And Trace Grader
Creates an objective rubric and grades an agent execution trace on task success, tool use, efficiency, and safety.
- PromptAgent Failure Recovery And Retry Policy Designer
Defines a structured error-handling policy covering retries, backoff, alternative tools, and graceful degradation for agent runtimes.
- PromptAgent Guardrail And Safety Constraint Compiler
Compiles a layered guardrail set covering input validation, action allow-lists, output filtering, and prompt-injection defense.
- PromptAgent Observation Logging And Reflection Loop
Adds a structured reflection step where the agent reviews its own trajectory mid-run to catch drift and re-plan.
- PromptAgent Output Contract And Structured-Response Enforcer
Defines a strict machine-parseable output contract for an agent and a self-validation step that guarantees conformance.
- PromptAgent State Machine And Transition Designer
Models an agent's behavior as an explicit finite state machine with states, transitions, guards, and terminal conditions.
- PromptAgent Tool Definition And Schema Writer
Writes precise tool/function definitions with JSON schemas, descriptions, and usage hints that minimize wrong-tool and bad-argument errors.
- PromptCron-Scheduled Autonomous Monitoring Agent
Specifies a recurring agent that monitors a signal, decides if action is warranted, and reports or escalates on a schedule.
- PromptGoal Decomposition And Task Graph Planner
Turns a high-level goal into a dependency-ordered task graph with parallelizable branches, owners, and verifiable acceptance criteria.
- PromptMulti-Agent Orchestration Blueprint
Plans a coordinated multi-agent team with roles, hand-off contracts, shared memory, and conflict resolution for a complex objective.
- PromptRAG Retrieval Agent Grounding Controller
Directs a retrieval-augmented agent to query, ground answers in sources, cite spans, and refuse when evidence is insufficient.
- PromptReAct Loop Reasoning Trace Designer
Builds a strict ReAct-style Thought/Action/Observation loop with explicit formatting and self-correction rules for tool-using agents.
- PromptSpec-To-Agent Requirements Translator
Converts an informal product spec into a precise agent specification: capabilities, tools, constraints, metrics, and test cases.
- PromptTree-Of-Thoughts Strategy Explorer For Agents
Has an agent branch multiple solution strategies, evaluate each, prune weak branches, and commit to the strongest path.
What you download
Everything comes in one pack (.zip) you keep. Start with 00-GIVE-THIS-TO-YOUR-AI.md: paste it into your AI and it knows which file to use for which job, and what to ask you first.
More for Developers
ai-agent-design/ ├─ 00-GIVE-THIS-TO-YOUR-AI.md ├─ START-HERE.md ├─ TIPS-AND-FOLLOW-UPS.md ├─ AI-CHEAT-SHEET.md └─ prompts/ ├─ 01-agent-clarifying-question-gate-before-action.md ├─ 02-agent-evaluation-rubric-and-trace-grader.md ├─ 03-agent-failure-recovery-and-retry-policy-designer.md ├─ 04-agent-guardrail-and-safety-constraint-compiler.md ├─ 05-agent-observation-logging-and-reflection-loop.md ├─ 06-agent-output-contract-and-structured-response-enforcer.md ├─ 07-agent-state-machine-and-transition-designer.md ├─ 08-agent-tool-definition-and-schema-writer.md ├─ 09-cron-scheduled-autonomous-monitoring-agent.md ├─ 10-goal-decomposition-and-task-graph-planner.md ├─ 11-multi-agent-orchestration-blueprint.md ├─ 12-rag-retrieval-agent-grounding-controller.md ├─ 13-react-loop-reasoning-trace-designer.md ├─ 14-spec-to-agent-requirements-translator.md └─ 15-tree-of-thoughts-strategy-explorer-for-agents.md
A look inside
ROLE: You are an autonomous agent disciplined about resolving ambiguity before acting. CONTEXT: A user has requested [REQUEST]. You have the ability to take real actions via …
Questions
What do I get?
A .zip with 15 prompts for designing reliable AI agents: each prompt as a ready .md file, each skill as a SKILL.md folder, plus 00-GIVE-THIS-TO-YOUR-AI.md (a start file your AI reads first), START-HERE.md, TIPS-AND-FOLLOW-UPS.md (tips and the follow-up questions for every file) and the free AI cheat sheet.
How do I use it?
Open ChatGPT, Claude or Gemini and paste 00-GIVE-THIS-TO-YOUR-AI.md, or attach the folder. It asks a few questions about your work once, then picks the right file for each job and fills in the blanks.
Is it a subscription?
No. €6 once, and the files are yours to keep. Nothing renews.
How do I download it?
Right after checkout, on the confirmation page. Sign in later with the email you paid with and the download button waits for you on this page.
Why this price?
Packs are priced by what they hold: €0.50 a prompt and €1 a skill. This one is €6, about €0.40 an item.