Prompt Cards

Least-Privilege Permissions Matrix for Tools
Create a permissions matrix: tools by scope, environment (dev/stage/prod), rate limits, and allowed parameters. Include an approval process for permission elevation.
Tags: least-privilege, permissions, tooling, security, governance
Author: Assistant
Created at: 2026-01-06 00:00:00
Average Rating:
Total Ratings:
Prompt Injection Defense for MCP Tool Users
Create a defense plan against prompt injection when agents consume untrusted text: content provenance, instruction isolation, and safe tool policies. Provide a red-team test suite.
Tags: prompt-injection, security, MCP, agents, red-team
Author: Assistant
Created at: 2026-01-06 00:00:00
Average Rating:
Total Ratings:
Guardrails Layering: Policy + Technical Controls
Design layered guardrails: policy rules, tool allowlists, output filters, and human escalation. Include regression tests to prevent guardrail drift during iterations.
Tags: guardrails, policy, allowlists, regression-tests, safety
Author: Assistant
Created at: 2026-01-06 00:00:00
Average Rating:
Total Ratings:
Observability: Traces for Prompt→Tool→Output
Design end-to-end tracing: prompt versions, retrieval results, tool calls, retries, and final answers. Include a log schema and query examples for incident investigation.
Tags: observability, tracing, logging, debugging, ops
Author: Assistant
Created at: 2026-01-06 00:00:00
Average Rating:
Total Ratings:
Agent Reliability Scorecard (SLIs/SLOs)
Define SLIs/SLOs for agents: task success, tool failure rates, safety violations, latency, and cost. Provide a dashboard layout and alert thresholds.
Tags: reliability, SLI, SLO, monitoring, cost
Author: Assistant
Created at: 2026-01-06 00:00:00
Average Rating:
Total Ratings:
Long-Horizon Task Decomposition Framework
Create a decomposition framework for multi-hour tasks: milestones, checkpoints, intermediate artifacts, and backtracking rules. Include a “progress ledger” to prevent losing the plot.
Tags: task-decomposition, long-horizon, checkpoints, planning, agents
Author: Assistant
Created at: 2026-01-06 00:00:00
Average Rating:
Total Ratings:
Verifier Model Pattern: Dual-Model Agreement
Design a verifier model workflow: primary proposes, verifier checks constraints and factuality, policy gate decides. Include disagreement handling and confidence thresholds.
Tags: verification, dual-model, policy-gate, confidence, quality
Author: Assistant
Created at: 2026-01-06 00:00:00
Average Rating:
Total Ratings:
Critic Model Pattern: Structured Self-Review Without Loops
Design a critic pattern: structured critique prompts, bounded iterations, and a stop rule. Include how to measure improvement vs added latency/cost.
Tags: critic, self-review, bounded-iteration, latency, quality
Author: Assistant
Created at: 2026-01-06 00:00:00
Average Rating:
Total Ratings:
A2A Negotiation: Contracting Tasks Between Agents
Create an A2A negotiation mechanism: task contracts, acceptance criteria, SLAs, and cost budgets. Include how agents refuse tasks they cannot verify or safely perform.
Tags: A2A, task-contracts, delegation, budgets, reliability
Author: Assistant
Created at: 2026-01-06 00:00:00
Average Rating:
Total Ratings:
MCP Tool Schema Design: Stable, Typed, Auditable
Design MCP tool schemas: typed inputs/outputs, explicit error codes, idempotency rules, and logging fields. Provide examples of good vs bad schema design for agent reliability.
Tags: MCP, schemas, typing, auditability, tool-design
Author: Assistant
Created at: 2026-01-06 00:00:00
Average Rating:
Total Ratings:
Tool Sandbox Model: Containment by Design
Create a sandbox model for tool execution: network isolation, file access boundaries, rate limits, and safe parameter validation. Include a threat model and tests for containment failures.
Tags: sandbox, tools, security, containment, threat-model
Author: Assistant
Created at: 2026-01-06 00:00:00
Average Rating:
Total Ratings:
RAG for Agents: Grounding and Verification Loop
Design a RAG pipeline for agents: retrieval, citation, cross-checking, and contradiction handling. Provide an evaluation plan to measure hallucination reduction and tool-call accuracy.
Tags: RAG, grounding, verification, evals, citations
Author: Assistant
Created at: 2026-01-06 00:00:00
Average Rating:
Total Ratings:

Curio AI Brain

Available in Chrome Web Store!