Curioprompt
Add Explore New Best

Prompt Cards

Self-Improving MCP Tool Wrappers: Input Validation
Design MCP wrappers that validate inputs, enforce types, and reject dangerous parameters. Include error taxonomy and audit logging for rejected calls.
Tags: MCP, tool-wrappers, input-validation, errors, audit
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Self-Improving Safety Regression Suite
Create a safety regression suite for tool-using agents: prompt injection tests, permission misuse tests, and data leakage tests. Gate deployments on this suite.
Tags: safety, regression-suite, tooling, leak-tests, permissions
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Self-Improving Code Health Dashboard
Design a dashboard that drives the agent’s priorities: complexity, test coverage, error hotspots, dependency risk, and SLOs. Include alert thresholds and weekly reports.
Tags: dashboard, code-health, prioritization, metrics, SLO
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Self-Improving Reliability: Circuit Breakers and Timeouts
Create an agent that identifies unreliable dependencies and adds circuit breakers, timeouts, and fallbacks. Validate via chaos testing in staging.
Tags: reliability, circuit-breakers, timeouts, fallbacks, staging
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Self-Improving Modularization: Extract Components Safely
Design a modularization plan: identify seams, extract modules, keep interfaces stable, and add integration tests. Require incremental steps and metrics.
Tags: modularization, interfaces, integration-tests, incremental, metrics
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Self-Improving Code Formatting: No Semantic Changes
Create a formatting agent that guarantees no semantic change: parse/print equivalence, tests, and diff classification. Include a strict policy for format-only PRs.
Tags: formatting, semantics, AST, equivalence, policy
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Self-Improving Agent Memory Retrieval: Reduce Wrong Context
Design retrieval that avoids irrelevant context: recency weighting, scope filters, and contradiction detection. Include evals for context precision/recall.
Tags: memory, retrieval, context, precision-recall, evals
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Self-Improving Code Review Prompts for Humans
Create review prompts that guide humans: “check invariants,” “check auth,” “check rollback.” Tune them based on escaped defects and reviewer feedback.
Tags: code-review, checklists, defect-prevention, feedback-loop
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Self-Improving Security Headers and CSP Policies
Design an agent to tune security headers and CSP safely: staged enforcement, report-only mode, breakage monitoring, and rollback. Require security team sign-off.
Tags: CSP, security-headers, staged-rollout, monitoring, signoff
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Self-Improving Logging Cost: Sampling and Cardinality Control
Create a plan to reduce logging costs: sampling, cardinality caps, and aggregation. Require proof that debugging capability is preserved via incident drills.
Tags: logging, cost-control, sampling, cardinality, SRE
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Self-Improving API Client Error Handling
Design an agent that improves error handling: retries, timeouts, and clearer exception types. Require integration tests and telemetry validation post-deploy.
Tags: error-handling, retries, timeouts, integration-tests, telemetry
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Self-Improving UX Copy: Measure Conversion Without Manipulation
Create a workflow to propose UX copy changes, test via A/B, and ensure no dark patterns. Include an ethics checklist and rollback criteria.
Tags: UX-copy, AB-testing, ethics, no-dark-patterns, rollback
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View

Curio AI Brain

Available in Chrome Web Store!