Prompt Cards

Self-Improving Code Comments: Accuracy-Checked
Design a comment improvement agent that updates misleading comments but requires linking to code references and tests to avoid stale documentation.
Tags: comments, docs-accuracy, verification, maintainability
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Change Budget: Limit Automated Changes per Day
Create a policy for change budgets: cap number/size of automated PRs per day, prioritize highest impact, and avoid overwhelming reviewers.
Tags: change-budget, rate-limiting, review-load, prioritization
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Safety Stop Button: Global Kill Switch for Automation
Design a global kill switch that halts all automated edits/deploys across environments. Include manual override process and audit logging.
Tags: kill-switch, safety, automation-control, ops, audit
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Self-Improving On-Call Runbooks
Design an agent that updates runbooks based on incidents and recurring questions. Include change review, versioning, and a “proof of usefulness” metric.
Tags: runbooks, SRE, docs, continuous-improvement, versioning
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Safe Refactor of Logging: Preserve Signal, Reduce Noise
Create a plan for improving logs: structured fields, sampling, PII redaction, and correlation IDs. Require that changes do not reduce incident investigability.
Tags: logging, observability, PII-redaction, correlation-ids, SRE
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
QA Agent: Scenario Tests for Real User Journeys
Design scenario tests that reflect real user journeys and have the self-improver maintain them. Include a process to add scenarios from support tickets.
Tags: QA, scenario-tests, user-journeys, support-tickets
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Safe Self-Improvement for Configurable Policies
Create a blueprint for self-updating policy files (rulesets) with tests, staging, and canary enforcement. Require explicit approval for tightening/loosening security.
Tags: policies, rulesets, testing, staging, security
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Code Ownership Rules: Don’t Edit What You Don’t Own
Design ownership enforcement: CODEOWNERS mapping, required reviewers per module, and automatic routing. The agent must not merge without required approvals.
Tags: codeowners, review, governance, approval, workflow
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Self-Improving Test Selection: Smart Subsets With Guarantees
Create a test selection algorithm that runs only relevant tests for a diff but guarantees critical coverage (safety suite always runs). Include calibration and drift checks.
Tags: test-selection, CI, calibration, safety-suite, drift
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Safe Tool Registry for MCP: Versioned and Audited
Design a tool registry: versioned MCP tools, deprecation, and audit trails. Include a process for approving new tools and revoking compromised ones.
Tags: tool-registry, MCP, versioning, audit, governance
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Self-Improving Router: Pick the Right Agent for the Task
Design a routing agent that selects specialized agents (tests, security, perf, docs) based on task intent and risk. Include confidence thresholds and fallbacks.
Tags: routing, specialists, multi-agent, risk, confidence
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Model Prompt Safety Linter
Create a linter for agent prompts: ban risky instructions, require citations for factual claims, enforce “no tool calls from untrusted text” policies.
Tags: prompt-lint, safety, citations, policy, enforcement
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:

Curio AI Brain

Available in Chrome Web Store!