Prompt Cards

Self-Improving Prompt Library With Versioning
Design a prompt library that the agent can improve safely: semantic versioning, eval gates, canary prompts, and rollback. Include prompt linting rules.
Tags: prompts, versioning, evals, canary, rollback
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Sandboxed Tool Execution for Code Changes
Create a sandbox spec: network isolation, filesystem constraints, resource limits, and safe temp dirs. Include how MCP tool wrappers enforce the sandbox.
Tags: sandbox, containment, resource-limits, security, MCP
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
No-Secrets Guarantee: Redaction and Leak Tests
Design secret-handling: vault integration, redaction in logs, and automated leak scans on diffs, logs, and artifacts. Include fail-closed behavior.
Tags: secrets, redaction, vault, leak-prevention, security
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Self-Edit Safety Case Template
Create a safety case template per capability: hazards, mitigations, tests, monitoring, rollback, and residual risk. Require evidence links and sign-off rules.
Tags: safety-case, hazards, mitigations, monitoring, signoff
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Human-in-the-Loop Review UX
Design a reviewer UX: diff summaries, risk flags, test results, and “approve with conditions.” Include prompts that help humans spot hidden risks quickly.
Tags: human-review, UX, diff-summary, risk-flags, workflow
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Safe Autonomy Levels: Manual→Assisted→Automatic
Define autonomy tiers for the self-improver. Specify which actions are allowed at each tier and what evidence is required to graduate tiers safely.
Tags: autonomy, tiers, governance, safety-evidence, controls
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Regression Detective Agent Using Golden Tests
Design golden tests for key outputs and an agent that compares before/after behavior. Include tolerance rules and how to prevent “golden drift” over time.
Tags: golden-tests, regression, behavioral-testing, drift
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Observability-First Self-Improvement
Create a tracing and logging spec for the self-edit loop: prompts, tool calls, diffs, test results, deploy events, and user impact metrics.
Tags: observability, tracing, logging, diffs, metrics
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Canary Deploy Agent: Progressive Delivery Playbook
Design a progressive delivery system: canary cohorts, SLO monitoring, automatic rollback, and incident annotations. Include safe defaults and stop conditions.
Tags: canary, progressive-delivery, SLO, rollback, ops
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Change Proposal Format: RFC for Every Self-Edit
Define an RFC template the agent must fill: motivation, risks, alternatives, test plan, rollout plan, and monitoring. Require linking evidence and metrics.
Tags: RFC, governance, change-management, testing, monitoring
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Least-Privilege MCP Permissions Matrix
Create a permissions matrix for MCP tools: read-only by default, write tools gated, deploy tools require human approval. Include environment separation (dev/stage/prod).
Tags: MCP, permissions, least-privilege, env-separation, governance
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
Dependency Update Agent With CVE Triage
Build a dependency update agent that monitors CVEs, proposes safe upgrades, runs integration tests, and creates changelog notes. Include rollback and pin rules.
Tags: dependencies, CVE, upgrades, testing, rollback
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:

Curio AI Brain

Available in Chrome Web Store!