Curioprompt
Add Explore New Best

Prompt Cards

Self-Improving Code Style Guide Generator
Create an agent that infers code style from the repo (naming, patterns, architecture) and generates a style guide. Use it to validate future edits.
Tags: style-guide, consistency, linting, patterns, repo
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Supply-Chain Safety: Lockfile and Integrity Enforcement
Design enforcement: lockfile required, checksum verification, artifact signing, and dependency allowlists/denylists. Include alerting on suspicious updates.
Tags: supply-chain, lockfile, integrity, signing, alerts
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Security Review Agent: Threat Model Every Change
Create a threat-modeling step: identify assets, attackers, and abuse cases for each PR. Include automated checks and a human escalation threshold.
Tags: security, threat-model, abuse-cases, PR-review, escalation
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Doc-to-Code Alignment: Verify Against Official Sources
Design a process where the agent checks a proposed change against official documentation versions, release notes, and migration guides. Require citations for claims.
Tags: documentation, verification, migrations, citations, compatibility
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Safe Web Crawling for Docs: Respectful and Compliant
Create a documentation crawler for self-improvement research that respects robots.txt, rate limits, and TOS. Include caching, dedupe, and citation storage.
Tags: crawler, docs, robots.txt, compliance, citations
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
SLO-Driven Improvement: Optimize What Users Feel
Design an improvement loop keyed to SLOs: latency, error rates, and quality metrics. Require that proposed changes specify which SLO they target and how measured.
Tags: SLO, metrics, latency, errors, quality, ops
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Self-Improvement Backlog: Triage and Prioritize
Create a backlog system: bugs, tech debt, performance, and security items. Include scoring by user impact, risk, and effort, and automatic issue creation via MCP.
Tags: backlog, triage, prioritization, issue-tracking, MCP
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Patch Minimization: Small Diffs, Big Wins
Design a patch strategy that prefers minimal diffs: isolate behavior changes, avoid formatting churn, and include clear intent comments. Add a “diff size budget.”
Tags: minimal-diff, refactor-safety, reviewability, quality
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Architecture Guardrails: No Unapproved Major Refactors
Define guardrails that block large architectural changes unless an explicit human-approved RFC exists. Include heuristics to detect “too big” diffs.
Tags: architecture, guardrails, RFC, change-size, governance
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Scoped Repo Understanding Agent: Map the System
Create an agent that builds a “system map”: modules, ownership, dependencies, and critical paths. Use it to constrain edits to low-risk areas first.
Tags: codebase-map, dependencies, ownership, risk-reduction
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Multi-Agent Consensus on Risky Changes
Design a consensus mechanism for risky changes: verifier override, structured voting, and escalation to human. Include disagreement logs and rationale storage.
Tags: consensus, multi-agent, risk, escalation, logging
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View
Evaluation Harness: Deterministic Replays
Build an eval harness for self-edits: deterministic tool mocks, seeded randomness, replayable runs, and stored artifacts for auditing decisions.
Tags: evals, reproducibility, mocks, replay, audit
Author: Assistant
Created at: 2026-02-20 00:00:00
Average Rating:
Total Ratings:
View

Curio AI Brain

Available in Chrome Web Store!