ai-boost/awesome-prompts

---

The prompt engineering world has split into two camps:

• Camp 1 — Prompt templates: collect system prompts, share copy-paste recipes, curate persona prompts. Useful, but limited.
• Camp 2 — Prompt as engineering: compile LM programs (DSPy), test and regress prompts (promptfoo), control generation structurally (Guidance), optimize prompts automatically (TextGrad, GEPA). This is where the long-term value is.

---

Table of Contents

• 📋 Prompts — copy-paste ready
• Coding & Development
• DevOps & SRE
• Data Engineering
• AI & ML
• Product & Strategy
• Project Management
• Healthcare & Clinical
• Industrial & Automotive
• Legal & Compliance
• Knowledge & Documentation
• Writing & Academic
• Learning & Education
• Research & Analysis
• Productivity & Tasks
• Safety & Compliance
• Meta & Prompt Engineering
• Image, Video & Audio Generation
• Creative & Role-play
• Game Development
• Translation
• Legacy (2023 era)
• 🔬 Frameworks — the engineering camp
• Prompt Programming
• Automatic Prompt Optimization
• Tool Use & Reliability
• Eval & Testing
• Red Team & Security
• Eval & Observability
• Low-Code & Workflow Platforms
• 🕵️ System Prompt Leaks — learn from production
• 🧠 Prompt Engineering — techniques & defense
• 🔭 Context Engineering
• 🤖 Agent Ecosystem — MCP, Skills, Harness
• 📖 Official Guides
• 📄 Papers — Foundations, Optimization, Reasoning, RAG, Agents, Multi-Agent, Safety, Self-Improving Agents, Tool Use, Evaluation, Memory, Multimodal
• 🛠 Tools & Libraries

Prompts

All prompts are open — click, copy, use directly.

Coding & Development

| Name | Description | Prompt | |------|-------------|--------| | 🤖 Agentic Coder | Plan-first coding agent — security checklist, test discipline, PR summary format (2025) | prompt | | 📋 Improve Audit Planner | Codebase audit → self-contained plans → cheap-executor dispatch — nine-dimension audit with file:line evidence, machine-checkable verification gates, isolated worktree execution, and backlog reconciliation; based on shadcn/improve (MIT, 8.6k+ stars, June 2026) | prompt | | 🔔 Proactive Coding Agent Architect | Design coding agents that notice what matters before being asked — reactive / scheduled / situation-aware levels, insight policy (monitor → evaluate → decide → ground → adapt), emission gates, developer context model, and feedback-driven learning; based on "Agentic Coding Needs Proactivity, Not Just Autonomy" (arXiv 2605.06717, 2026) and Google's Jules evaluation work (June 2026) | prompt | | 🪿 Goose AI Engineering Agent Operator | Vendor-neutral open-source AI engineering agent operator — MCP-native extension discipline, plan-then-execute loops, multi-provider awareness, least-privilege permission model; based on block/goose → aaif-goose/goose under the Linux Foundation Agentic AI Foundation (Apache-2.0, ~50k stars, June 2026) | prompt | | ♊ Gemini CLI Prompt Architect | Gemini-CLI-optimized prompt engineer — four-element task prompts (goal/context/constraints/done-when), GEMINI.md discipline, built-in tool preferences (search/file/shell/fetch), MCP @-server mentions, multimodal inputs, and anti-patterns; based on google-gemini/gemini-cli (Apache-2.0, 105k+ stars, 2026) | prompt | | 🛠 OpenAI Codex CLI Prompt Architect | Codex-optimized prompt engineer — four-element task prompts (goal/context/constraints/done-when), AGENTS.md discipline, tool preferences, and anti-patterns; based on OpenAI's official Codex Prompting Guide (Feb 2026) | prompt | | 🖥 Cline Prompt Architect | Cline-optimized prompt engineer — four-element task prompts (goal/context/constraints/done-when), Plan/Act mode discipline, .clinerules authoring, MCP server and plugin preferences, multi-agent team scoping, and headless CI/CD conventions; based on cline/cline (Apache-2.0, 64k+ stars, 2026) | prompt | | 🔱 Grok Build Prompt Architect | Grok-Build-optimized prompt engineer — four-element task prompts (goal/context/constraints/done-when), AGENTS.md / CLAUDE.md project-rule discipline, .grok/skills/ authoring, TUI slash commands (/compact, /fork, /rewind), headless grok -p / ACP grok agent stdio scoping, MCP-aware tool preferences, permission rules, and sandbox profiles; based on xai-org/grok-build (Apache-2.0, 18k+ stars, July 2026) | prompt | | 🟠 MiMo Code Prompt Architect | MiMo-Code-optimized prompt engineer — four-element task prompts (goal/context/constraints/done-when), build/plan/compose agent selection, persistent SQLite FTS5 memory (MEMORY.md / checkpoint.md / tasks), /goal judge-verified stop conditions, compose-mode specs-driven workflows, deterministic JS workflows, and .mimocode/skills/ authoring; based on XiaomiMiMo/MiMo-Code (MIT, 12k+ stars, June 2026) | prompt | | 🌙 Kimi Code Prompt Architect | Kimi-Code-CLI-optimized prompt engineer — four-element task prompts (goal/context/constraints/done-when), coder/explore/plan subagent selection, /goal judge-verified stop conditions, AI-native /mcp-config, SKILL.md authoring, lifecycle hooks, video/multimodal input, and KIMI.md/AGENTS.md project-rule discipline; based on MoonshotAI/kimi-code (MIT, 6.2k+ stars, May 2026) | prompt | | 🧩 OpenAI Codex Skill Author | Author installable Codex skills in the official Agent Skills format — SKILL.md with trigger-tuned description, optional agents/openai.yaml for invocation policy and MCP dependencies, scripts-only-when-needed discipline, and progressive-disclosure context design; based on OpenAI's Codex Skills docs and github.com/openai/skills (2026, 22.6k+ stars) | prompt | | 🦘 Roo Code Custom Mode Architect | Design focused, least-privilege Custom Modes for the open-source Roo Code VS Code agent — role definition, tool allowlist (read/edit/browser/command/mcp), file-permission discipline, model-routing hints, and mode-specific safety guardrails; outputs .roomodes JSON and a verification checklist; based on RooVetGit/Roo-Code (Apache-2.0, 50k+ stars, 2026) | prompt | | 🐼 Qwen3-Coder-Next Agentic Coding Architect | Design agentic coding harnesses for Qwen3-Coder-Next — 80B/3B hybrid MoE economics, 256K native context (1M via YaRN), non-thinking output, specialized function-call format, FIM editing, plan-then-execute loops, and verifiable reward signals; based on the Qwen3-Coder-Next Technical Report (arXiv 2603.00729, 2026) | prompt | | 📐 Formal Theorem Proving Architect | Blueprint-driven Lean 4 prover — dependency-graph decomposition, parallel lemma proving, compiler-feedback refinement loops; 99.2% pass@1 on MiniF2F-test, 75.6% on PutnamBench; based on Goedel-Architect (arXiv 2606.06468, June 2026) | prompt | | 🧪 Prototype Architect | Throwaway-prototype skill — logic prototypes (interactive TUI for state machines) and UI prototypes (radically different variants on a single route with floating switcher); based on mattpocock/skills (Jan 2026, 117k+ stars) | prompt | | 🔍 Code Reviewer | Security-focused code reviewer — OWASP Top 10, severity grading, fix examples (2026) | prompt | | 🕸 Multi-Agent Orchestrator | Central dispatch agent — task decomposition, parallel delegation, state tracking, error recovery (2026) | prompt | | 🎛 Teams-First Multi-Agent Orchestrator | Teams-first multi-agent orchestration layer for Claude Code — 19 specialized agents with model routing (haiku/sonnet/opus), delegation rules, skill triggers, team pipeline (plan→prd→exec→verify→fix), structured commit trailers, and project memory; based on Yeachan-Heo/oh-my-claudecode (Feb 2026, 35k+ stars) | prompt | | 🧱 Agent Harness Designer | System prompt for designing reliable agent runtimes — tool minimization, approval gates, memory/compaction, rollback, observability, evals; derived from OpenAI/Anthropic harness guidance (2026) | prompt | | 🔐 Autonomous Permission Classifier Architect | Design model-based permission classifiers for coding agents — prompt-injection probe, reasoning-blind transcript classifier with two-stage filter, block/allow templates, deny-and-continue semantics, and recursive subagent handoff gates; based on Anthropic's "How we built Claude Code auto mode" (March 2026) | prompt | | 🔁 Loop Engineering Architect | Design external loop specifications that let coding agents run without step-by-step prompting — trigger, goal, five-level verification ladder, architecture, stopping rule, durable memory; based on "Stop Hand-Holding Your Coding Agent" (arXiv 2607.00038, July 2026) | prompt | | 🔄 Claude Code Loops Operator | Turn/goal/time/proactive loop operator for Claude Code — choose the right primitive (/goal · /loop · /schedule), encode verification skills, manage tokens, and design routines that run while you sleep; based on Anthropic's official "Loop engineering: Getting started with loops" guide (July 2026) | prompt | | 🛞 Loop Engineering Patterns Operator | Practical loop pattern operator for recurring coding-agent tasks — select from 7 production patterns (PR Babysitter, Daily Triage, CI Sweeper, etc.), scaffold with loop-init, score Loop Ready with loop-audit, and operate the five building blocks + memory across Grok, Claude Code, Codex, and Opencode; based on cobusgreyling/loop-engineering (MIT, 9.7k+ stars, June 2026) | prompt | | 🧭 Fable Method Agent Loop Architect | Think / act / prove agent loop — classify the ask, define done with named verification, gather primary-source evidence in parallel, commit to one recommendation, act surgically, verify by observation, report outcome-first; includes domain adapters, triviality/fit/intent/recall/authorization gates, twin-check, and artifact gate; based on Sahir619/fable-method (MIT, 1.9k+ stars, July 2026) | prompt | | 📜 Auditable Enterprise LLM Agent Harness Architect | Reconstruct prompt-heavy enterprise LLM prototypes into traceable, auditable, code-owned systems — source-to-claim pipeline, code-owned contracts, seven validation dimensions, replaceable composition boundary, insight-first answer structure; based on "From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents" (arXiv 2607.08028, July 2026) | prompt | | ⚡ Agent Harness Performance Engineer | Cross-harness agent harness optimization — token economics, memory persistence hooks, continuous learning via instinct extraction, verification loops, parallelization, security scanning; based on affaan-m/everything-claude-code (Jan 2026, 182k+ stars) | prompt | | 💰 Agent Cost Observability Architect | End-to-end cost observability and budget-governance system for AI coding agents — multi-provider token telemetry, real-time TUI/menubar dashboards, per-project budget envelopes, cost-anomaly detection, optimization recommendation loops, forecast-and-actual tracking; based on getagentseal/codeburn (Apr 2026, 7.2k+ stars) | prompt | | 📁 Agent Virtual Filesystem Architect | Unified virtual-filesystem layer for AI agents — mount topology, resource adapters, bash-tool surface, two-layer cache, snapshots/cloning, framework integration; based on strukto-ai/mirage (May 2026, 2149 stars) | prompt | | 🖥 AOS CE Agent Operating System Architect | Architect for Unicity AOS Community Edition — capsules, Astrid Runtime, Forge workbench, meta-harness loops, MCP bridge, and least-privilege capability design; based on unicity-aos/aos-ce (Rust, 6.5k+ stars, July 2026) | prompt | | 🏢 QM Multiplayer Agent Harness Architect | Design and deploy Y Combinator's QM — a multiplayer agent harness for work with personal + shared scopes, Slack + web surfaces, admin governance, per-scope sandbox, multi-harness core (Pi/OpenCode/Codex/Claude Code), shared skills, and crons/watches; based on yc-software/qm (MIT, ~5k stars, July 2026) | prompt | | 🧹 Agent State Hygiene Architect | Local-agent state maintenance architect — inspect-before-mutate discipline, report-first workflow, archive-don't-delete policy, handoff-doc continuity, session metadata bloat detection, stale worktree pruning, log rotation, and config hygiene; based on vibeforge1111/keep-codex-fast (May 2026, 1.2k+ stars) | prompt | | ⚙️ Autonomous Software Factory Orchestrator | Chat-driven autonomous development orchestrator — human sets direction via lightweight messages, self-coordinating claws execute planning/build/test/review/push loops; notification routing (git/tmux/GitHub/lifecycle) kept strictly outside agent context windows; based on ultraworkers/claw-code (Mar 2026, 191k+ stars) | prompt | | 🖥 Computer Use Operator | System prompt for browser/desktop agents — observe → act → verify loops, least privilege, confirmation gates, phishing/prompt-injection resistance; derived from OpenAI's 2026 computer-use guidance | prompt | | 🌐 Browser Harness Designer | Self-healing browser harness architect — direct CDP websocket, thin editable runtime, agent-generated helper layer, domain/interaction skill separation; based on browser-use/browser-harness (Apr 2026, 12k+ stars) | prompt | | 🎭 Webwright Browser Agent | Microsoft SWE-style browser agent — code-as-action Playwright automation, critical-point plan, screenshot evidence, self-verification loop, one-shot vs parameterized CLI modes; based on microsoft/Webwright (Apr 2026, 4.6k+ stars) | prompt | | 🌐 Vercel Agent Browser Operator | Native Rust browser automation operator for AI agents — snapshot-first navigation with @eN refs, semantic locators, batch execution, MCP server mode, React introspection, Web Vitals, and axe-core a11y audits; based on vercel-labs/agent-browser (Apache-2.0, 39k+ stars, Jan 2026) | prompt | | 🖼 UI-TARS Desktop Agent Operator | Vision-language model driven GUI agent operator — screenshot-first observation, structured mouse/keyboard actions, GUI/browser/remote operator modes, MCP tool mounting, event-stream context engineering; based on bytedance/UI-TARS-desktop (2026, 36.6k+ stars, Apache-2.0) | prompt | | 📱 Phone Harness Operator | Real-iPhone agent operator via macOS iPhone Mirroring — screenshot + Vision OCR for eyes, HID-level CGEvents for hands; least-privilege phone control, observe-act-verify loops, iOS gesture quirks, high-impact confirmation gates; based on ShawnPana/phone-harness (MIT, 1.3k+ stars, Aug 2026) | prompt | | 🖥 Agent-Native CLI Designer | Agent-native CLI architect for GUI software — 7-phase SOP to wrap any GUI app into a stateful, agent-usable CLI with REPL + subcommand modes, backend integration, test planning, and SKILL.md generation; based on HKUDS/CLI-Anything (Mar 2026, 34k+ stars) | prompt | | 🧩 Agent Skill Designer | Prompt for packaging reusable agent skills — narrow scope, tool-aware workflow, safety rules, verification checklist, SKILL.md draft output; derived from Anthropic/Google skill guidance (2026) | prompt | | 🧠 Managed Agent Architect | Prompt for designing long-running managed-agent systems — brain/hands split, worker contracts, checkpoints, permission scoping, recovery; derived from Anthropic/OpenAI 2026 harness guidance | prompt | | 🚀 Launch Your Agent Architect | Founder copilot for launching Claude Managed Agents (CMA) — interview a founder, scope the smallest v0, launch in their own Anthropic account, grade against a binary rubric, iterate, and schedule deployments; based on anthropics/launch-your-agent (Apache-2.0, June 2026) | prompt | | 🔌 Agent Protocol Advisor | Prompt for choosing MCP vs A2A vs simpler transports — protocol mapping, trust boundaries, ownership, retries, migration plan; derived from Google's 2026 protocol guide | prompt | | 🔌 A2A Agent Protocol Architect | Architect A2A-compliant agent-to-agent systems — AgentCard discovery, Task lifecycle, Message/Part/Artifact contracts, JSON-RPC/gRPC/HTTP bindings, async streaming, OAuth/mTLS security, idempotency, versioning; based on the A2A open protocol (Google → Linux Foundation, v1.0 2026, 22k+ stars, Apache-2.0) | prompt | | 🌐 Omnigent Meta-Harness Architect | Vendor-agnostic control plane for orchestrating multiple coding-agent harnesses — adapter contracts, policy envelopes, sandbox profiles, portable context bundles, and cross-harness verification; based on omnigent-ai/omnigent (Apache-2.0, 7.4k+ stars, June 2026) | prompt | | 🌐 Vercel Eve Agent Architect | Filesystem-first agent architect for Vercel Eve — design durable backend agents using agent/instructions.md, agent/tools/, agent/skills/, agent/channels/, agent/schedules/, agent/connections/, and agent/subagents/ conventions; path-named capabilities, typed Zod tools, load-on-demand skills, human-in-the-loop approvals, and eve eval harness; based on vercel/eve (Apache-2.0, 4.3k+ stars, June 2026) | prompt | | 🧮 Agentic Code Reasoner | Prompt for evidence-backed code reasoning — semi-formal reasoning chain, competing hypotheses, verification-first conclusions for complex code understanding (2026) | prompt | | 🧠 ADHD Parallel Ideation Skill | Parallel divergent ideation for coding agents — spawns N isolated branches under cognitive frames (hardware/regulator/biology/speedrunner/etc), scores/clusters/prunes traps, deepens survivors; mechanical generator/critic split with zero shared context during divergence; for architecture, naming, API design, and fuzz