提示词库

给编程 Agent 和 AI 工作流用的系统提示词。

awesome-prompts 里维护的角色提示词和系统提示词,按领域分组。复制到 Claude Code、Codex 或任意对话模型里就能用。

353 条

Beauty D&D 中文

Text adventure romance simulator with DALL-E image generation (Chinese)

2D Game Asset Forge EN

Production-ready 2D sprite sheets, animated GIFs, tilemaps, parallax layers, and game maps: asset planning, grid layout, frame containment, style matching, layer separation, engine-ready export; based on 0x0funky/agent-sprite-forge (Apr 2026, 2.2k+ stars)

5W3H Intent Architect EN

Structured intent expansion for any request: Who/What/When/Where/Why/How/How much/How long; reduces cross-model variance and dual-inflation bias; based on "Does Structured Intent Representation Generalize?" (arXiv 2603.25379, 2026)

A2A Agent Protocol Architect EN

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)

A2UI Agent-to-User Interface Architect EN

Prompt for designing A2UI-compliant declarative agent-generated interfaces: component catalog allowlists, surface updates, data-model bindings, action intents, sandboxed rendering, no executable code; based on Google's A2UI open protocol (github.com/google/A2UI, 2026, 15.4k+ stars, Apache-2.0)

Abstract Chain-of-Thought Architect EN

Design latent reasoning systems with discrete abstract tokens: vocabulary design, bottleneck warm-up, self-distillation under constrained decoding, RL length penalty, early-exit probes, trajectory audit; up to 11.6× fewer reasoning tokens vs. verbal CoT; based on "Thinking Without Words" (arXiv 2604.22709, April 2026; IBM Research AI)

Academic Paper Architect EN

Full-spectrum manuscript orchestrator: 12-agent pipeline (literature strategy → structure → argument → draft → citation → bilingual abstract → simulated peer review → formatting); style calibration, writing quality checks, IRON RULE checkpoints, 8 invocation modes; based on Imbad0202/academic-research-skills (May 2026, 18k+ stars)

Academic Peer Reviewer EN

Comprehensive manuscript review: contribution assessment, methodology critique, reproducibility, ethics, constructive feedback, recommendation with confidence (2026)

Accessibility Auditor EN

WCAG 2.2 AA auditor: screen reader testing, keyboard navigation, ARIA patterns, assistive tech, CI/CD integration, legal compliance (ADA/EAA/508) (2026)

Adaptive Learning Designer EN

AI-driven personalized education: knowledge tracing, spaced repetition, intelligent tutoring, learning analytics, engagement design, ethical safeguards (2026)

ADHD Parallel Ideation Skill EN

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 fuzzy-debugging decisions; based on UditAkhourii/adhd (May 2026, 717+ stars, The New Stack featured, preprint)

ADK SkillToolset Designer EN

Prompt for ADK-style progressive-disclosure skills: L1 metadata, on-demand skill payloads, load/unload triggers, versioning, skill-factory tradeoffs (2026)

AG-UI Frontend Architect EN

Prompt for designing AG-UI-compliant agent-to-user frontend integrations: event sourcing, lifecycle/tool/state events, SSE/WebSocket transport, human-in-the-loop interrupts, generative UI payloads; based on the AG-UI open protocol (ag-ui-protocol/ag-ui, 2026, 14k+ stars)

Agent Context Efficiency Engineer EN

Context-window optimization architect for AI coding agents: Think-in-Code discipline (script execution vs bulk file reads), sandboxed tool-output routing, session continuity via indexed event stores, context telemetry with savings targets, and cross-platform discipline (3 OS × 15 adapters); based on mksglu/context-mode (Feb 2026, 15.4k+ stars, Hacker News #1, used by Microsoft/Google/Meta/Amazon/NVIDIA)

Agent Cooperation Designer EN

Prompt for designing cooperative multi-agent systems: shared objective, local roles, disagreement rules, anti-herding controls, evaluation signals (2026)

Agent Cost Observability Architect EN

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)

Agent Data Injection Attack Auditor EN

Red-team auditor for agent data injection (ADI): malicious data disguised as trusted metadata, tool outputs, or agent-context structures; structural isolation, schema validation, provenance labeling, and out-of-band verification; based on "Agent Data Injection Attacks are Realistic Threats to AI Agents" (arXiv 2607.05120, July 2026)

Agent Environment Engineering Architect EN

Design the runtime, artifacts, constraints, and interfaces that let off-the-shelf CLI agents do metric-driven autonomous scientific discovery: permissions/artifact/budget/human-in-the-loop engineering, hidden-evaluator sandbox, parallel propose-implement loops, cost-capped exploration; based on EurekAgent (arXiv 2606.13662, June 2026; THU-Team-Eureka/EurekAgent)

Agent Eval Designer EN

Evaluation prompt for real-world agents: task suites, noise audits, reproducibility, intervention/safety metrics, failure taxonomy; derived from Anthropic's 2026 eval guidance

Agent Governance Orchestrator EN

Prompt for defining ownership, delegation, authority, approvals, and audit trails across multiple agents: governance-first orchestration design (2026)

Agent Harness Designer EN

System prompt for designing reliable agent runtimes: tool minimization, approval gates, memory/compaction, rollback, observability, evals; derived from OpenAI/Anthropic harness guidance (2026)

Agent Harness Performance Engineer EN

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)

Agent Memory Architect EN

Agent memory systems architect: STM/LTM design, extraction/storage/retrieval modules, hierarchical graph memory, context compression, reasoning-aware recall; based on 2026 memory-architecture research (2026)

Agent Permission Auto-Mode Architect EN

Two-layer permission classifier for agentic tools: fast heuristic filter + model-based risk scorer, read-vs-write auto-approval policies, blast-radius gates, user-override protocols, and audit-driven threshold tuning; based on Anthropic's Claude Code Auto Mode (Mar 2026)

Agent Protocol Advisor EN

Prompt for choosing MCP vs A2A vs simpler transports: protocol mapping, trust boundaries, ownership, retries, migration plan; derived from Google's 2026 protocol guide

Agent Red Team Architect EN

End-to-end adversarial test architect for AI agent systems: kill-chain design, indirect injection, multi-turn escalation, cross-channel attacks, ecosystem propagation, automated red-team pipelines; based on Black Hat 2026, USENIX Security 2026, and OpenAI 2026 safety research (2026)

Agent Reliability Engineer EN

Reliability-engineering prompt that separates reliability from capability: four-dimension scorecard (consistency, robustness, predictability, safety/fault-tolerance), 3D reliability surface R(k, ε, λ) with explicit operating envelopes, chaos-engineering plan with fault injection, harness-hardening checklist (environment-coupled loops, replan triggers, snapshots, typed error contracts, confirmation gates, budgets), pass@1-overestimates-by-20-40% guardrail, unsafe-success detection; based on "Towards a Science of AI Agent Reliability" (arXiv 2602.16666, 2026) and "ReliabilityBench: Evaluating LLM Agent Reliability Under Production-Like Stress" (arXiv 2601.06112, 2026)

Agent Safety Testing at Scale Architect EN

Scalable automated safety-testing architect for LLM agents: literature-driven risk taxonomy, combinatorial executable safety-case generation, deterministic verifier predicates, adaptive sandbox execution with control agent and evidence-grounded verifiers; based on "Safety Testing LLM Agents at Scale" / Vera (arXiv 2607.01793, July 2026)

Agent Skill Compositional Risk Auditor EN

Compositional security audit for installed agent skill sets: capability extraction, pair-level forbidden unions, transitive multi-hop chains, host-model disposition analysis, install-time set-level gates; based on "When Safe Skills Collide" (arXiv 2606.00448, 2026)

Agent Skill Designer EN

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)

Agent Skill Effectiveness Auditor EN

Paired audit for whether an injected agent skill actually helps on a real-world SE task: baseline-first measurement, context-interference detection (surface anchoring, hallucination, concept bleed), token-overhead accounting, and a keep/drop decision gate; based on SWE-Skills-Bench (arXiv 2603.15401, 2026)

Agent Skill Optimizer Architect EN

Text-space skill trainer that treats natural-language skill documents as neural-network parameters: rollout (forward pass), reflect (backward pass), aggregate, select (gradient clipping), update, and gate (validation) loops; learning-rate schedules, slow-update epoch boundaries against catastrophic forgetting, meta-skill cross-epoch memory, and convergent diagnostics on frozen LLMs; produces deployable best_skill.md artifacts; based on microsoft/SkillOpt (May 2026, arXiv 2605.23904)

Agent Skill Supply-Chain Security Auditor EN

Supply-chain security audit for agent skill ecosystems: DDIPE poisoning detection, MCP schema hardening, cross-skill propagation analysis, provenance verification, least-privilege harness review; based on 2026 agent skill supply-chain attack research (2026)

Agent State Hygiene Architect EN

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)

Agent Style Enforcer EN

Literature-backed technical-prose writing ruleset: 21 rules (12 canonical from Strunk & White/Orwell/Pinker/Gopen & Swan + 9 field-observed from LLM output 2022, 2026) with severity tiers, BAD/GOOD examples, and escape hatch; drop-in for any AI agent producing `.md`, `.tex`, `.rst`, or source-code comments; based on yzhao062/agent-style (2026)

Agent Tool Engineer EN

Prompt for designing, evaluating, and iteratively improving agent tools: tool selection/omission (constraint collapse), namespacing, context-rich returns, token-efficient responses, description prompt-engineering, agent-driven optimization loops; based on Anthropic's 2026 "Writing effective tools for agents" guidance

Agent Trajectory Triage Specialist EN

Post-deployment trajectory sampling and triage prompt: three-dimensional signal taxonomy (interaction / execution / environment), cheap-rules-first extractors, diversified ranking, reviewer-feedback loop, explicit privacy-redaction step; designed to lift informative traces over random sampling without ground-truth labels; based on "Signals: Trajectory Sampling and Triage for Agentic Interactions" (arXiv 2604.00356, April 2026, 6.2k HF likes)

Agent Virtual Filesystem Architect EN

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)

Agent World Model Architect EN

Predictive environment simulators for agent imagination: state-space design, dynamics modeling, counterfactual rollouts, plan-then-execute integration, world-model-specific safety (hallucinated futures, goal misgeneralization, deceptive alignment); spans physics, language, and hybrid world models; based on VLA-World, OccuBench, and 2026 world-model safety research (2026)

Agent-First Language Architect EN

Programming-language designer that treats agents as primary users: small regular surface, deep standard library, deterministic structured tooling, and explicit syntax; based on vercel-labs/zerolang (May 2026, 3.6k+ stars)

Agent-Native CLI Designer EN

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)

Agent-Native Memory System Architect EN

Data-management-first memory system architect: designs representation/storage, extraction, retrieval/routing, and maintenance as measurable modules; workload-aware benchmarking, localized-vs-global maintenance trade-offs, update-correctness discipline; based on "Are We Ready For An Agent-Native Memory System?" (arXiv 2606.24775, June 2026; OpenDataBox/MemoryData benchmark suite)

Agent-Powered Vulnerability Scanner Architect EN

Hybrid security scanner architect: regex matchers for fast wide coverage + AI agents for deep analysis, project-specific INFO.md context engineering, evidence-driven custom matchers, trust-boundary triage, and cost-governed revalidation; designed for monorepos and large codebases; based on vercel-labs/deepsec (Apr 2026, 2.7k+ stars)

AgentAtlas Trajectory Auditor EN

Beyond-outcome agent evaluation: separates outcome success, control-decision quality, and trajectory quality using a six-state taxonomy (Act / Ask / Refuse / Stop / Confirm / Recover); identifies primary error source and downstream impact; tests for label-menu dependence; based on "AgentAtlas: Beyond Outcome Leaderboards for LLM Agents" (arXiv 2605.20530, May 2026)

AgentAtlas Trajectory Eval Architect EN

Diagnostic agent evaluator: scores trajectories by control-decision taxonomy (Act / Ask / Refuse / Stop / Confirm / Recover), trajectory-failure taxonomy, six-axis coverage audit, and taxonomy-aware vs. taxonomy-blind gap; separates real capability from prompt-supervision artifacts; based on "AgentAtlas: Beyond Outcome Leaderboards for LLM Agents" (arXiv 2605.20530, May 2026)

Agentic CAD & Hardware Designer EN

Parametric CAD and hardware-design engineer: STEP-first build123d/Python parts and assemblies, natural-language spec → CAD brief, enclosures/fixtures/joints/mating, URDF/SDF/SRDF robotics descriptions, source-controlled geometry with validated exports; based on earthtojake/text-to-cad (Apr 2026, 2952 stars)

Agentic Code Reasoner EN

Prompt for evidence-backed code reasoning: semi-formal reasoning chain, competing hypotheses, verification-first conclusions for complex code understanding (2026)

Agentic Coder EN

Plan-first coding agent: security checklist, test discipline, PR summary format (2025)

Agentic Company Orchestrator EN

Zero-human-company multi-agent orchestration architect: org-chart design, heartbeat-driven execution, goal-aligned delegation, budget governance with hard stops, ticket-based task tracking, board approval gates, multi-company isolation, and portable company templates; based on paperclipai/paperclip (Mar 2026, 64k+ stars)

Agentic Context Engineering Architect EN

Evolving-context playbook architect for self-improving agents: Generator/Reflector/Curator roles, itemized structured bullets with outcome counters, incremental delta updates (no full rewrites), grow-and-refine with semantic de-duplication, anti-collapse and anti-brevity guardrails; based on "Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models" (arXiv 2510.04618, v3 March 2026; +10.6% agent benchmarks, +8.6% finance)

Agentic Deontic Reasoning Architect EN

Rule-following agent architect: stores statutes/policies as retrievable harness files, binds case facts to rule elements on demand, handles cross-references and exceptions, verifies conclusions before submission; based on DAR (arXiv 2606.05009, June 2026)

Agentic HTML Publisher EN

Local-first, ship-ready HTML publisher: turns Markdown/CSV/JSON/notes into single-file HTML via 75 skill templates across 9 surfaces (magazine, deck, poster, social cards, prototype, data report, Hyperframes); juice-inlined CSS for WeChat, 2× PNG for X, standalone .html download; anti-AI-slop design discipline with locked palettes, CJK font stacks, and 8 px baseline grid; based on nexu-io/html-anything (May 2026, 4.5k+ stars)

agentmemory Persistent Memory Architect EN

Persistent-memory architect for coding agents: confidence-scored memory taxonomy, hybrid retrieval, temporal knowledge graph, session compression, MCP tool surface, and platform integration across Claude Code / Codex / Cursor / Gemini CLI / Hermes / OpenClaw / pi / OpenCode; based on rohitg00/agentmemory (Feb 2026, 27k+ stars)

Agents Best Practices EN

Provider-neutral agent harness architect: MVP blueprint, loop design, tool/permission contracts, context/memory/compaction, planning/goals, skills/MCP connectors, prompt caching, observability/evals, safety guardrails; based on DenisSergeevitch/agents-best-practices (May 2026, 654 stars)

AGENTS.md Author EN

Authoring prompt for the AGENTS.md open standard: concise repo-root file telling cross-vendor coding agents (Codex CLI, Cursor, Aider, Gemini CLI, Jules, Factory, RooCode; Claude Code via CLAUDE.md) how to set up, build, test, and commit safely; recommended section order, extract-don't-invent commands, monorepo nested-file resolution, ≤200-line discipline, anti-patterns, provenance + questions output; based on the official agents.md spec, OpenAI's Aug 2025 introduction, and Agentic AI Foundation / Linux Foundation 2026 stewardship

Agile Transformation Lead EN

Enterprise agile transformation: operating model design, framework selection, product management integration, flow optimization, change management, technical practices (2026)

AI Co-Mathematician EN

Interactive research partner for open-ended mathematical discovery: ideation, literature bridging, computational exploration, conjecture formation, theorem proving, theory building; manages uncertainty, tracks dead ends, refines intent across turns; scored 48% on FrontierMath Tier 4; based on Google DeepMind's AI Co-Mathematician (arXiv 2605.06651, May 2026)

AI Ethics Reviewer EN

Algorithmic ethics audit: fairness & bias, transparency, privacy, safety, accountability, societal impact, cross-cultural considerations, mitigation roadmap (2026)

AI-Native Product Architect EN

AI-first product design: agentic workflows, generative UI, human-in-the-loop at the right level, self-improving loops, trust & transparency architecture (2026)

按分类浏览

Coding & Development 103 · Meta & Prompt Engineering 71 · Safety & Compliance 27 · AI & ML 24 · Product & Strategy 22 · Research & Analysis 20 · Writing & Academic 15 · Knowledge & Documentation 9 · Productivity & Tasks 9 · Legal & Compliance 8 · DevOps & SRE 7 · Healthcare & Clinical 6 · Industrial & Automotive 6 · Game Development 6 · Learning & Education 5 · Data Engineering 4 · Project Management 4 · Translation 4 · Creative & Role-play 3

系统提示词、CLAUDE.md 和 AGENTS.md

在 ChatGPT 或 API 调用里,系统提示词放在 system 字段。编程 agent 则从文件里读长期指令:Codex 读 AGENTS.md,Claude Code 读 CLAUDE.md,仓库里只有 AGENTS.md 时也会读它。把这页的提示词贴进对应文件,项目里的每次会话都会用上。 CLAUDE.md 和 AGENTS.md 怎么选 →