提示词
提示词工程与模板
mantis-strategy
Senpi-ai
MANTIS v6.0.0 — Slipstream (Cross-Asset Catchup Hunter), senpi_runtime_helpers migration. Plumbing-only flip from openclaw cron + mcporter subprocess + in-Python state to in-process SenpiClient (direct HTTPS for MCP, direct HTTP POST to runtime /signals, long-lived producer_daemon). Thesis preserved verbatim from v5.0: when BTC (or another leader) makes a significant 4h move and a correlated alt hasn't responded yet, Mantis strikes the alt before the catchup completes. Confidence-tier sizing preserved. Leader-reversal veto NOW WORKS (v5.0 was silent no-op).
dire-strategy
Senpi-ai
DIRE v2.0.0 — BRENTOIL XYZ specialist, helpers-native rewrite (2026-05-12). Plumbing-only migration from v1.7.0: producer + v2 runtime (Wolverine v5 / Grizzly v6 / Polar / Kodiak template). NO thesis change. The scanner becomes a producer that emits signals via SenpiClient.push_signal(); the v2 runtime owns execution, DSL exits, and risk guard rails. v1.7.0 thesis preserved verbatim: 4TF alignment hard gate, SM HARD BLOCK via mark/oracle premium proxy, OI velocity scoring, volume spike scoring, price cleanliness check, MIN_SCORE 11, ALL FIVE soft confirmations required (FP-003), FP-001 quiet hours (00-04 UTC unless apex 12+), conviction-scaled sizing (3x / 5x / 7x / 10x by score), DSL preset with v1.7 T0/T1 patch (T0 5%/35% lock, T1 8%/50%). First Kodiak-family port to a non-crypto asset.
dog-strategy
Senpi-ai
DOG v3.0.0 — Contrarian Pup (SM Exhaustion Fader), senpi_runtime_helpers migration. Plumbing-only flip from openclaw-CLI subprocess + mcporter subprocess + Python state to in-process SenpiClient (direct HTTPS for MCP, direct HTTP POST to runtime /signals, long-lived producer_daemon). Thesis preserved verbatim from v2.5: multi-asset (BTC/ETH/SOL/HYPE) contrarian fader, 3.0% exhaustion gate, regime hard-gate, 15m freshness gate, MIN_SCORE 8, conservative leverage (7x base, 10x at score 12+), wide DSL for reversal development.
kestrel-strategy
Senpi-ai
KESTREL v3.0.0 — XYZ Macro Breakout Rider (senpi_runtime_helpers migration). Plumbing-only port from v2.0. NO thesis change. NO scoring change. NO threshold change. Producer ports onto senpi_runtime_helpers (in-process SenpiClient + direct HTTP POST to runtime /signals + producer_daemon long-lived loop). Detects >=1.5% hourly price breakouts on commodities, indices, and high-volume equities 24/7 on Hyperliquid XYZ DEX. LLM regime gate + FEE_OPTIMIZED_LIMIT entries/exits + held-asset dedup + post-close cooldown + chain DB telemetry. Conservative 3-5x leverage.
AI Instruction File Standards Guide
AsiaOstrich
Create and maintain AI instruction files (CLAUDE.md, .cursorrules, etc.) with proper structure. Use when: creating AI instruction files, separating universal vs project-specific rules, configuring AI tools. Keywords: CLAUDE.md, cursorrules, windsurfrules, clinerules, AI instructions, system prompt, 指令檔案, AI 設定.
issue-discover
catlog22
Unified issue discovery and creation. Create issues from GitHub/text, discover issues via multi-perspective analysis, or prompt-driven iterative exploration. Triggers on "issue:new", "issue:discover", "issue:discover-by-prompt", "create issue", "discover issues", "find issues".
workflow-lite-plan
catlog22
Lightweight planning and execution skill - route to lite-plan or lite-execute with prompt enhancement. Triggers on "workflow:lite-plan", "workflow:lite-execute".
skill-generator
catlog22
Meta-skill for creating new Claude Code skills with configurable execution modes. Supports sequential (fixed order) and autonomous (stateless) phase patterns. Use for skill scaffolding, skill creation, or building new workflows. Triggers on "create skill", "new skill", "skill generator".
memory-manage
catlog22
Unified memory management - CLAUDE.md updates and documentation generation with interactive routing. Triggers on "memory manage", "update claude", "update memory", "generate docs", "更新记忆", "生成文档".
ccw-cli-tools
catlog22
CLI tools execution specification (gemini/claude/codex/qwen/opencode) with unified prompt template, mode options, and auto-invoke triggers for code analysis and implementation tasks. Supports configurable CLI endpoints for analysis, write, and review modes.
team-tech-debt
catlog22
Unified team skill for tech debt identification and cleanup. All roles invoke this skill with --role arg for role-specific execution. Triggers on "team tech-debt", "tech debt cleanup", "技术债务".
aws-sdk-java-v2-bedrock
giuseppe-trisciuoglio
Provides Amazon Bedrock patterns using AWS SDK for Java 2.x. Use when working with foundation models (listing, invoking), text generation, image generation, embeddings, streaming responses, or integrating generative AI with Spring Boot applications.
langchain4j-testing-strategies
giuseppe-trisciuoglio
Provides testing strategies for LangChain4j-powered applications. Handles mocking LLM responses, testing retrieval chains, and validating AI workflows. Use when testing AI-powered features reliably.
prompt-engineering
giuseppe-trisciuoglio
This skill should be used when creating, optimizing, or implementing advanced prompt patterns including few-shot learning, chain-of-thought reasoning, prompt optimization workflows, template systems, and system prompt design. It provides comprehensive frameworks for building production-ready prompts with measurable performance improvements.
spring-ai-mcp-server-patterns
giuseppe-trisciuoglio
Provides Model Context Protocol (MCP) server implementation patterns with Spring AI. Use when building MCP servers to extend AI capabilities with custom tools, resources, and prompt templates using Spring's official AI framework.
langchain4j-mcp-server-patterns
giuseppe-trisciuoglio
Provides Model Context Protocol (MCP) server implementation patterns with LangChain4j. Use when building MCP servers to extend AI capabilities with custom tools, resources, and prompt templates.
langchain4j-ai-services-patterns
giuseppe-trisciuoglio
Provides patterns to build declarative AI Services with LangChain4j using interface-based patterns, annotations, memory management, tools integration, and advanced application patterns. Use when implementing type-safe AI-powered features with minimal boilerplate code in Java applications.
claude-md-management
giuseppe-trisciuoglio
Provides comprehensive CLAUDE.md file management capabilities including auditing, quality assessment, and targeted improvements. Use when user asks to check, audit, update, improve, fix, maintain, or validate CLAUDE.md files. Also triggers for "project memory optimization", "CLAUDE.md quality check", "documentation review", or when CLAUDE.md needs to be created from scratch. This skill scans all CLAUDE.md files, evaluates quality against standardized criteria, outputs detailed quality reports with scores and recommendations, then makes targeted updates with user approval.
biomni
jimmc414
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.
typst
lucifer1004
"Typst document creation and package development. Use when: (1) Working with .typ files, (2) User mentions typst, typst.toml, or typst-cli, (3) Creating or using Typst packages, (4) Developing document templates, (5) Converting Markdown/LaTeX to Typst"
sticker-factory
guanyang
Automated factory workflow: Generates grid-based sticker sheets (defaulting to Office Worker style but adaptable) and auto-packages them for WeChat using wechat-sticker-maker.
skill-gen
crafter-station
Auto-generate Claude skills from documentation URLs using Firecrawl agent. Use when user wants to create a skill from docs, API references, or tool homepages. Asks up to 3 clarifying questions before deep extraction. Supports topic focus (e.g., "only auth endpoints") and outputs to local .claude/skills/ by default.
multi-perspective
flonat
"Explore a research question from multiple independent perspectives with diverse epistemic priors. Spawns parallel agents with distinct disciplinary lenses, then synthesises findings. Triggers: 'look at this from different angles', 'get diverse perspectives'."
devils-advocate
flonat
"Challenge research assumptions and identify weaknesses in arguments. Stress-test papers before submission or revision. Triggers: 'find holes in my argument', 'what would a reviewer say'. Not for proofreading — use /proofread. Not for full peer review — use referee2-reviewer agent."