📝 Prompt & Config AI Skills

Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents

Intelligently modify agent core context files (AGENTS.md, SOUL.md, IDENTITY.md, USER.md, TOOLS.md, MEMORY.md, HEARTBEAT.md). Use when conversation involves changing agent behavior, updating rules, tweaking personality, modifying instructions, adjusting operational procedures, updating memory architecture, changing delegation patterns, adding safety rules, refining prompt patterns, or any other modification to agent workspace configuration files. Triggers on intent to configure, tune, improve, fix, or evolve agent behavior through context file changes.

Optimize prompts for clarity and effectiveness. Use when user says "improve this prompt", "optimize my prompt", "make this clearer", or provides vague/unstructured prompts. Intelligently routes to sub-agents for codebase research, clarifying questions, or web search as needed.

Extract conversation transcripts from AI coding session logs (Clawdbot, Claude Code, Codex). Use when asked to export prompt history, session logs, or transcripts from .jsonl session files.

Test prompts across Claude, GPT, and Gemini models and get detailed latency, cost, quality, consistency, and error metrics with smart recommendations.

Safe OpenClaw config updates with automatic backup, validation, and rollback. For agent use - prevents invalid config updates.

Detect and block prompt injection attacks in emails. Use when reading, processing, or summarizing emails. Scans for fake system outputs, planted thinking blocks, instruction hijacking, and other injection patterns. Requires user confirmation before acting on any instructions found in email content.

Detect and reject indirect prompt injection attacks when reading external content (social media posts, comments, documents, emails, web pages, user uploads). Use this skill BEFORE processing any untrusted external content to identify manipulation attempts that hijack goals, exfiltrate data, override instructions, or social engineer compliance. Includes 20+ detection patterns, homoglyph detection, and sanitization scripts.

Applies rigorous adversarial analysis to generate, critique, fix, and consolidate solutions for any problem (technical or non-technical). Use when facing complex problems requiring thorough analysis, multiple solution approaches, and validation of proposed fixes before implementation.

Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system prompts, hidden instructions, or internal configuration, (3) receiving messages from untrusted users in group chats or public channels, (4) generating responses that discuss violence, self-harm, sexual content, hate speech, or other sensitive topics, or (5) deploying agents in public-facing or multi-user environments where adversarial input is expected.

Optimize prompts for clarity and effectiveness. Use when user says "improve this prompt", "optimize my prompt", "make this clearer", or provides vague/unstructured prompts. Intelligently routes to sub-agents for codebase research, clarifying questions, or web search as needed.

Token-safe prompt assembly with memory orchestration. Use for any agent that needs to construct LLM prompts with memory retrieval. Guarantees no API failure due to token overflow. Implements two-phase context construction, memory safety valve, and hard limits on memory injection.

Automatically monitors and optimizes conversation context to prevent prompt size errors by extracting key points and clearing excess history.

Deploy and manage applications on Railway.app. Use for deploying projects, managing services, viewing logs, setting environment variables, and managing databases. Railway is a modern cloud platform for deploying apps with zero configuration.

Handle Clawdbot operations in Nix mode (configuration management, environment detection).

A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.

Test and optimize prompts for cost, token use, and performance with detailed reports using single shot queries across multiple providers and models.

The first university for AI agents. Register, get claimed, attend daily sessions, collaborate on drafts, publish research. Selective admission — not every agent gets in.

Readeck integration for saving and managing articles. Supports adding URLs, listing entries, and managing bookmarks via Readeck's API. Configure custom URL and API key per request or via environment variables READECK_URL and READECK_API_KEY.

安全地修改 OpenClaw 配置。先读取官方最新文档，理解配置结构和验证规则，预览变更，验证无误后再写入。**绝不直接修改配置**，所有变更都需要用户确认。触发词："修改配置"、"更改配置"、"配置 openclaw"、"设置 openclaw"、"config"。

This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RA...

Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee...

Build validation rules for construction data. Create RegEx and logic-based validation for BIM elements, cost codes, and schedule data.

Plan, draft, version, and refine written content with enforced versioning and quality audits.