搜索「Prompt」的结果

io.clawhub.ethagent/prompt

A comprehensive AI agent skill for writing prompts that get consistently excellent results from AI models. Teaches the principles behind effective prompting,...

io.clawhub.seojoonkim/prompt-guard

650+ pattern AI agent security defense covering prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, cascad...

io.clawhub.maorun/prompt-injection-guard

Prompt injection defense. Detect and block malicious prompts, protect system instructions, sanitize user input.

io.clawhub.nukewire/clawdefender

Security scanner and input sanitizer for AI agents. Detects prompt injection, command injection, SSRF, credential exfiltration, and path traversal attacks. Use when (1) installing new skills from ClawHub, (2) processing external input like emails, calendar events, Trello cards, or API responses, (3) validating URLs before fetching, (4) running security audits on your workspace. Protects agents from malicious content in untrusted data sources.

io.clawhub.abe238/adversarial-prompting

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.

io.clawhub.gyaan-dub/prompt-enhancer

Automatically rewrites rough user inputs into optimized, structured prompts for dramatically better AI responses. Prefix any message with "p:" to activate.

io.clawhub.syedateebulislam/remember-all-prompts-daily

Preserve conversation continuity across token compaction cycles by extracting and archiving all prompts with date-wise entries. Automatically triggers at 95% token usage (pre-compaction) and 1% (new sprint start) to export session history, then ingests archived summaries on session restart to restore context.

io.clawhub.alexunitario-sketch/prompt-assemble

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.

io.clawhub.aviv4339/indirect-prompt-injection

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.

io.clawhub.eltemblor/email-prompt-injection-defense

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.

io.clawhub.tolibear/promptify-skill

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.

io.clawhub.zskyx/detect-injection

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.

io.clawhub.dandysuper/seedance-2-prompt-engineering-skill

Generate precise, timecoded Seedance 2.0 prompts integrating multimodal inputs with asset mapping for controlled 4-15s video creation and editing.

io.clawhub.tolibear/promptify

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.

io.clawhub.abdullah4ai/prompt-architect

Transform rough ideas into professional-grade LLM prompts. Analyzes text, images, links, and documents to craft optimized prompts using proven frameworks (Co...

io.clawhub.thesash/prompt-log

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.

io.clawhub.zhang-shubo/image2prompt

Analyze images and generate detailed prompts for image generation. Supports portrait, landscape, product, animal, illustration categories with structured or natural output.

io.clawhub.tomstools11/prompt-engineering-expert

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

skillsmp.nidhinjs-prompt-master-skill-md

Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other non-prompt-engineering work.

io.github.affaan-m/ECC/prompt-optimizer

Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.

io.github.microsoft/hve-core/prompt-refactor

Refactor existing prompt artifacts against explicit requirements through the full prompt-builder loop.

io.github.mukul975/Anthropic-Cybersecurity-Skills/testing-prompt-injection-in-rag-pipelines

Probe RAG applications for prompt injection via poisoned retrieved context and embedding manipulation.

io.github.mukul975/Anthropic-Cybersecurity-Skills/testing-for-system-prompt-leakage

Extract and defend system prompts plus embedded secrets and routing logic.

io.github.xalgord/xalgorix/testing-llm-prompt-injection-and-jailbreaks

Testing LLM-backed applications, chatbots, and AI agents for direct and indirect prompt injection, jailbreaks, system-prompt leakage, and tool/agent abuse during authorized penetration tests, using structured payload families and reliable confirmation signals.