'prompt' 검색 결과

반복하는 LLM API 요청에서 공통 지시와 자료를 캐시로 재사용하기 쉽게 배치합니다. 캐시 사용량, 읽기·쓰기·저장 비용과 응답 시간을 확인해 구성을 검토합니다.

• 반복 API 요청의 공통 지시를 재배치합니다
• 캐시 읽기·쓰기·저장 비용을 계산합니다
• 캐시 사용률과 응답 시간을 측정합니다

Polish an existing prompt file by improving its wording, structure, and organization. Correct spelling, grammar, and unclear instructions while preserving the original intent, front matter, encoding, and Markdown structure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Polishing a prompt before sharing it
• Clarifying instructions without changing their intent
• Reviewing the order and organization of a long prompt

Review AI prompts for harmful output risks, bias, privacy concerns, security weaknesses, and clarity. Receive an assessment, a revised prompt, and suggested tests with explanations of the principles behind each improvement.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a prompt before putting it into use
• Check wording for stereotypes and bias
• Assess data exposure and prompt injection risks

Build a screening pipeline for web pages, PDFs, and images before an AI agent reads them. Extract hidden text, check for malicious instructions with detection models, and record decisions to block or allow content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Screening external content before an agent reads it
• Checking uploaded PDFs and images for hidden instructions
• Scanning documents before adding them to a knowledge base

Design and audit an agent's system prompt, the instructions that guide its work. Define a concrete outcome, starting input, available tools, completion checks, fallback behavior, and final report so the prompt describes a complete run.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing the core instructions for a new agent
• Auditing a prompt before saving it
• Defining behavior when tools or permissions are missing

Convert articles, tutorials, or prompt collections into reusable agent skills, with one independent capability per skill. Package portable instructions, example prompts, working demos, preview images, and validation so the methods can transfer to other projects.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Convert tutorial steps into reusable agent skills
• Split a prompt collection into independent capabilities
• Package skills with example prompts and working demos

Rewrite a prompt to address the same task more deeply. The skill identifies what an expert would examine, which original materials and methods they would use, and what independent evidence would confirm the result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Refining a request without expanding its scope
• Identifying original materials and expert methods
• Adding independent criteria for checking results

Create a copy-ready prompt teammates can give their AI agents to apply a fix, upgrade, or setup change. It includes tested commands, verification steps, stopping conditions, and what to report, with enough context to work independently.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sharing a tested fix with teammates
• Preparing an upgrade request for another person's AI agent
• Handing off setup changes to non-technical teammates

Improve a Browserbase Agent's system prompt by running a fixed task, examining messages and logs, and changing one instruction at a time. Compare quality, duration, and message counts, then repeat runs to check consistency.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Refining prompts for a Browserbase Agent demo or proof of concept
• Diagnosing inconsistent Agent runs from recorded evidence
• Comparing prompt revisions by quality, duration, and message count

Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt optimization validation, "did my prompt change help," or prompt regression testing. Outputs per-dimension win rates with statistical significance using OpenJudge PairwiseAnalyzer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Analyzes and improves prompts using 31 frameworks across 7 intent categories. Use when a user wants to improve, rewrite, structure, or engineer a prompt — including requests like "help me write a better prompt", "improve this prompt", "what framework should I use", "make this prompt more effective", or any prompt engineering task. Recommends the right framework based on intent (create, transform, reason, critique, recover, clarify, agentic), asks targeted questions, and delivers a structured, high-quality result.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when 王建硕 wants to evaluate whether a change to VoiceDrop's 挖矿 system prompt is actually better than the live version — runs the local eval harness (golden fixtures × champion-vs-candidate, same input), dispatches blind pairwise judge subagents, aggregates a win-rate verdict, and on approval promotes the candidate into agent/src/prompts/mine.js. Triggers — "评估 prompt"、"挖矿 prompt 改好了吗"、"eval prompt"、"比一比两版 prompt"、"/wjs-evaling-voicedrop-prompts".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build a production-ready prompt package — system prompt, few-shot examples, output format, edge case handling, eval criteria. Use when asked to "prompt engineering", "build a prompt", "write a system prompt", or "improve this prompt".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Specialized business strategy prompt methodology for Claude. Provides 11 tested approaches (3 identity, 4 reasoning, 4 output formats) for consulting, M&A, corporate strategy, and strategic planning tasks. Use when building prompts for deal evaluation, due diligence, portfolio strategy, business model analysis, board narratives, investment cases, market entry plans, or strategic options assessments. Trigger on: "build a prompt for M&A analysis," "due diligence prompt," "board narrative," "investment case," "market entry strategy," "strategic options," "portfolio strategy prompt," "business model analysis prompt," "consulting-style analysis." Do NOT use for evaluating or scoring existing prompts (use rootnode-prompt-validation if available) or for auditing Claude Projects (use rootnode-project-audit if available).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate on "optimize prompt", "improve this prompt", "prompt engineering", or ANY complex task request. Requires prompt-learning MCP server. NOT for simple questions (just answer them), NOT for direct commands (just execute them), NOT for conversational responses (no optimization needed).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate on "optimize prompt", "improve this prompt", "prompt engineering", or ANY complex task request. Requires prompt-learning MCP server. NOT for simple questions (just answer them), NOT for direct commands (just execute them), NOT for conversational responses (no optimization needed).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Writes, fixes and red-teams prompts — system prompts, templates, meta-prompts, agent or bot instructions — as copy-paste-ready artifacts, and picks the model tier for a prompt, task or plan's subtasks. Trigger to write, improve, debug or rewrite a prompt; which model should run this; a prompt that costs too many tokens, to cut with behavior held; or say promptwright (model, optimize — tune against test cases, slim, refresh). Not for a fan-out's units (dispatchwright), installed local models (lmstudiorunner), skills or their slim (skillwright), sourced comparisons (researchscribe), handoffs (handoffwright) or a pre-build interview (grillwright).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Screen AI application inputs and historical logs for prompt injection, where malicious instructions try to redirect the model. Combine pattern matching, text structure scoring, and a DeBERTa classifier to flag suspicious content and produce JSON results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Screening chatbot and AI agent inputs
• Checking external text used in retrieval-based AI applications
• Auditing historical interaction logs for injection attempts

Plan caching for repeated LLM requests by choosing what to reuse: shared prompt beginnings, complete responses, or documents loaded in advance. Covers Anthropic prompt caching, cache invalidation, and problems caused by changing inputs or outdated answers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reusing shared instructions across Claude requests
• Caching answers to repeated or similar questions
• Planning document preloading with CAG

Improve prompts through test cases and baseline comparisons, measure how well AI answers use retrieved sources, and check agent configurations. Includes Python tools for prompt analysis, retrieval quality reports, and token estimates, with costs calculated from supplied rates.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare prompt revisions against a baseline
• Measure answer quality against retrieved sources
• Check agent tool settings and loop risks

Use Meta's Prompt Guard to detect malicious instructions in user prompts and external data. This skill guides input filtering, batch checks for retrieved documents, detection threshold adjustments, and splitting long text for inspection.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Detecting attempts to override an LLM's instructions
• Checking API responses for embedded malicious instructions
• Batch screening documents retrieved for RAG