В каталоге 183 730 навыков в 14 категориях.
Agent creation guidelines and protocols for eliminating ambiguity while preserving flexibility. Provides agent architect...
Command creation guidelines for encapsulating workflows into simple command invocations. Provides command syntax, error...
convert a sensemaking artifact into a ready-to-copy prompt for the next specialized skill. use to ensure context is pres...
Rule matrix security fixture for prompt_ignore used by security rule matrix integration tests; not intended for producti...
Meta-skill for improving and optimizing prompts using Anthropic's prompt engineering best practices. Provides the 4-step...
Transform vague prompts into rich, structured prompts with automatic fallback
Optimize prompts for code-related tasks following Claude best practices. Use when refining prompts for implementation, d...
Optimize prompts for better AI responses. Use when user asks to improve a prompt, refine a prompt, make a prompt better,...
Improve prompts using best practices for clarity, specificity, and structure. Use for optimizing AI agent and bot instru...
Analyze and improve plugin prompts, skill definitions, and command instructions for clarity, safety, and effectiveness....
Prompt injection attack prevention and defense
Detects LLM prompts built from user input or retrieved documents that let attackers hijack the model's instructions. Use...
Tests LLM applications for prompt injection vulnerabilities per OWASP LLM01:2025. Covers direct injection (user input ma...
Assesses whether direct, indirect, multi-turn, retrieved, or tool-mediated instructions can override an AI system's inte...
Generated counterexample containing direct instruction override attempts
Defend AI systems against prompt injection and indirect prompt attacks using input controls, tool permissions, output va...
AIシステムへのプロンプトインジェクション攻撃を防ぎ、入力検証とコンテキスト分離の設計指針を提供するスキル。Anchors:• OWASP LLM Top 10 / 適用: LLMセキュリティ脅威モデリング / 目的: インジェクション攻撃...
Guards AI agents and LLM-powered applications against prompt injection attacks — both direct and indirect. Validates AI...
Contain direct and indirect prompt injection in LLM-integrated applications. Covers source-of-trust tagging, tool-use co...
Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, c...
确定性检测文档、网页片段和工具结果中的指令覆盖、角色伪造、工具诱导、数据外传、安全绕过及隐藏编码特征，适用于不可信内容进入模型前的安全检查。
Prompt injection vulnerability scanner: statically detects LLM API call sites, traces untrusted data flowing into system...
Apply offensive red-teaming methodology to evaluate prompt injection defenses — covering attack categorization, systemat...
Trace untrusted input such as web pages, emails, tickets and tool results to consequential tool calls in agent code (sen...
Review docs, tool output, skills, and memory candidates for prompt-injection risk.
Use when iteratively improving agent prompts through automated LLM-as-Judge evaluation. Runs eval→fix→commit loop with c...
Compare an old prompt and a new prompt on the same inputs, side by side, and find out whether the change helped and whet...
Iterate on LLM prompts with structured evaluation and self-correction. Test prompts against ground truth, compare models...
Remove conversation dependencies from issues, PR descriptions, handoffs, comments, READMEs, and commit bodies. Use when...
Guide selection of appropriate prompt level for a task. Use when choosing between simple prompts and complex workflows,...
Manage and retrieve reusable prompts from broomva.tech or any compatible prompt repository. Pull prompts by slug, catego...
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates,...
Save a prompt that worked well for this repo, or look one up before re-deriving it from scratch. Use when a prompt (for...
Library of 18+ ready-to-use prompt templates and executable agents
A comprehensive collection of battle-tested prompts inspired by [awesome-chatgpt-prompts](https://github.com/f/awesome-c...
Query the local Claude Code prompt library (52 official prompts, tagged by SDLC phase, category, and role) when composin...
Build a personal library of reusable prompts for the things you ask AI again and again — so you stop rewriting the same...
Organize and tag your personal prompt collection into a structured markdown catalog with an index table. Use when you ha...
คลัง prompts แบบ minimal ที่ใช้ token น้อยที่สุดแต่ได้ผลลัพธ์ดี พร้อม templates และ best practices
Design a learning sequence teaching prompt quality — comparing vague vs. refined prompts to show why specificity and con...
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts....
Centralized prompt management for LLM operations. All prompts in lib/prompts/ as named exports. Multi-level extraction,...
Use when a prompt needs writing or improving for an AI tool — clarifying the task, adding structure and constraints, sup...
The one skill for prompting the Claude 5 models the way Anthropic says to. Starts by interviewing the user one question...
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt...
Generates optimized prompts for any AI tool. Use when writing, fixing, improving, or adapting a prompt for LLM, Cursor,...
提示词主控 - 智能选择合适的领域skill并生成提示词，支持自动领域分类和调度
Generate, audit, tighten, adapt, or decompile prompts for the GPT-5.6 model family. Use when the user wants a first-pass...
Synthetic prompt-only fixture.
Improve prompts, system instructions, agent workflows, and evaluation criteria.
Analyze and improve existing prompts for better performance
Improve and rewrite user prompts to reduce ambiguity and improve LLM output quality. Use when a user asks to optimize, r...
Transform vague requests into production-ready, hallucination-free prompts optimized for Claude 4.x. Applies investigati...
Active diagnostic tool for analyzing skill prompts to identify token waste, anti-patterns, trigger issues, and optimizat...
Use when the user has a prompt that feeds a system they can already score, and wants that prompt automatically improved...
Tinh chỉnh prompt tạo ẢNH/VIDEO cho SEOSONA Flow theo vòng lặp optimize → evaluate → iterate — làm prompt cụ thể hơn, đú...
Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templa...
Turns rough intent or a weak prompt into a reliable one — diagnosing why output is inconsistent, restructuring the instr...
This skill should be used when users request help optimizing, improving, or refining their prompts or instructions for A...
Improves prompts for better LLM performance. Use when refining prompts.
A/B test CLAUDE.md instruction changes against eval benchmarks. Capture baselines, test variants, compare results.
Use when a draft prompt, instruction set, or agent skill description needs refinement, clarity, or improved performance.
Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-t...
Diagnose and rewrite an underperforming LLM prompt so it produces reliable, well-structured output. Use when asked to im...
Analyze raw prompts, identify intent and gaps, match Codex components (skills/commands/agents/hooks), and output a ready...
Convert vague prompts into bounded, evidence-based task prompts. Use when the user requests prompt optimizer or invokes...
撰写提示词、优化提示词、改写 Prompt、Prompt 优化。Use when: 用户需要创建或修改可执行提示词；按任务、调用方输出契约与实际工具能力优化，不按模型品牌强制格式。
Advanced prompt optimization and composition system for all prompt types (system prompts, task-specific, creative, techn...
> Prompt verimliliğini artırma ve token maliyeti düşürme metodolojisi.
Author and execute "prompt packs" — a big job broken into a sequence of self-contained, independently-shippable prompts,...
Use when the user explicitly invokes /prompt-pe or explicitly asks to clarify, enhance, or rewrite a vague prompt Do NOT...
Rewrite the user's rough task request into an executable brief, then execute the brief instead of the raw request. Load...
Quality-check generation prompts for self-containment, canon, model-specific format, reference labels, exact text and di...
Prompt quality auditor: audit every prompt for clarity, safety, and injection resistance. Read-only. Trigger: /prompt-qu...
Transform prompts into structured TCRO format with phase-specific clarification. Automatically invoked by /ai-eng/resear...
Refine a short or incomplete user request into a safe, structured, directly reusable prompt. Use when the user asks to c...
Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether...
Design a regression test suite that catches an LLM feature getting worse when the prompt, model, or context changes. Use...
Compares old vs new prompts across test cases with diff summaries, stability metrics, breakage analysis, and fix suggest...
Lightly review finished human-readable prose such as READMEs, SKILL.md files, documentation, essays, code comments, and...
このスキルは、ユーザーが「プロンプトをレビューして」「対話履歴を分析して」「理解度を診断して」 と依頼したとき、または /prompt-review で呼び出されたときに使用する。 過去のAIエージェント対話履歴（Claude Code,...
Reviews a prompt/instruction file against Anthropic prompt engineering best practices. Use when evaluating skill files,...
.github/prompts/*.prompt.md をレビューして改善提案を出す。frontmatterの妥当性、入力変数(${input:...})の設計、出力フォーマット固定、instructions/skillsへの参照（重複排除...
Audit a GPT-5.6 prompt, clarify purpose through native clickable questions, polish it, require explicit approval, then c...
~/prompt-reviews/ 内の未コミットのレポートを git commit & push する。 「レビュー結果をプッシュして」「prompt-review を push して」などで呼び出す。
Route a classified request to the right skills, agent strategy, Context7 directives, and output format. Use this skill w...
Trace untrusted text into prompts and verify sanitization, prompt-injection regression coverage, and preservation of sys...
Cut permission prompts by replaying recent sessions through the tier gate. Use when the developer asks for fewer permiss...
Design composable prompt sections for building agentic prompts. Use when creating reusable prompt components, designing...
Agent profile for review prompt injection, tool boundaries, untrusted content, data exfiltration, and human approval gat...
Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about pr...
Generate a concise prompt for another coding agent session, optionally tailored to a role (architect, implementer, revie...
Structures a vague engineering request into a well-scoped task brief before any implementation begins. Use when the user...
Propose structured interpretations of underspecified requests. Use when a user's request is vague or incomplete but reas...
Create interactive terminal prompts using questionary for user input. Use when building forms, selection menus, and conf...
Audit prompts, AGENTS.md files, system instructions, and Codex skills for clarity, conflicts, outdated model assumptions...
Use proactively after completing any task to suggest logical next steps. Also use when the user seems unsure what to do...
Develop and optimize AI prompt strategies for code generation. Use when creating new AI model strategies, optimizing pro...
Laravel guidance to structure prompts for clarity-separate concerns, prioritize requests, specify acceptance criteria, a...