Testing & Security skills

Evaluate a codebase for agent-friendliness based on autonomous agent best practices. Use when asked to "evaluate for agents", "check agent readiness", "audit for autonomous execution", "assess agent-friendliness", or when reviewing infrastructure for unattended agent operation. Also use when asked about making a codebase more suitable for AI agents or autonomous workflows.

The English summary is being prepared. Showing the original description.

Create .agent/baseline.md and later compare against it. Use when capturing baseline build/lint/test results or investigating newly introduced findings.

The English summary is being prepared. Showing the original description.

Handle failures and errors during workflow. Use when build breaks, tests fail unexpectedly, or agent gets stuck. Semi-automatic recovery with user confirmation for destructive actions.

The English summary is being prepared. Showing the original description.

Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.

The English summary is being prepared. Showing the original description.

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.

The English summary is being prepared. Showing the original description.

Initialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or replace an agent init command (Codex, Claude), standardize multi-agent behavior, or audit an existing AGENTS.md for clarity, commands, boundaries, and repo-specific context. For Claude Code, also create CLAUDE.md as a symlink to AGENTS.md.

The English summary is being prepared. Showing the original description.

Design and implement evaluation frameworks for AI agents. Use when testing agent reasoning quality, building graders, doing error analysis, or establishing regression protection. Framework-agnostic concepts that apply to any SDK.

The English summary is being prepared. Showing the original description.

Use these when you want low-noise lint/test output (good for LLM/CI logs) while staying aligned with repo policy.

The English summary is being prepared. Showing the original description.

Use this skill when architecting new Claude Code agents following Anthropic best practices. Guides through YAML frontmatter creation, agent structure definition, role boundaries, and validation. Critical for creating minimal agent files (~150 lines) with proper skill invocations. Examples: <example>Context: User wants to create a new agent for security auditing user: "Create a security-auditor agent" assistant: "I'll use the agent-creator skill to build this agent following Anthropic best practices" <commentary>New agent creation requires the agent-creator skill to ensure proper structure and YAML frontmatter.</commentary></example> <example>Context: Existing agent file is too verbose and needs refactoring user: "The architect agent is 2000 lines, refactor it to minimal structure" assistant: "I'll use the agent-creator skill to refactor this into a minimal ~150 line agent with a separate skill file" <commentary>Agent refactoring requires the agent-creator skill to separate identity from technical procedures.</commentary></example>

The English summary is being prepared. Showing the original description.

Implement hooks for permission control and security in custom agents. Use when adding security controls, blocking dangerous operations, implementing audit trails, or designing permission governance.

The English summary is being prepared. Showing the original description.

Deterministic custom subagent selection helper. Use when you need a reproducible, auditable decision on which custom subagents to activate for a user query (runs scripts/agent_evaluator.py).

The English summary is being prepared. Showing the original description.

Add a new AI provider to agentconfig.org's comparison system. Use when integrating a new coding assistant (e.g., Cursor, Claude Desktop, GitHub Copilot alternative) with proper type system updates, implementation data, UI components, tests, and documentation.

The English summary is being prepared. Showing the original description.

Generate adversarial inputs, edge cases, and boundary test payloads for stress-testing LLM robustness

The English summary is being prepared. Showing the original description.

Comprehensive documentation of Claude's capabilities for visual regression testing, CI/CD integration, and quality assurance automation. Use when setting up testing infrastructure, implementing visual regression, or understanding agent testing capabilities. (project)

The English summary is being prepared. Showing the original description.

Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update the model configuration. Covers models.json configuration, CI test matrix, and handle validation.

The English summary is being prepared. Showing the original description.

Analyze recent changes and add test coverage for HEAD commit

The English summary is being prepared. Showing the original description.

Answer Engine Optimization (AEO) audit methodology for LLM visibility. Use when auditing brands for ChatGPT/Gemini mentions, checking LLM citations, analyzing AI search visibility, or when user mentions "AEO", "LLM visibility", "ChatGPT mentions", "Gemini citations", or "AI search optimization".

The English summary is being prepared. Showing the original description.

Expert chaos engineer specializing in controlled failure injection, resilience testing, and building antifragile systems. Masters chaos experiments, game day planning, and continuous resilience improvement with focus on learning from failure.

The English summary is being prepared. Showing the original description.

Review documentation for quality, clarity, SEO, and technical correctness. Optimized for Docus/Nuxt Content but works with any Markdown documentation. Use when asked to: "review docs", "check documentation", "audit docs", "validate documentation", "improve docs quality", "analyze documentation", "check my docs", "review my documentation pages", "validate MDC syntax", "check for SEO issues", "analyze doc structure". Provides actionable recommendations categorized by priority (Critical, Important, Nice-to-have).

The English summary is being prepared. Showing the original description.

Complete DataForSEO API integration for SEO data and analysis. Use when the user asks for keyword research, search volume, SERP analysis, backlink audits, competitor analysis, rank tracking, domain authority, technical SEO audits, content monitoring, Google Trends, or any SEO-related data queries. Covers all DataForSEO APIs including SERP, Keywords Data, DataForSEO Labs, Backlinks, OnPage, Domain Analytics, Content Analysis, Business Data, Merchant, App Data, and AI Optimization APIs. Outputs CSV files.

The English summary is being prepared. Showing the original description.

Run the backend verification loop after Kotlin/Spring code changes — Kotlin style + unit tests via `gradlew verify`, plus integration tests when repos/migrations changed — and drive fixes until green. Use after editing backend code or when the user asks to verify/check the build.

The English summary is being prepared. Showing the original description.

Multi-step reasoning engine for complex analysis and systematic problem solving. Use when: (1) Complex debugging scenarios with multiple layers, (2) Architectural analysis and system design, (3) Problems requiring hypothesis testing and validation, (4) Multi-component failure investigation, (5) Performance bottleneck identification. Triggers: "--think", "--think-hard", "--ultrathink", "analyze step by step", "break down this problem", "systematic analysis". IMPORTANT: Do NOT use for simple single-step tasks.

The English summary is being prepared. Showing the original description.

Grill the user about a requirement, decision, or idea before implementation, then produce an actionable planning report without writing code. Use when the user wants to clarify requirements, stress-test an idea, compare approaches, or plan before coding.

The English summary is being prepared. Showing the original description.

Analyze liquid markets with a strict ICT/SMC framework that combines multi-timeframe bias, liquidity sweeps, displacement, close-confirmed MSS/BOS, FVG/OB/Breaker/OTE retracements, premium-discount location, session timing, invalidation, targets, and risk-to-reward. Use for ICT chart reviews, live-market analysis, OHLCV scans, or validating a user's trade thesis. Return an auditable setup status and conditional plan; do not use for generic indicator analysis, order execution, or claims of proven institutional intent.

The English summary is being prepared. Showing the original description.