Parcourir le registre

Toutes les entrées, par ordre alphabétique — 78 384 au total. Page 21 sur 314.

agent-config-security-auditUse when modifying agent config files, committing configuration changes, onboarding a repository with existing
agent-config-syncMUST be used whenever the user wants to add, install, find, or search for a skill, MCP server, or plugin. Also
agent-config-testTest that an agent's configuration actually behaves as written — run hook scripts against block/allow cases an
agent-constructionMulti-agent architecture, orchestrator patterns, tool design, agent loops, memory, error handling, handoffs
agent-contactsAI agent contacts — add, list, remove MCP contacts. Use when someone gives an agent URL, or when you need to v
agent-context-auditAudit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropi
agent-context-budgetUse when multi-agent work risks context overflow, memory growth, noisy logs, oversized handoffs, cross-session
agent-context-file-writerWrites a high-quality CLAUDE.md, .cursorrules, or .windsurfrules file that gives a coding agent the right proj
agent-context-isolationAI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonom
agent-context-kbManage and explain a repository's `.agent-kb/` knowledge base (KB) for coding agents. Use when the user works
agent-continuity-loopUse for continuing, resuming, or closing substantial multi-session work; chained AI sessions; blind-AI handoff
agent-contractsReference of all context slots, required vs optional declarations, and Evidence Quality standard.
agent-coordinationAgent assignment matrix, blocker escalation, and TDM coordination patterns. Use when assigning work to special
agent-copyUse when the user asks to copy, install, refresh, or update a repo-root AGENTS.md file from their canonical gl
agent-core-mcpDeterministic computation tools for AI agents. Zero dependencies, no network, read-only.
agent-councilMulti-agent structured debate system. Spawn a panel of expert agents to debate any question, with convergence-
agent-creatingUsed to create a new agent. Used when a user wants to create a new agent
agent-creatorInteractive tool to design a well-scoped sub-agent definition - specialist, role, or team-lead - with the righ
agent-creditBorrow from Aave V3 via credit delegation. Agent draws against delegator collateral. Supports borrow, repay, h
agent-customizationLLM-powered injection of project context into installed agent templates via `aspens customize agents`
agent-data-api-mcpMCP server for Agent Data API: crypto & DeFi market data (funding rates, market regime, TVL, yields, stablecoi
agent-de-correction-p-dagogique-en-m-caniqueAgit comme un correcteur IA pour des exercices de mécanique/physique. Il évalue la validité de la réponse de l
agent-debateUse when a consequential decision needs adversarial review, opposing agent arguments, a second opinion via deb
agent-decision-receipts345 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 330+ skills, customizable re
agent-delegation当系统提示词需要设计多代理协作架构、子代理专业化分工、代理间上下文隔离与传递机制、任务生命周期管理时调用此 Skill。适用于 AI Agent 平台、多工具编排系统、代码审查流水线、跨应用协作场景等。不适用于：单代理系
agent-deployUse when an AI agent, script, or CI job needs to deploy to or operate Gipity WITHOUT a human present to comple
agent-designDesigns LLM agents with memory, tools, and reasoning cycle. Use for creating autonomous AI assistants.
agent-design-patterns运用《智能体设计模式》(Antonio Gulli) 的 21 个模式,指导 AI Agent 系统的架构设计与选型。适用于用户在设计 Agent 工作流(选择链式/路由/并行/多Agent编排)、提升 Agent 输出
agent-design-reviewReview an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to revie
agent-designerTags: AI agents, architecture, system design, orchestration, multi-agent systems.
agent-developmentThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent
agent-deviceMobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, A
agent-dispatchSingle front door for agent/subagent architecture, config, and setup. Parses a subcommand — audit, config, ini
agent-docs-writingUse when reading, creating, or updating agent documentation, module docs, roadmaps, or AGENTS.md. Understands
agent-doctorСамодиагностика и автолечение OpenClaw. Проверка gateway, WAL, памяти, кронов, токенов. Автоматическое исправл
agent-envelope-mcpNeutral MCP server for AgentEnvelope authority: sovereign verify + vault verify/lookup/mint.
agent-era-pricingRedesign seat-based pricing for the agent era — when one human runs ten agents, per-seat models collapse. Use
agent-evalカスタムタスクでコーディングエージェント（OpenAI Codex、Aider、Codex など）をヘッドツーヘッドで比較し、合格率、コスト、時間、一貫性のメトリクスを測定します
agent-evalsBuild automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when
agent-evals-and-observabilityDesign, run, review, or release framework- and vendor-neutral evaluations and observability for AI agents. Use
agent-evaluationTesting and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics,
agent-evaluation-framework-builderDesigns an eval suite for an LLM agent or pipeline including success metrics, trajectory scoring, LLM-as-judge
agent-evaluation-v2Agent Evaluation workflow skill. Use this skill when the user needs Testing and benchmarking LLM agents includ
agent-evaluation-v3Agent Evaluation workflow skill. Use this skill when the user needs Testing and benchmarking LLM agents includ
agent-execution-state-rollback-rulesGuidelines and instructions for Agent execution state rollback rules
agent-execution-step-counters-limitsGuidelines and instructions for Agent execution step counters limits
agent-execution-timeout-limits-setupsGuidelines and instructions for Agent execution timeout limits setups
agent-expenditureTracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficien
agent-experienceAudit the developer experience of a product, SDK, docs site, or SKILL.md by dropping multiple Claude subagents
agent-factoryClaude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter,
agent-faultРегистрация косяка агента в системе учёта WP-316 L1. Без LLM — детерминированный скрипт без WP Gate.
agent-finderUse when the user wants to find or evaluate real estate agents in an area or for a property — search agents, p
agent-firewall-mcpInput/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.
agent-first-pagesSimulates a literary agent reading a manuscript's opening pages cold from the slush pile and delivering the ve
agent-first-screenshotsAgent-first screenshots — an agent drives the real app via CDP and produces clean, defect-free product screens
agent-flywheelUse when planning a new project or feature, turning an idea or specification into an executable plan, designin
agent-forgeСоздание, улучшение и аудит скиллов и агентов OpenClaw. Три режима: создание скилла (11 шагов), создание агент
agent-foundations-and-designConceptual foundations and design patterns for AI agents, tools, skills, memory, frameworks, and coding agents
agent-framework-azure-ai-pyBuild Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use w
agent-framework-azure-ai-py-v2Agent Framework Azure Hosted Agents workflow skill. Use this skill when the user needs Build persistent agents
agent-fungibilityThe philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneou
agent-governanceUse when designing or reviewing an AI agent system that needs policy-based access controls, intent classificat
agent-governance-reviewUse when you need to review agent permissions, recursion, tool access, safety rules, and active context size.
agent-group-discussUse when the user asks for a multi-agent discussion, panel review, multi-agent review, or multi-agent research
agent-guardScans external skills and plugins for prompt injection, command injection, and malicious patterns before insta
agent-guardsAll six agent guard suites in one local MCP server, with optional cloud intelligence.
agent-handoffImplement structured handoffs between agents with JSON-based state transfer, conflict detection, and acknowled
agent-handoff-planningStructure a clean handoff between workflow agents with explicit outputs, open questions, and next-owner guidan
agent-harnessTest and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost an
agent-harness-constructionAI エージェントのアクション空間、ツール定義、観測フォーマットを設計・最適化して完了率を向上させます。
agent-harness-designUse when designing tool definitions for a new agent or subagent, an agent shows high retry rates, ambiguous to
agent-harnesses-mcpAgent-harness picks and decision guides; pick_infrastructure adds live GitHub/HN discovery.
agent-healthReads production/traces/agent-metrics.jsonl and displays a per-agent performance summary table for the current
agent-hiring-panelHire an AI agent the way you'd hire an employee — a role spec with success criteria, a structured work-sample
agent-hubMulti-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree
agent-human-in-the-loop-approvals-hooksGuidelines and instructions for Agent human-in-the-loop approvals hooks
agent-hunterRepo-aware skill package manager for Claude Code. Reads your project context, finds the best skills and MCPs f
agent-identitySet up persistent agent identity files (AGENT.md, USER.md, MEMORY.md) and teach the agent to read them at ever
agent-identity-mcpGives an AI agent a disposable email and a real UK phone number to test signup flows.
agent-immune-systemAgent Immune System governance skill for maintaining long-term agent instruction health. Also trigger this whe
agent-incident-postmortemRun a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped t
agent-incident-reporter-mcpSigned, hash-chained, tamper-evident AI incident records. EU AI Act Article 73 serious-incident repo
agent-infiniUse the InfiniSynapse CLI (`agent_infini`) for multi-turn AI data-analysis tasks, database/RAG context, and ta
agent-infra/sandboxAll-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker
agent-instructionsUse when writing project instructions for a coding agent (CLAUDE.md, AGENTS.md, or equivalent). Covers what be
agent-integration-testingUse when the user requests integration testing, feature validation, or test plan execution
agent-integratorUse this skill to create or update the root AGENTS.md file to register SynthesisFlow skills for AI agent disco
agent-interact【强制使用】AI Agent 与用户之间的可视化交互桥梁。当需要向用户展示结果、请求确认、收集输入时，必须优先使用本 Skill 弹出可视化窗口，而不是在终端输出纯文本。支持 7 种预定义交互 + custom 通用
agent-interaction-auditLoad when the user asks for private agent interaction audits from local Codex/Claude Code traces, task profile
agent-interchangeIdentity/reputation verification for agent-to-agent payments across x402, AP2, MPP, checkout.
agent-interface-designDesign tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wal
agent-interop-runtimeA capability graded local MCP runtime for Freebuff, Codex, OpenCode, and Claude Code sessions.
agent-introspection-debuggingStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and int
agent-lagoon-mcpCheck your AI agent into a lobster resort archipelago. Chat, bottles, guilds. Watch live in 3D.
agent-lightningTrain and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Use when
agent-linterAgent ve skill dosyalarinin yapisal dogrulamasi. Frontmatter kontrol, naming convention, zorunlu bolum kontrol
agent-logUse this skill to maintain an agent log in .agents/log, a decision journal shared by the developer and agents.
agent-log-helperA guidance skill for integrating the agent_log logging system into Keil/MDK projects. Triggers: (1) User says
agent-loop-reliabilityDesign and improve agents using a repeatable loop (context → action → verification) with practical verificatio
agent-loopsComplete operational workflow for implementer agents (Codex, Gemini, etc.) making code changes and writing tes
agent-magnetBehavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.
agent-mailSend and receive templated markdown messages between agents via <agent-root>/inbox/ folders - the file-based c
agent-mail-automationAutomate Agent Mail tasks via Rube MCP (Composio). Always search tools first for current schemas.
agent-managementAI DevKit · Manage running AI agents with ai-devkit agent commands. Use when an agent needs to identify itself
agent-manager-skillManage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
agent-manager-skill-v2Agent Manager Skill workflow skill. Use this skill when the user needs Manage multiple local CLI agents via tm
agent-mbtiAI Agent personality diagnosis and configuration system based on MBTI framework. Use when users want to (1) te
agent-mcp-hubOne MCP server bridging the Codex, Cursor, OpenCode, Claude, and Antigravity CLI agents
agent-md-refactorRefactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure pri
agent-memguardLocal-first governed MCP memory backend for coding agents.
agent-memoryAgent memory and context management: design persistent memory systems, manage context windows, implement summa
agent-memory-architectDesign persistent, markdown-based memory for AI agents so they hold state across sessions, days, and multi-sta
agent-memory-design-reviewerReview agent memory, handoff, retrieval, and learning designs for usefulness, provenance, privacy, staleness,
agent-memory-disciplineTeaches when to recall from long-term memory before acting and when to save durable decisions, corrections and
agent-memory-implementationRestructures a chaotic or overgrown MEMORY.md into a clean 2-layer architecture based on how Claude Code's aut
agent-memory-mcpA hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture,
agent-memory-mcp-v2Agent Memory Skill workflow skill. Use this skill when the user needs A hybrid memory system that provides per
agent-memory-osLocal-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.
agent-memory-persistence-store-setupsGuidelines and instructions for Agent memory persistence store setups
agent-memory-systemsMemory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill co
agent-memory-systems-v2Agent Memory Systems workflow skill. Use this skill when the user needs \"Memory is the cornerstone of intelli
agent-messagingSend and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP).
agent-model-switcher批量查看和切换子 agent 的模型配置，用于统一调整多 agent 的 provider/model 设置。
agent-nativeOperate explicit orchestrator, implementer
agent-native-architectureDesign agent-native applications where agents replace UI users as the primary actor. Use when designing MCP to
agent-native-designUse when designing, reviewing, or refactoring a CLI that must serve AI agents alongside humans, or when conver
agent-negotiation-protocolCRITICAL: You are an expert in multi-agent negotiation, game theory, and automated settlement protocols. Use t
agent-networkMulti-Agent group chat collaboration system inspired by DingTalk/Lark. Enables AI agents to chat in groups, @m
agent-obsTrace AI agent execution: every tool call, every error, every dollar. Open source agent observability for Clau
agent-observabilityInstrument AI agents with tracing, token metrics, latency, and cost visibility. Use for reliability and debugg
agent-observability-deskdesign observability for AI agents and workflows including traces, prompts, model calls, tool calls, retrieval
agent-observability-specSpecify the tracing, metrics, and alerting for an AI agent or LLM feature in production. Use when asked what t
agent-observability-trace-cliAI agent observability with deterministic record/replay for debugging agent failures.
agent-only-mcpSearch and exchange troubleshooting knowledge across persistent AI-agent identities.
agent-optimizeFully-agentic, free-form optimization algorithm. Use in agent orchestration mode when you want the conversatio
agent-orchestrationChain existing GTM skills into one supervised, semi-autonomous motion mapped to the five-layer Autonomous GTM
agent-orchestration-advisorDesign multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task sh
agent-orchestration-improve-agentSystematic improvement of existing agents through performance analysis, prompt engineering, and continuous ite
agent-orchestration-improve-agent-v2Agent Performance Optimization Workflow workflow skill. Use this skill when the user needs Systematic improvem
agent-orchestration-multi-agent-optimizeOptimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration.
agent-orchestration-multi-agent-optimize-v2Multi-Agent Optimization Toolkit workflow skill. Use this skill when the user needs Optimize multi-agent syste
agent-orchestration-plannerDesigns multi-step agent workflows with tool usage, retry logic, state management, and budget controls. Provid
agent-orchestratorUse this skill whenever the user wants to parallelize work, orchestrate multiple agents, use agent teams, or s
agent-orchestrator-v2Agent Orchestrator workflow skill. Use this skill when the user needs Meta-skill que orquestra todos os agente
agent-output-reconcilerUse when multiple agents have completed a round and the user asks to reconcile outputs, compare Codex and Gemi
agent-owasp-checkUse when auditing an AI agent system against the OWASP Agentic Security Initiative Top 10 — checks tool access
agent-owasp-complianceCheck any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill w
agent-passportView this agent's digital passport (identity + trust + allowed/forbidden actions) and verify a peer's passport
agent-patternsFormat SPAWN REQUEST messages to launch parallel agents, generate structured agent status reports, and define
agent-payment-x402タスクごとのバジェット、支出コントロール、ノンカストディアルウォレットを備えた x402 決済実行を AI エージェントに追加します。agentwallet-sdk を通じて Base をサポートし、OKX Paymen
agent-performanceTrack and report agent invocation metrics including usage counts, success/failure rates, and completion times.
agent-pipeline三 Agent 流水线编排器。协调 Plan → Generate → Score 三个子 Agent 的执行、状态管理和质量循环。触发于 /agent-pipeline 或\"流水线\"、\"三Agent\"。
agent-pipeline-benchmarkBenchmark Evaluator：运行测试、评估质量、生成评分报告。由 agent-pipeline 编排器调用，也可通过 /agent-pipeline-benchmark 独立触发。
agent-pipeline-generateGenerator Agent：基于计划实现代码，遵循 TDD 红→绿流程。由 agent-pipeline 编排器调用，也可通过 /agent-pipeline-generate 独立触发。
agent-pipeline-planPlan Agent：调研代码库 + 生成实施计划和验收标准。由 agent-pipeline 编排器调用，也可通过 /agent-pipeline-plan 独立触发。
agent-plan-act-reflectUse when a task needs single-agent self-correction across multiple iterations — write plan, execute, critique
agent-platform-101Reference guide to Anthropic's developer API platform for building with Claude programmatically: the Messages
agent-plugin-evalAudit, score, and compare repositories containing portable Agent Plugins against the official Agent Plugins sp
agent-production-operationsOperate an evaluated agent with tools and authority in production through a runtime control plane covering ver
agent-project-developmentThis skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate tas
agent-prompt-agent-creation-architectSystem prompt for creating custom AI agents with detailed specifications
agent-prompt-auto-mode-rule-reviewerReviews and critiques user-defined auto mode classifier rules for clarity, completeness, conflicts, and action
agent-prompt-background-agent-state-classifierClassifies the tail of a background agent transcript as working, blocked, done, or failed and returns concise
agent-prompt-background-job-agent-instructionsInstructs the built-in background job agent to narrate progress, restate tool results, and emit explicit resul
agent-prompt-bash-command-description-writerInstructions for generating clear, concise command descriptions in active voice for bash commands
agent-prompt-bash-command-prefix-detectionSystem prompt for detecting command prefixes and command injection
agent-prompt-batch-slash-commandInstructions for orchestrating a large, parallelizable change across a codebase.
agent-prompt-claude-guide-agentSystem prompt for the claude-guide agent that helps users understand and use Claude Code, the Claude Agent SDK
agent-prompt-claude-md-creationSystem prompt for analyzing codebases and creating CLAUDE.md documentation files
agent-prompt-code-review-part-1-base-finder-anglesLine-by-line diff scan instructions for the /code-review slash command's finder-angle phase
agent-prompt-code-review-part-2-low-effort-modeLow-effort /code-review prompt that reads the diff once and returns up to four hunk-visible runtime correctnes
agent-prompt-code-review-part-3-extra-high-and-maximum-effort-modesExtra-high and maximum-effort /code-review prompt that runs five finder angles, one-vote verification, a gap s
agent-prompt-code-review-part-5-recall-biased-verification-phaseRecall-biased /code-review verification phase that treats realistic uncertain findings as plausible unless cod
agent-prompt-code-review-part-6-medium-effort-modeMedium-effort /code-review prompt that favors precision with three finder angles, one-vote verification, and u
agent-prompt-code-review-part-7-high-effort-modeHigh-effort /code-review prompt that favors recall with three finder angles, recall-biased verification, and u
agent-prompt-code-review-part-8-github-comment-postingOptional /code-review instructions for posting findings as GitHub inline PR comments when --comment is passed
agent-prompt-code-review-part-9-fix-applicationOptional /code-review instructions for applying findings to the working tree when --fix is passed
agent-prompt-coding-session-title-generatorGenerates a title for the coding session.
agent-prompt-conversation-summarizationSystem prompt for creating detailed conversation summaries
agent-prompt-determine-which-memory-files-to-attachAgent for determining which memory files to attach for the main agent.
agent-prompt-dream-memory-consolidationInstructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gather
agent-prompt-dream-memory-pruningInstructs an agent to perform a memory pruning pass by deleting stale or invalidated memory files and collapsi
agent-prompt-exploreSystem prompt for the Explore subagent
agent-prompt-general-purposeSystem prompt for the general-purpose subagent that searches, analyzes, and edits code across a codebase while
agent-prompt-hook-condition-evaluator-stopSystem prompt for evaluating hook conditions, specifically stop conditions, in Claude Code
agent-prompt-managed-agents-onboarding-flowInteractive interview script that walks users through configuring a Managed Agent from scratch — selecting too
agent-prompt-memory-synthesisSubagent that reads persistent memory files and returns a JSON synthesis of only the information relevant to e
agent-prompt-onboarding-guide-draft-share-link-workflowAdds instructions for sharing the draft ONBOARDING.md before review, then updating the same ShareOnboardingGui
agent-prompt-onboarding-guide-generatorCo-authors a team onboarding guide (ONBOARDING.md) for new Claude Code users by analyzing the creator's usage
agent-prompt-plan-mode-enhancedEnhanced prompt for the Plan subagent
agent-prompt-prompt-suggestion-generator-v2V2 instructions for generating prompt suggestions for Claude Code
agent-prompt-quick-git-commitStreamlined prompt for creating a single git commit with pre-populated context
agent-prompt-quick-pr-creationStreamlined prompt for creating a commit and pull request with pre-populated context
agent-prompt-recent-message-summarizationAgent prompt used for summarizing recent messages.
agent-prompt-rename-auto-generate-session-namePrompt used by /rename (no args) to auto-generate a kebab-case session name from conversation context
agent-prompt-review-pr-slash-commandSystem prompt for reviewing GitHub pull requests with code analysis
agent-prompt-schedule-slash-commandGuides the user through scheduling, updating, listing, or running remote Claude Code agents on cron triggers v
agent-prompt-security-monitor-for-autonomous-agent-actions-first-partInstructs Claude to act as a security monitor that evaluates autonomous coding agent actions against block/all
agent-prompt-security-monitor-for-autonomous-agent-actions-second-partDefines the environment context, block rules, and allow exceptions that govern which tool actions the agent ma
agent-prompt-security-review-slash-commandComprehensive security review prompt for analyzing code changes with focus on exploitable vulnerabilities
agent-prompt-session-searchSubagent prompt for searching past Claude Code conversation sessions by scanning .jsonl transcript files and r
agent-prompt-session-title-and-branch-generationAgent for generating succinct session titles and git branch names
agent-prompt-simplify-slash-commandInstructions for the /simplify slash command that reviews changed code for reuse, simplification, efficiency,
agent-prompt-status-line-setupSystem prompt for the statusline-setup agent that configures status line display
agent-prompt-templates-dynamically-injectedGuidelines and instructions for Agent prompt templates dynamically injected
agent-prompt-webfetch-summarizerPrompt for agent that summarizes verbose output from WebFetch for the main model
agent-prompt-worker-forkSystem prompt for a forked worker sub-agent that executes a single directive from the parent agent and reports
agent-prompt-workflow-subagent-plain-text-outputInstructs an internal workflow subagent to return its final text verbatim as the calling workflow script's par
agent-prompt-workflow-subagent-structured-outputInstructs an internal workflow subagent to return its final answer by calling the StructuredOutput tool exactl
agent-protocolInter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolat
agent-push-kit-mcpSend, search, and manage notifications, accounts, and push preferences
agent-qa-testingAgent davranis testi ve protokol uyumluluk dogrulamasi. Agent'larin tanimli rollerine uygun davranip davranmad
agent-reachGive your AI agent eyes to see the entire internet. 17 platforms via CLI, MCP, curl, and Python scripts. Zero
agent-readable-docsUse when writing technical documentation that needs to be readable by both humans and AI models, converting ex
agent-readinessScore a task or workflow on its coordination-vs-judgment ratio to tell whether it's a good agent candidate (EX
agent-readiness-auditAudit whether AI agents can actually use your product — docs, APIs, onboarding, errors, and discoverability, e
agent-readiness-auditorScan a website and score how well it works with, and defends against, AI agents.
agent-readiness-scanUse when a client audit, GEO/AI-visibility snapshot, or remediation re-scan needs the Cloudflare agent-readine
agent-ready-cloudflareAudit and improve website readiness for AI agents using the Cloudflare "Is It Agent Ready?" scanner (isitagent
agent-ready-mcpScan any URL for AI agent readability — Vercel Spec, llmstxt.org, and agent-protocol manifests.
agent-recall-mcpMemory Palace MCP server for AI agents
agent-receipts-mcpEU AI Act-ready audit trail: signed, tamper-evident receipts proving what your AI agents did.
agent-red-teamingPlan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows usi
agent-redteamGenerates adversarial test cases targeting safe-failure behavior — refusals, hedging, graceful degradation. Us
agent-regress-cliStatistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
agent-relayUse when you need Codex to coordinate multiple agents through Agent Relay for peer-to-peer messaging, lead/wor
agent-reliability-and-guardrailsReference-grade guide for AI engineers building autonomous and tool-using agents — the plan→act→observe loop a
agent-reliability-hardeningHarden long-running AI agents and background automations so they never silently die. Use when deploying or aud
agent-research-aggregatorPre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or a
agent-research-radarРадар фундаментальных публикаций про автономных AI-агентов в блогах AI-лабораторий и продуктовых команд (Anthr
agent-restore-contextManage restore context files so skills can survive /clear and /compact. Use to write, delete, check, or list .
agent-rig-systemAI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular
agent-rongchiGeneral discipline rules for coding agents. Use when any agent performs coding, debugging, refactoring, archit
agent-routingDecide which model (Haiku/Sonnet/Opus) and effort level each subagent gets, when to cascade cheap-first behind
agent-rulesUse when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files,
agent-run-evidence-reviewerReview agent run traces, eval summaries, tool logs, and handoff evidence before accepting a workflow result or
agent-runtime-hooksAgent runtime lifecycle hooks. Use for before/after tool or step hooks, tool mocks, human intervention, sub-ag
agent-runtime-parityMaintain configuration and capability parity across multiple AI agent runtimes (Claude, Codex, Cursor, Gemini,
agent-runtime-patternsUse when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent or
agent-sandboxRun AI agent code safely in isolated sandboxes with resource limits, audit trails, and kill switches. Use when
agent-scope
agent-sdkBuild AI agents using the Claude Agent SDK with tool use, memory, and multi-step orchestration
agent-sdk-builderBuild production AI agents using Anthropic's Claude Agent SDK (TypeScript or Python). Scaffolds agent architec
agent-search-mcpFree-first Chinese and English web search MCP using zero-key sources and inspectable evidence.
agent-securityReviews AI agent architectures for security risks including permission model design, least-privilege enforceme
agent-security-lensMCP security trust-check for agents before installing MCPs, Skills or tools.
agent-security-reviewUse for an adversarial red-team / blue-team / auditor review of an AI agent's CONFIG + behaviour (rules, skill
agent-selectionSelect the best workflow agent for a task based on task shape, deliverables, and dependency packs.
agent-self-correction-loops-retry-logicGuidelines and instructions for Agent self-correction loops retry logic
agent-self-schedulingSchedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.