Skills directory · page 2

Add or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.

Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.

Adopt Context Docs in a new or existing project and add its ongoing maintenance rule to the project's agent instruction file, such as AGENTS.md or CLAUDE.md. Use for project setup or adoption requests; use context-docs directly for routine maintenance or audits.

Adopt Context Docs in a new or existing project and add its ongoing maintenance rule to the project's agent instruction file, such as AGENTS.md or CLAUDE.md. Use for project setup or adoption requests; use context-docs directly for routine maintenance or audits.

Tough, critical review of a diff or PR before merge, through hostile reviewer personas that catch shared blind spots. Use whenever the user wants a change torn apart, a harsh second opinion, or a self-review felt too agreeable.

Use when content should be cited by ChatGPT, Perplexity, Claude or Gemini (answer engine optimization), before rewriting it. Scores E-E-A-T and structure with aeo_audit.py, rewrites with aeo_optimizer.py and logs citations with citation_tracker.py.

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

Works through a project while you're away, finding improvements and new ideas, building the best of them on a local branch and leaving a report for when you're back.

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

Full-stack diagnostics for agent and LLM applications. Audits the 12-layer agent stack for wrapper regressions, memory pollution, tool-discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings and code-first fixes. Intended for developers building agent applications, autonomous loops, or LLM-powered features.

Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms — for verification tasks, not unattended automation.

Use when an autonomous agent takes a side-effecting action (deploy, delete, pay, grant access) that may need proving later, or for EU AI Act Art. 12 record-keeping. Builds a tamper-evident signed receipt with build_action_manifest.py and verifies it.

Design multi-agent systems (supervisor, swarm, pipeline) and tool schemas; find bottlenecks in run logs. Use whenever agents split work or a run is slow or costly. Not for Claude Code workflow files (workflow-builder).

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

Compare coding agents such as Claude Code, Aider, and Codex head to head on custom tasks, measuring pass rate, cost, time, and consistency.

A head-to-head comparison of coding agents such as Claude Code, Aider, and Codex on custom tasks, with pass-rate, cost, time, and consistency metrics.

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

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.

Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code interpreter, file search, web search), integrating MCP servers, managing conversation threads, or implementing streaming responses. Covers function tools, structured outputs, and multi-tool agents.

Use when an agent should drive a goal in one of this repo's domains to a verified close, before starting the work. Compiles the goal into a task plan with goal_compiler.py and runs it through loop_controller.py, which verifies each task, caps retries and escalates.

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent's tool set, action space, or observation format.

Audit and apply one policy — model, thinking effort, compaction threshold, approval mode — across every installed coding harness, each with its own config file, knob name, and unit. Use when a setting must hold everywhere or before claiming it is already set. Not for a single-harness edit.

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

A structured self-debugging workflow for AI-agent failures using capture, diagnosis, contained recovery, and introspection reports.

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

Use when someone wants to build, launch, grade or schedule a Claude Managed Agent in their own Anthropic account ('build me an agent', 'run this nightly'). Reads the session goal, routes with goal_router.py and compiles the loop with loop_compiler.py.

Create, manage, and orchestrate AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "hibernate agent", "wake agent", "install plugin", "show agent", "restart agent", or any agent lifecycle management task.

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

How to use the agent-marketplace CLI to install shared AI agent resources from Git, directory, or hosted Marketplace sources and materialize them into native harness layouts. Use when setting up a repo, writing `.agents/config.yaml`, installing/removing skills, commands, subagents, hooks, MCP servers, or collections, checking sync drift, updating locks, preparing pre-upgrade configuration conversion, or repairing shared harness config ownership.

How to develop on the agent-marketplace codebase itself: architecture tour, testing workflow, TUI (Bubble Tea) and CLI (Cobra) conventions, and the config/resolver/materialization invariants that every change must preserve. Use when adding features, fixing bugs, or reviewing changes to the agent-marketplace Go binary, running local TUI QA, or maintaining harness compatibility validation. Every TUI change must ship a real-terminal TUI QA journey that proves the changed flow.

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.

Use when an agent keeps relearning the same correction, CLAUDE.md has grown unreadable, or you need to trace where a remembered rule came from. Promotes facts through four tiers only on recurrence across sessions and days, with memory_promote.py and a human adopt step.

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm

Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.

Evolve an agent's operating contract: its identity file, operating protocol, layered memory / skills / config, and any repo whose product IS an agent contract or control plane. Use when asked to optimize, review, or refactor those files, or when the owner corrects how the agent approached identity, routing, delegation, or persistence. Not for ordinary repo coding rules, and not for one-off task notes.

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Support Base through agentwallet-sdk, X Layer through OKX Payments / OKX Agent Payments Protocol, and Solana plus multi-network EVM through upstream x402 packages and facilitator-based settlement.

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk, X Layer through OKX Payments / OKX Agent Payments Protocol, and Solana plus multi-network EVM through the upstream x402 packages with facilitator-based settlement. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Support Base through agentwallet-sdk, X Layer through OKX Payments / OKX Agent Payments Protocol, and Solana plus multi-network EVM through upstream x402 packages and facilitator-based settlement.

Use when C-suite advisor agents need to call each other or run a multi-role meeting. Defines invocation syntax, loop prevention, isolation and response formats.

Use before shipping any agent, prompt, model or tool change, or when a pass-rate drop needs a verdict. Runs repeated trials, gates candidate vs baseline with paired statistics in regression_gate.py, checks tool-call trajectories and finds flaky cases.

Use when asked why an agent did something, what a past session or run changed, whether tests really passed, or to verify a session summary. Answers from the recorded transcript, not memory, with trace_finder.py, trace_timeline.py and claim_checker.py.

Verify a local agent API, temporary gateway tunnel, and remote sandbox callback with a tool-free task, then restore the original app connection.

Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime identifiers, or handle credentials. Use when building or reviewing an agent runtime, autonomous worker, tool gateway, memory service, or multi-tenant agent deployment. Do not use for general web application security or offensive testing.

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

Build an evidence-based ECC installation plan for a specific repository by conducting a parallel, repository-aware review of skills, commands, rules, hooks, and extras, classifying them into DAILY and LIBRARY categories. Use when ECC should be trimmed to what the project actually needs rather than loading the full package.

並行リポジトリ対応のレビューパスを使用して、スキル、コマンド、ルール、フック、エクストラを DAILY と LIBRARY のバケットに分類することで、特定のリポジトリ向けのエビデンスに基づいた ECC インストール計画を構築します。プロジェクトが完全なバンドルをロードする代わりに実際に必要なものに ECC をトリミングする必要がある場合に使用します。

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa