Research

Standalone CLI bridge - launch external AI CLIs (gemini, codex, claude) directly without MCP server. Use when you need to delegate tasks to specialized CLI tools with their own context windows. Supports role-based prompts and file references.

Use OpenAI's Deep Research API (o3 / o4 models) to automate multi-step, citation-backed research workflows.

Help with paper references using paperpipe (papi). Use when user asks about papers, wants to verify code against a paper, needs paper context for implementation, or asks about equations/methods from literature.

Conducts systematic investigations across diverse information sources with cross-validation and credibility assessment. Use when researching complex topics, fact-checking claims, understanding different perspectives, or building comprehensive understanding. Triggers on phrases like "investigate", "verify", "fact check", "cross-reference", "multiple sources", "different perspectives on".

Complete adapter lifecycle assistant for LimaCharlie. Supports External Adapters (cloud-managed), Cloud Sensors (SaaS/cloud integrations), and On-prem USP adapters. Dynamically researches adapter types from local docs and GitHub usp-adapters repo. Creates, validates, deploys, and troubleshoots adapter configurations. Handles parsing rules (Grok, regex), field mappings, credential setup, and multi-adapter configs. Use when setting up new data sources (Okta, S3, Azure Event Hub, syslog, webhook, etc.), troubleshooting ingestion issues, or managing adapter deployments.

コマンド/エージェント/スキルの統合設計を整理し、連携パターンと複合ワークフローを支援するスキル。起動パターン、参照パターン、統合検証の手順を一貫して整理する。Anchors:• The Pragmatic Programmer (Andrew Hunt, David Thomas) / 適用: 連携手順の設計 / 目的: 再現性の確保• Multi-Agent Systems (Wooldridge) / 適用: エージェント連携 / 目的: 協調設計の整理• Workflow Patterns (van der Aalst) / 適用: 複合ワークフロー / 目的: 実行フローの明確化Trigger:Use when integrating commands with agents and skills, designing composite workflows, or validating integration rules.command agent skill integration, composite workflow, agent invocation, skill reference

This skill enables Claude to design and execute chaos engineering experiments to test system resilience. It is used when the user requests help with failure injection, latency simulation, resource exhaustion testing, or resilience validation. The skill is triggered by discussions of chaos experiments (GameDays), failure injection strategies, resilience testing, and validation of recovery mechanisms like circuit breakers and retry logic. It leverages tools like Chaos Mesh, Gremlin, Toxiproxy, and AWS FIS to simulate real-world failures and assess system behavior.

Quick reference for operating within jonmagic's second-brain workspace. Use when working with files in the brain repository—provides directory structure, naming conventions, append-only norms, wikilink patterns, and file organization rules. Essential for understanding where to create files, how to name them, and how to maintain continuity with existing structures.

State-of-the-art procedure for fixing bugs in software projects. Use this skill when a bug has been detected or declared by the user, agent, or another skill (not during early-stage work in progress). Enforces a disciplined test-driven approach - understand, reproduce experimentally, write failing tests, fix the code, and clean up.

Author documentation for Tenzir projects. Use when creating or updating tutorials, guides, explanations, reference, or integrations.

Research library documentation and API references using Context7 integration. Use when users ask about libraries, frameworks, packages, APIs, or need documentation for third-party code.

Prepares a complete interview plan based on the Candidate Profile and company research. Use after receiving an invitation.

Initialize a new software project with customized structure through interactive Q&A. Use when user mentions "new project", "start project", "initialize project", "create project", or "set up project". Gathers methodology, team structure, documentation preferences, and integration requirements to generate appropriate RULE.md and directory structure.

Research technical solutions by searching the web, examining GitHub repos, and gathering evidence. Use when exploring implementation options or evaluating technologies.

Transform research ideas into compelling, fundable grant proposals (NSF, NIH, ERC).

Use when addressing PR review comments - REQUIRES TodoWrite first (Iron Law), then follows structured 7-step workflow to assess comment validity with feature-research, distinguish bugs from style preferences, and fix valid issues or refute invalid ones with evidence

Synthesize research findings for OAK planning using the oak.plan-research workflow. Use when consolidating findings from codebase exploration, comparing approaches, or creating research/*.md documents.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Validates research/plan/code against overengineering, underengineering, and hallucination

Comprehensive guide for implementing Fullstory's User Consent API for web applications. Teaches proper consent flow implementation, selective capture modes, GDPR/CCPA compliance patterns, and cookie consent integration. Includes detailed good/bad examples for consent banners, preference centers, and privacy-conscious recording to help developers implement privacy-compliant session recording.