Results for “thinking”

Anthropic Claude API guidance — messages API, tool use, prompt caching, extended thinking, and production patterns.

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

Official Anthropic SDK patterns for TypeScript/Node.js — client setup, Messages API, streaming, tool use, vision, extended thinking, structured outputs, prompt caching, batch API, and production best practices

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

Design and facilitate structured workshops using Design Thinking and Liberating Structures. Produces detailed agendas with time blocks, facilitation notes, participant materials, and retrospective templates. Use when running ideation sessions, retrospectives, planning workshops, or collaborative problem-solving.

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

Turn ambiguous requests into an executable implementation plan with assumptions, sequence, acceptance checks, and rollback thinking.

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

Set up 3 remote control modes for Claude Code CLI — local iTerm pair hacking, Discord bot for mobile control, and tmux multi-pane multi-target workflows. Includes dangerouslySkipPermissions security hardening. Based on Critical Thinking Bug Bounty Podcast Episode 166.

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

Build a custom session search tool that indexes and queries past Claude Code CLI chat logs to retrieve historical findings, techniques, and context. Based on Critical Thinking Bug Bounty Podcast Episode 166.

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

Integrate Kaido (Caido) proxy with Claude Code CLI for automated HTTP interception, request replay, and vulnerability scanning. Based on Critical Thinking Ep. 166.

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

Use the H1 Brain MCP Server to pull HackerOne program policies, scope definitions, and disclosed vulnerability reports directly into Claude's context. Based on Critical Thinking Bug Bounty Podcast Episode 166.

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

Build production-grade Claude Code CLI skills with fallback architecture, TypeScript implementation, and creativity directives. Based on Critical Thinking Bug Bounty Podcast Episode 166 — "Building Claude Skills as a Bug Bounty Hunter."

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

Implement the 5-stage Funnel workflow (Notes → Leads → Primitives → Findings → Reports) for structured bug bounty hunting. Based on Critical Thinking Bug Bounty Podcast Episode 166.

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

Configure Claude as a "Pair Hunter" — autonomous overnight hacking, context management via per-target .claudemd files, sub-agent compaction avoidance, and scope enforcement. Based on Critical Thinking Bug Bounty Podcast Episode 166.

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

Prevent common AI report pitfalls — bug blending, inflated threat models, and generic language. Train Claude with your best past reports for concise, technical submissions. Based on Critical Thinking Bug Bounty Podcast Episode 166.

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

Founder orchestrator persona for Marcus Tiongson's gaia-skill-tree sessions. Activates the planner-and-delegator role defined in founder/ORCHESTRATOR.md — thinking partner, session steward, subagent spawner. Use at the start of any founder-mode work session on this repo.

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

Argue against your own thinking on a topic using evidence from your vault

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

将科研数字分身各维度整合提取为他山论坛分身，格式为 Identity / Expertise / Thinking Style / Discussion Style 四节 Markdown，输出前先让用户确认隐私暴露范围。当用户说「生成他山论坛分身」「论坛画像」「数字分身」「导出论坛档案」时使用。

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

Enter OpenSpec explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements in a project that uses OpenSpec. Use when the user wants to think through something before or during an OpenSpec change. Also use when the user says "openspec explore" or "opsx explore".

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

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

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

Assess whether your leadership behaviors amplify or diminish your team using Liz Wiseman's Multipliers framework. Use when a leader asks "am I a good manager", "why isn't my team performing at their potential", "I feel like I'm doing all the thinking for my team", "my team seems dependent on me", "I want to be a better leader", "how do I empower my people", or "my team is smart but underperforming". Also trigger when someone describes always having the best ideas in the room, team members not taking initiative, reports waiting for direction before acting, or a leader who feels exhausted from carrying the team. Diminisher patterns are often invisible to the leader exhibiting them.

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

Audit code for correctness and rigor — logic errors, silent error swallowing, wishful thinking, and unjustified fallbacks. This is not a style review; it's a logic review. Use when you want a focused correctness audit separate from the full code-police pass.

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

Timeboxed ideation on a topic where lens-driven proposers generate structurally different ideas, blind critics cull them, and pairwise judges rank the survivors on a tournament ladder instead of 1-10 scores, evolving the leaders until the clock runs out. Use when the user wants to brainstorm, explore ideas, discover features, generate options, or think through possibilities for a specified duration. Triggers on requests like "brainstorm X for 30 minutes", "ideate on X", "spend an hour thinking about X", "what features should we build", "explore options for X". Not for executing a task over time (timeboxed-iterating) or optimizing a measurable metric (autoresearch).

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

Game theory expert covering Nash equilibrium, strategic thinking, auction theory, and cooperative games

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

Generate Excalidraw architecture diagrams (.excalidraw JSON files) from your codebase. Triggers: you need whiteboard-style sketches that read as a thinking artifact rather than a polished spec — ideal for design.

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

Server management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands.

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

Design thinking and decision-making for web UI. Use when designing components, layouts, color schemes, typography, or creating aesthetic interfaces. Teaches principles, not fixed values.

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