Thermal engineering for infrastructure: heat transfer (conduction, convection, radiation), cooling load analysis for data centers, heat exchanger sizing via LMTD and e-NTU,…
Score 70/100
Track and update investment theses for portfolio positions and watchlist. Maintains scorecard of pillars, catalysts, and conviction level.
Score 70/100
Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database).
Score 70/100
Good-faith divergent brainstorming for achieving a goal. Validates assumptions, then spawns brainstormers running different techniques (first-principles, working-backwards,…
Score 70/100
Adversarial deliberation process for making decisions. Spawns advocate agents for each option who argue their cases before a judge (you) who renders a verdict.
Score 70/100
Apply Alan Chan (Heptabase CEO) framing — product 0→1 / 深度學習 / focus 紀律 / 跨領域推論 / 招聘判斷.
Score 70/100
Apply Naval Ravikant's framing — leverage / specific knowledge / wealth-vs-capture / long-horizon bets / desire management.
Score 70/100
Retrospective learning from a completed experience. Takes a project, incident, decision that played out, or time period; gathers ground truth (observations) separately from…
Score 70/100
Good-faith adversarial scrutiny of an idea or plan. Spawns critical skeptics across relevant lenses, pairs them with an advocate defending the idea, and synthesizes the exchange…
Score 70/100
强制 AI Agent 在执行任何高风险或实质性操作（如修改文件、执行命令、查询数据库）前进行逻辑梳理、步骤拆解。这是一种显式驱动 ReAct 循环的思想链（CoT）触发器。
Score 70/100
When the user wants to review past decisions, understand why something was built a certain way, audit decision quality, or learn from past reasoning.
Score 70/100
Update beliefs systematically based on new evidence using probabilistic reasoning. Use when estimating probabilities, learning from data, or making decisions under uncertainty.
Score 70/100
Apply Herbert Simon's Bounded Rationality and satisficing to make good-enough decisions under real-world constraints.
Score 70/100
Know the boundaries of your expertise and operate within them. Use when evaluating opportunities, making decisions outside your domain, or assessing when to defer to experts.
Score 70/100
Classify problems by complexity domain (clear, complicated, complex, chaotic) and match approach to domain. Use for choosing methodologies, problem framing, and process design.
Score 70/100
Systematic checklist to identify and counteract cognitive biases in decision-making. Use before major decisions, when evaluating recommendations, or when stakes are high.
Score 70/100
Engages structured analysis to explore multiple perspectives and context dependencies before responding.
Score 70/100
Core thinking disciplines for rigorous collaborative reasoning. Invoked by skills that need truth-convergent thinking — come prepared, name confidence, sit with fog, verify before…
Score 70/100
Apply Kahneman's Dual-Process Theory to recognize when to trust intuition vs engage deliberate analysis.
Score 70/100
Make order-of-magnitude estimates for unknown quantities by decomposing into known or estimable factors.
Score 70/100
For non-perishable things, future life expectancy is proportional to current age. Use for technology selection, evaluating frameworks/libraries, and predicting tool longevity.
Score 70/100
Combine multiple mental models for richer analysis. Use for complex problems requiring multiple lenses, high-stakes decisions, or when single models leave blind spots.
Score 70/100
Rapid decision-making loop for dynamic situations. Use for incident response, competitive scenarios, time-sensitive decisions, and situations requiring quick adaptation.
Score 70/100
Express confidence in ranges, update predictions with new information, and track calibration over time.
Score 70/100
Argue against the strongest version of opposing positions, not the weakest. Use for design reviews, evaluating alternatives, conflict resolution, and decision validation.
Score 70/100
Use when facing a decision, unclear or recurring problem, system behavior question, communication challenge, or when generating novel solutions — loads structured thinking…
Score 70/100
Improve by removal rather than addition. Focus on what to stop doing, eliminate the negative, and subtract complexity.
Score 70/100
Review third-party skill repos for format fit, provenance, and first-party adoption paths without treating them as direct harness dependencies.
Score 70/100
Provides guidance on creating custom error types with thiserror, including proper derive macros, error messages, and source error chaining.
Score 70/100
Structured X thread templates — 12 proven thread formats (listicle, story, how-to, contrarian, etc.) with fill-in frameworks.
Score 70/100
PyQt/PySide6 threading and concurrency - QThread, QThreadPool, QTimer, thread safety, concurrent patterns
Score 70/100
Model extension lifecycle as intent, materialization, and active runtime layers, then sync each layer with dedicated transitions.
Score 70/100
Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or…
Score 70/100
Creates simple Three.js web apps with scene setup, lighting, geometries, materials, animations, and responsive rendering.
Score 70/100
Three.js color pipeline — sRGB vs Linear, toneMapping (None/ACES/Reinhard), texture colorSpace, when to use NoToneMapping for UI textures.
Score 70/100
Three.js scene setup, cameras, renderer, Object3D hierarchy, coordinate systems. Use when setting up 3D scenes, creating cameras, configuring renderers, managing object…
Score 70/100
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or…
Score 70/100
Three.js vanilla 3D guidelines for WebGL/WebGPU. Apply when editing `.js`/`.ts` files with Three.js imports or `three` package usage.
Score 70/100
Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating…
Score 70/100
Three.js lighting - light types, shadows, environment lighting. Use when adding lights, configuring shadows, setting up IBL, or optimizing lighting performance.
Score 70/100
Three.js asset loading - GLTF, textures, images, models, async patterns. Use when loading 3D models, textures, HDR environments, or managing loading progress.
Score 70/100
Three.js materials - PBR, basic, phong, shader materials, material properties. Use when styling meshes, working with textures, creating custom shaders, or optimizing material…
Score 70/100
Three.js post-processing - EffectComposer, bloom, DOF, screen effects. Use when adding visual effects, color grading, blur, glow, or creating custom screen-space shaders.
Score 70/100
Three.js shaders - GLSL, ShaderMaterial, uniforms, custom effects. Use when creating custom visual effects, modifying vertices, writing fragment shaders, or extending built-in…
Score 70/100
Create 3D scenes, interactive experiences, and visual effects using Three.js. Use when user requests 3D graphics, WebGL experiences, 3D visualizations, animations, or interactive…
Score 70/100
Three.js textures - texture types, UV mapping, environment maps, texture settings. Use when working with images, UV coordinates, cubemaps, HDR environments, or texture…
Score 70/100
Implement API throttling policies to protect backend services from overload. Use when controlling API request rates.
Score 70/100
Plan and run a campus event people actually show up to: dinner, talk, conference, screening, run, ritual, pop-up, or weird scene. Heavy on wedge, invite design, and distribution.
Score 70/100
Add an idea to the backlog parking lot (999.x numbering)
Score 70/100
Add phase to end of current milestone in huntmap
Score 70/100
Capture idea or task as todo from current conversation context
Score 70/100
Audit milestone completion against original intent before archiving
Score 70/100
Run all remaining phases autonomously — discuss→plan→execute per phase
Score 70/100
List pending todos and select one to work on
Score 70/100
Archive completed milestone and prepare for next version
Score 70/100
Route freeform text to the right hunt or THRUNT command automatically
Score 70/100
Execute a trivial task inline — no subagents, no planning overhead
Score 70/100
Insert urgent work as decimal phase (e.g., 72.1) between existing phases
Score 70/100
Surface the agent's assumptions about a phase approach before planning
Score 70/100
Interactive command center for managing multiple project or hunt phases from one terminal
Score 70/100