GitHub
curiosity-loops
Use when facing a significant decision (career pivot, product direction, technical choice) and feeling stuck or indecisive, when seeking contextual advice rather than generic recommendations
☆ 2查看技能
研究与调研 AI 技能
发现 研究与调研 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
分类目录: 研究与调研
研究与调研 清除筛选
全部技能
GitHub
unstuck-scaling
Use when AI agents frequently hit dead ends, when reliability is the main constraint on scaling utility, or when general model improvements don't solve specific blockers
☆ 2查看技能
GitHub
selective-micromanagement-matrix
Leadership is a dynamic range. When confidence in team direction is low, temporary tactical micromanagement is the correct move—not autonomy. Teach the framework, then pull back.
☆ 2查看技能
GitHub
ai-teammate-model
Use when designing AI agent products, defining roadmaps for agentic workflows, or evaluating how to evolve AI from passive tool to proactive partner in software development
☆ 2查看技能
GitHub
causal-interview-protocol
A JTBD interviewing technique to reconstruct the customer's timeline and uncover causal mechanisms behind a purchase. Resembles criminal investigation—penetrate surface-level answers to find the struggling mome...
☆ 2查看技能
GitHub
house-operational-architecture
A three-part structural framework for building a scalable company—Foundation (Founding Documents), Posts & Beams (Supporting Structures), and Mechanicals (Operating Cadence). Use when moving from PMF to scaling...
☆ 2查看技能
GitHub
bar-raiser-hiring-mechanism
A quality control mechanism with a designated interviewer from outside the hiring chain who has veto power to ensure candidates raise the bar (better than 50% of current employees in role). Amazon's talent dens...
☆ 2查看技能
GitHub
bar-test-positioning
Use after drafting positioning statements, before writing website copy, or when marketing language sounds corporate rather than human
☆ 2查看技能
GitHub
three-layer-agent-stack
Use when building AI-powered products or agents, when raw model intelligence isn't enough to solve user problems, or when designing the architecture for agentic workflows
☆ 2查看技能
GitHub
fear-and-anger-decision-filter
Fear creates exaggerated negative predictions. When gripped by fear, bet that the opposite will happen if you act against it, then take action. Use for high-stakes decisions that feel emotionally dangerous.
☆ 2查看技能
GitHub
long-horizon-holdout
Use when running experiments on platforms where user value compounds over time, when growth teams claim credit for revenue that would have happened anyway, or when short-term wins don't translate to long-term v...
☆ 2查看技能
GitHub
in-the-details-review-loop
A leadership cadence where the CEO/Leader reviews actual work (designs, prototypes, copy) weekly rather than just metrics or status slides. Use when feeling product quality is slipping or team is moving too slo...
☆ 2查看技能
GitHub
add-a-zero-heuristic
A goal-setting mental model where leaders increase the target by 10x to force teams to abandon current processes and use first-principles thinking. Use during annual planning when teams default to safe, increme...
☆ 2查看技能
GitHub
absolute-volume-framework
Use in power-law businesses like platforms or VC, when conversion rate optimization shrinks your funnel, or when efficiency metrics block potential outlier winners
☆ 2查看技能
GitHub
energy-audit-and-zone-of-genius
Review your calendar, color-code activities by energy impact (Green/Red), and systematically delegate draining tasks to maximize time in your Zone of Genius.
☆ 2查看技能
GitHub
hierarchy-of-marketplaces
A roadmap for marketplace domination. Level 1: Focus on a "thimble" to maximize Happy GMV. Level 2: Tip the market via growth loops. Level 3: Dominate to capture economic rents. Not all GMV is equal.
☆ 2查看技能
GitHub
chatter-driven-development
Use when designing futuristic agentic workflows, when wanting AI to proactively act on team communications, or when eliminating the bottleneck of formal specifications
☆ 2查看技能
GitHub
controllable-inputs-framework
Focus on Input Metrics (selection, price, speed) rather than Output Metrics (revenue, stock price). Inputs are controllable and causal; outputs are lagging. Amazon's flywheel philosophy.
☆ 2查看技能
GitHub
gardening-mindset
Use when dealing with ecosystems, network effects, or high-uncertainty environments where the right answer cannot be known in advance, when rigid planning consumes more value than it creates
☆ 2查看技能
GitHub
waterline-model
Diagnose team problems by checking structural issues (goals/roles) at the surface before diving deep into personality conflicts. 80% of team problems are structural, not personal.
☆ 2查看技能
GitHub
project-experience
Project-specific patterns, conventions, and learnings for docker-containers. Triggers: "project patterns", "how does this project", "project conventions", "local setup", "build order", "test setup", "project-sp...
☆ 2查看技能
GitHub
codex-collaboration
This skill should be used when the user asks to "collaborate with Codex", "use Codex for planning", "get Codex review", "delegate to Codex", "Codexと協調", "Codexにレビューを依頼", "Codexに計画を作成させたい",...
☆ 2查看技能
GitHub
opence-plan
Create an opence plan and scaffold change artifacts.
☆ 2查看技能
GitHub
opence-archive
Archive a completed change and apply spec updates to the main specifications.
☆ 2查看技能
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。