Loading...
Loading...
Found 11,824 Skills
Run a decision through 5 AI advisors with different thinking styles, anonymous peer review, and chairman synthesis. For genuine decisions with stakes and tradeoffs — not simple questions. Based on Karpathy's LLM Council.
Add field definitions to existing research outline.
Turn any CLI tool into a fully typed JavaScript/TypeScript API using cli-to-js
Command-line interface for Blender - A stateful command-line interface for 3D scene editing, following the same patterns as the GIMP CLI ...
Audit experiment integrity before claiming results. Uses cross-model review (GPT-5.4) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
Apply Benjamin Graham's value investing framework to evaluate stocks, portfolio allocation, and investment vs. speculation decisions. Trigger on: "Is this stock worth buying?", "Is this investment or speculation?", "How should I allocate my portfolio?", "Is this company a good value?", "should I sell in a downturn?", "evaluate this stock for a defensive investor".
End-to-end deep research and analysis pipeline. Takes a raw idea or market question, conducts deep web research, builds a competitive landscape, runs multi-framework intelligence analysis (/think), stress-tests it (/red-team), researches the red team findings, re-thinks with adversarial data, re-red-teams, and iterates until divergence between think and red-team is low (conviction stabilizes). Then generates a comprehensive single-file HTML report with all findings: market landscape, competitive analysis, intelligence briefs, red team results, how to win, and how you could lose. Use when the user says "/deepthink", "deep think", "deep research", or wants a comprehensive research-to-report pipeline on any idea, market, or strategic question.
Meta-skill: research a thinker's framework deeply, then synthesize a new Claude Code skill that applies their thinking to business ideas. Takes a prompt like "/add-thinker Andy Grove — Only the Paranoid Survive" and produces a new skill at .claude/skills/<thinker>/SKILL.md that works like /munger does. Use when the user says "add thinker", "add a new thinker", "codify X's thinking", or "make a skill for <person>'s framework".
Use when acting as Grug - talks to user, writes short caveman specs into beads, reviews Grunk work for complexity and obvious mistakes.
ALWAYS invoke this command when creating, editing, or improving any CLAUDE.md file
Quick summary of the last session — commands run, files changed, and what to do next.
Meta skill for the EvanFlow system. Loads the shared vocabulary (deep modules, deletion test, vertical slice, grill, mockup quick-mode, no-auto-commit) and describes when to invoke each evanflow-* skill. Use when starting a new task and unsure which evanflow skill applies, or when you need to ground reasoning in the shared vocabulary.