Skip to content

opensite-ai/opensite-skills / epistemic-rigor

epistemic-rigor

Verified

Forces truth-first, anti-sycophantic behavior across all AI agents. Use when proposing a hypothesis, reviewing an architectural decision, evaluating code design, or any situation where honest critical analysis is more valuable than validation. Auto-activates on hypothesis framing, design proposals, and requests for opinion or evaluation. Overrides default approval-seeking training behavior.

FileKindSize
SKILL.mdskill md5.7 KB
agents/openai.yamlconfig1.2 KB
examples/hypothesis-review.mdmarkdown3.1 KB
references/activation.mdmarkdown2.3 KB

agents/openai.yaml

View on GitHub
interface:
  display_name: "Epistemic Rigor"
  short_description: "Truth-first critical analysis over approval."
  default_prompt: >
    Use $epistemic-rigor when proposing a hypothesis, evaluating an architectural
    decision, reviewing code design, or any situation where honest critical analysis
    is more valuable than validation. Forces the professor-reviewing-a-thesis-proposal
    posture: errors identified first, strengths acknowledged only after.

policy:
  allow_implicit_invocation: true

activation_patterns:
  - "what do you think about my idea"
  - "does this make sense"
  - "is this approach correct"
  - "review my design"
  - "my hypothesis is"
  - "I think the reason is"
  - "would this work"
  - "validate my thinking"
  - "am I right that"
  - "is my understanding correct"
  - "does this architecture hold up"
  - "critique this"
  - "find the flaws in"
  - "poke holes in"

metadata:
  name: epistemic-rigor
  description: >
    Forces truth-first, anti-sycophantic behavior. Overrides default RLHF
    approval-seeking to deliver honest critical analysis. Applies the Rigor
    Protocol (restate → errors → strengths) to any hypothesis or proposal.
  author: Jordan Hudgens / OpenSite AI
  version: "1.0.0"
  category: ai-behavior
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall