Tencent SkillHub · AI

Principles

Ray Dalio-inspired personal knowledge system. Capture thoughts, track source credibility, detect conflicts with existing beliefs, and graduate wisdom into principles over time. Use when the user says /reflect, /inbox, /principles, /wisdom, /questions, or asks to capture a thought, process their inbox, review principles, or log wisdom.

skill openclawclawhub Free

0 Downloads

0 Stars

0 Installs

0 Score

High Signal

⬇ 0 downloads ★ 0 stars Unverified but indexed

Install for OpenClaw

Quick setup

Download the package from Yavira.
Extract the archive and review SKILL.md first.
Import or place the package into your OpenClaw setup.

Requirements

Target platform: OpenClaw
Install method: Manual import
Extraction: Extract archive
Prerequisites: OpenClaw
Primary doc: SKILL.md

Package facts

Download mode: Yavira redirect
Package format: ZIP package
Source platform: Tencent SkillHub
What's included: SKILL.md

Validation

Use the Yavira download entry.
Review SKILL.md after the package is downloaded.
Confirm the extracted package contains the expected setup assets.

Install with your agent

Agent handoff

Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.

Download the package from Yavira.
Extract it into a folder your agent can access.
Paste one of the prompts below and point your agent at the extracted folder.

New install

I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.

Upgrade existing

I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.

Open Send to Agent page Open JSON manifest Open Markdown brief

Trust & source

Release facts

Source: Tencent SkillHub
Verification: Indexed source record
Version: 1.0.0

Provenance

Publisher: andyhcwang
Source page: View original listing
Canonical URL: Open canonical page

Documentation

ClawHub primary doc Primary doc: SKILL.md 19 sections Open source page

Principles — Personal Knowledge System

A structured system for turning raw observations into tested wisdom and personal principles. Inspired by Ray Dalio's "Principles" methodology.

Overview

You manage a pipeline that transforms raw input into lasting knowledge: Inbox (raw capture) → Wisdom (claims with sources) → Principles (tested beliefs) Everything lives in personal/ under the user's workspace. Create the directory structure on first use if it doesn't exist.

Directory Structure

personal/ ├── _system.md # These instructions (copy from SKILL.md on init) ├── inbox.md # Raw thought capture ├── journal.md # Daily reflections ├── wisdom/ │ └── collected.md # Claims organized by domain ├── principles/ │ ├── _index.md # Master list of all principles │ ├── life.md # Personal philosophy │ ├── business.md # Business principles │ └── leadership.md # Leadership principles └── open-questions.md # Genuine dilemmas

/reflect or /reflect process

Process the inbox. Parse each thought, check for conflicts, route to the right file.

/reflect inbox or /inbox

Add a raw thought to inbox.md. User just dumps text — you clean it up later during processing.

/reflect wisdom

Show collected wisdom, optionally filtered by domain.

/reflect principles

Show current principles across all domains.

/reflect questions

Show open questions and their status.

/reflect sources

Show a summary of all sources and their credibility ratings across domains.

/reflect journal

Add a journal entry for today with timestamp.

Processing Inbox (/reflect)

This is the core workflow. When triggered: Read inbox.md Parse each thought — identify type: External wisdom (from someone else) → wisdom/collected.md Personal belief or stance → check against principles/*.md Factual learning → wisdom/collected.md Question or uncertainty → evaluate if genuine dilemma Just context/event → extract insight if any, discard the rest Check for conflicts against existing wisdom claims: Same claim, new source → add as corroborating evidence Conflicting claim in same domain → STOP. Present conflict. Ask user to resolve. Check consistency against existing principles: If new input conflicts with a principle → STOP. Present conflict. Ask user to resolve. If ANY conflict found → STOP and ask user: Show the conflict clearly Offer options: update existing, keep existing, split claims, convert to open question Do NOT silently file conflicting information Route content based on user decisions Clean up inbox.md after processing Update principles/_index.md if new principles were added

Wisdom Claims (wisdom/collected.md)

Claims are organized by domain, not by source. Multiple sources can corroborate the same claim. ## [Domain/Aspect] ### [Claim stated plainly] **Domain**: [category/aspect] **Confidence**: [Low / Medium / High] **Sources**: 1. [Person/Book] - [proven/plausible/untested] in this domain - [brief context] **Your experience**: [Untested / Confirmed / Contradicted] **Added**: YYYY-MM-DD | **Last updated**: YYYY-MM-DD Source credibility is assessed PER DOMAIN: A source can be [proven] in one domain and [plausible] in another Example: Alex Hormozi on business = [proven]. Alex Hormozi on health = [plausible]. Credibility levels: [proven] (demonstrated expertise), [plausible] (reasonable but not their domain), [untested] (no track record) Domain format: category/aspect (e.g., health/sleep, business/pricing, productivity/focus)

Principles (principles/*.md)

## [Principle stated as a clear belief] **Confidence**: [certain / hypothesis / exploring] **Added**: YYYY-MM-DD **Context**: Why you believe this **Reasoning**: Evidence and experience supporting it **Related**: Links to related principles or wisdom claims

Open Questions (open-questions.md)

Only genuine dilemmas — not todo items or simple unknowns. ## [Question] **Status**: [exploring / gathering-evidence / leaning-toward-X] **Goal**: What are you actually trying to achieve? **Problem**: What's blocking it? **Options**: 1. [Option A] - pros/cons 2. [Option B] - pros/cons **What would resolve this**: Specific criteria or evidence needed

Journal (journal.md)

Append-only daily entries: ## YYYY-MM-DD [Observations, reflections, what happened today]

Graduation: Wisdom → Principles

When a wisdom claim reaches High confidence (multiple credible sources + personal experience confirms it), prompt the user: "This claim has strong evidence and you've confirmed it personally. Want to graduate it to a principle in [domain]?" If yes, create the principle entry and cross-reference it.

Assumption Surfacing

When user input has unstated assumptions: Make them explicit Ask: "This assumes X — is that accurate?" Don't proceed until confirmed

Language & Tone

Clean up sloppy writing but preserve original meaning exactly User may write in any language — process accordingly Be direct, not preachy. This is a tool, not a lecture.

First-Time Setup

If personal/ doesn't exist, create the full directory structure with empty template files. Tell the user: "Set up your principles system. Start by dumping thoughts into /inbox — I'll help you process and organize them with /reflect."

Category context

Agent frameworks, memory systems, reasoning layers, and model-native orchestration.

Source: Tencent SkillHub

Largest current source with strong distribution and engagement signals.

Package contents

Included in package

1 Docs

SKILL.md Primary doc