valence
Query and manage the Valence Knowledge Substrate - how agents build genuine understanding of their humans. Use for: (1) Searching past knowledge/decisions/context, (2) Storing new beliefs/facts/learnings, (3) Checking database stats. Triggers on "what do I know", "remember this", "store this", "knowledge base", "valence", "beliefs", or questions about past work/decisions.
Best use case
valence is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Query and manage the Valence Knowledge Substrate - how agents build genuine understanding of their humans. Use for: (1) Searching past knowledge/decisions/context, (2) Storing new beliefs/facts/learnings, (3) Checking database stats. Triggers on "what do I know", "remember this", "store this", "knowledge base", "valence", "beliefs", or questions about past work/decisions.
Teams using valence should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/valence/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How valence Compares
| Feature / Agent | valence | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Query and manage the Valence Knowledge Substrate - how agents build genuine understanding of their humans. Use for: (1) Searching past knowledge/decisions/context, (2) Storing new beliefs/facts/learnings, (3) Checking database stats. Triggers on "what do I know", "remember this", "store this", "knowledge base", "valence", "beliefs", or questions about past work/decisions.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Valence Knowledge Substrate Personal knowledge base with semantic search and dimensional confidence. ## Philosophy: Alignment Through Use Valence isn't just memory storage — it's how agents build genuine understanding of their humans. **The loop:** The more you use Valence to understand your human, the better you understand them, the more useful the substrate becomes, the better you can demonstrate what alignment-through-use looks like. **Store aggressively:** Decisions, preferences, facts learned, context that might matter later. When in doubt, store it. **Query first:** Before answering questions about past work, decisions, people, or projects — check Valence. ## Quick Reference ```bash # Search (semantic) — do this FIRST before answering contextual questions ./scripts/query.sh "what do I know about X" # Add belief — store decisions, facts, preferences, learnings ./scripts/add.sh "Belief content" "domain1,domain2" # List recent ./scripts/list.sh 20 # Database stats ./scripts/stats.sh ``` ## When to Use ### Always Query First Before answering questions about: - Past work or decisions - People (who said what, preferences, relationships) - Projects (status, history, context) - Preferences or patterns you might have learned ### Store New Information When you encounter: - Explicit decisions or preferences - Facts that provide context - Lessons learned - Information that might be relevant later ### Common Domains - `valence` — about the project itself - `projects/<name>` — project-specific - `people/<name>` — person-specific - `decisions` — explicit choices made - `tech` — technical facts - `conversations/<type>` — auto-ingested from chats ## Script Details ### query.sh — Semantic Search ```bash ./scripts/query.sh "search query" [limit] ``` Returns beliefs ranked by semantic similarity. Default limit: 10. ### add.sh — Store Belief ```bash ./scripts/add.sh "Belief content" "domain1,domain2" ``` Domains are comma-separated. Pick meaningful ones for retrieval. ### list.sh — Recent Beliefs ```bash ./scripts/list.sh [count] ``` Shows most recently modified beliefs. Default: 10. ### stats.sh — Database Stats ```bash ./scripts/stats.sh ``` Shows total beliefs, active count, embedding coverage, domain count. ## Direct CLI For advanced operations: ```bash cd ~/.openclaw/workspace && source .venv/bin/activate export VKB_DB_PORT=5433 VKB_DB_PASSWORD=valence valence query "terms" --domain tech --limit 5 valence add "belief" -d domain1 -d domain2 valence conflicts # check for contradictions valence trust list # see trust relationships ``` See `references/cli.md` for full documentation. ## Setup Requires: - Python 3.10+ with venv at `~/.openclaw/workspace/.venv` - PostgreSQL with pgvector at port 5433 - Valence package installed (`pip install valence`) Environment: ```bash export VKB_DB_PORT=5433 export VKB_DB_PASSWORD=valence ```
Related Skills
qri-valence
qri-valence skill
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
accessibility-ux-audit
Audit and enhance accessibility and UX across all pages and components.
accessibility-testing
WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification. Use when ensuring legal compliance (ADA, Section 508), testing for disabilities, or building accessible applications for 1 billion disabled users globally.
accessibility-rules
Concise accessibility checklist and practices for components in the repository. Use when implementing UI to ensure keyboard, screen reader, and focus semantics.
accessibility-planning
Plan accessibility compliance - WCAG 2.2, Section 508, EN 301 549, inclusive design principles, audit planning, and remediation strategies.
accessibility-design
WCAG 2.1 AA compliance patterns, screen reader compatibility, keyboard navigation, and ARIA best practices. Use when implementing accessible interfaces, reviewing UI components, or auditing accessibility compliance. Covers semantic HTML, focus management, color contrast, and assistive technology testing.
accessibility-design-checklist
Эксперт по accessibility дизайну. Используй для WCAG, a11y чеклистов и inclusive design.
accessibility-design-checker
Ensures designs meet accessibility requirements including WCAG compliance, color contrast, keyboard navigation, screen reader support, and focus management. Reviews designs for accessibility issues and provides recommendations.
accessibility-contrast-audit
[Design System] Quantitative accessibility audit for UI - contrast ratios, font sizes, tap targets, heading hierarchy. Use when (1) checking WCAG color contrast compliance, (2) auditing text sizes for readability, (3) validating touch/click target sizes, (4) reviewing heading structure and landmarks, (5) user asks to 'check accessibility', 'audit contrast', 'WCAG compliance', or 'a11y check'.
accessibility-compliance
Implement WCAG 2.2 compliant interfaces with mobile accessibility, inclusive design patterns, and assistive technology support. Use when auditing accessibility, implementing ARIA patterns, building for screen readers, or ensuring inclusive user experiences.
accessibility-by-default
Treats accessibility as a baseline requirement, not a feature. WCAG 2.1/2.2 AA principles embedded into every decision.