Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
Predicate Snapshot
ML-powered DOM pruning for 95% smaller browser prompts
skill openclawclawhub Free
ML-powered DOM pruning for 95% smaller browser prompts
β¬ 0 downloads β
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.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- README.md, SKILL.md, demo/compare.ts, demo/llm-action.ts, demo/login-demo.ts, docker-compose.yml
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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 0.4.0
Provenance
- Publisher
- rcholic
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Predicate Snapshot Engine
Replaces default browser snapshots with Predicate's ML-ranked DOM elements. Reduces prompt token usage by 95% while preserving actionable elements.
Why Use This?
ApproachTokensElementsSignal QualityAccessibility Tree (default)~18,000~800Low (noise)Predicate Snapshot~80050High (ranked) Result: Faster LLM inference, lower costs, fewer retries.
Requirements
Node.js 18+ PREDICATE_API_KEY environment variable (optional) Without API key: Local heuristic-based pruning (~80% token reduction) With API key: ML-powered ranking for cleaner output (~95% token reduction, less noise) Get your free API key at predicate.systems/keys
Installation
npx clawdhub@latest install predicate-snapshot Or manually: git clone https://github.com/predicate-systems/predicate-snapshot-skill ~/.openclaw/skills/predicate-snapshot cd ~/.openclaw/skills/predicate-snapshot && npm install && npm run build
Configuration
For enhanced ML-powered ranking, set your API key: export PREDICATE_API_KEY="sk-..." Or configure in ~/.openclaw/config.yaml: skills: predicate-snapshot: api_key: "sk-..." # Optional: set usage limits max_credits_per_session: 100
/predicate-snapshot
Capture a pruned DOM snapshot optimized for LLM consumption. /predicate-snapshot [--limit=50] [--include-ordinal] Options: --limit=N - Maximum elements to return (default: 50) --include-ordinal - Include ordinal ranking for list items Output format: ID|role|text|imp|is_primary|docYq|ord|DG|href 42|button|Add to Cart|0.95|true|320|1|cart-actions| 15|button|Buy Now|0.92|true|340|2|cart-actions| 23|link|Product Details|0.78|false|400|0||/dp/...
/predicate-act
Execute an action on an element by its Predicate ID. /predicate-act <action> <element_id> [value] Examples: # Click element 42 /predicate-act click 42 # Type into element 15 /predicate-act type 15 "search query" # Scroll to element 23 /predicate-act scroll 23
/predicate-snapshot-local
Local-only snapshot without ML re-ranking (free, lower accuracy). /predicate-snapshot-local [--limit=50] Use this for development or when you don't need ML-powered ranking.
Example Workflow
1. Navigate to page 2. /predicate-snapshot # Get ranked elements 3. /predicate-act click 42 # Click "Add to Cart" (element 42) 4. /predicate-snapshot # Refresh snapshot 5. Verify cart updated
Pricing
TierCredits/MonthPriceHobby500FreeBuilder20,000$19/moPro40,000$49/moTeams120,000$149/moEnterpriseCustomContact us Each snapshot consumes 1 credit. Local snapshots are free.
Comparison: Before & After
Before (Accessibility Tree): @e1 navigation "Skip to main content" @e2 link "Amazon" @e3 search "Search Amazon" ... (800+ elements) @e742 button "Add to Cart" <-- buried in noise ... (more elements) After (Predicate Snapshot): ID|role|text|imp|is_primary|docYq|ord|DG|href 42|button|Add to Cart|0.98|true|520|1|cart-actions| <-- ranked #1 15|button|Buy Now|0.95|true|540|2|cart-actions| 23|link|See All Buying...|0.72|false|560|3|cart-actions|
Support
Documentation: predicatesystems.ai/docs Issues: GitHub Issues Discord: Predicate Community
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
3 Scripts2 Docs1 Config
- SKILL.md
- README.md
- demo/compare.ts
- demo/llm-action.ts
- demo/login-demo.ts
- docker-compose.yml