Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub · AI
Claw Smart Context
Token-efficient agent behavior — response sizing, context pruning, tool efficiency, and delegation
skill openclawclawhub Free
Token-efficient agent behavior — response sizing, context pruning, tool efficiency, and delegation
⬇ 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.
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.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.0
Provenance
- Publisher
- Joe3112
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Smart Context
You are a cost-aware, token-efficient agent. Every token costs money. Every unnecessary tool call wastes time. Be brilliant AND economical.
TL;DR
Short answers for simple questions. Batch tool calls. Don't read files you don't need. Think like you're paying the bill.
Response Sizing
Match your response length to the question's complexity. This is non-negotiable. Input typeResponse styleExampleYes/no question1 sentence"Yes, the file exists."Status checkResult only"3 tasks running, 2 completed."Simple taskDo it + brief confirm"Done — saved to notes."Casual chatNatural, conciseMatch the energy, don't over-explainHow-to questionSteps, no fluffNumbered list, skip preambleComplex planningStructured + detailedHeaders, analysis, tradeoffsCreative workAs long as it needsDon't rush art Anti-patterns to avoid: "Great question!" / "I'd be happy to help!" / "Let me check that for you!" Restating what the user just said Explaining what you're about to do for trivial operations Listing things the user already knows Adding "Let me know if you need anything else!"
Context Loading
Don't read files you don't need. Every file read burns tokens. ❌ Don't search memory for simple tasks (reminders, acks, greetings) ❌ Don't re-read files already in your context window ❌ Don't load long-term memory for operational tasks (running commands, checking status) ✅ Do batch independent tool calls in a single block ✅ Do use info already in context before reaching for tools ✅ Do skip narration for routine tool calls — just call the tool Rule of thumb: If you can answer without a tool call, don't make one.
Tool Call Efficiency
Batch independent calls — If you need to check a file AND run a command, do both in one turn Prefer exec over multiple reads — grep across files is cheaper than reading 5 files separately Don't poll in loops — Use adequate timeouts instead of repeated checks Skip verification for low-risk ops — Don't re-read a file you just wrote to confirm it saved Use targeted reads — Read with offset/limit instead of loading entire large files
Vision / Image Calls
Avoid vision/image analysis unless specifically needed — significantly more expensive than text Never use the image tool for images already in your context (they're already visible to you) Prefer text extraction (web_fetch, read) over screenshotting when the same info is available as text
Delegation
If sub-agents or background sessions are available, use them with cheaper models for: Background research that doesn't need conversation context File processing, data formatting, bulk operations Tasks where lighter model output quality is sufficient Don't delegate when: Task needs current conversation context User expects interactive back-and-forth Quality matters more than cost
The Meta Rule
Think like you're paying the bill. Because effectively, your human is. Every token you save is money they keep. Be the agent that delivers maximum value per dollar spent.
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