# Send Claw Smart Context to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- 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.
## Suggested prompts
### New install

```text
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

```text
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.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "claw-smart-context",
    "name": "Claw Smart Context",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Joe3112/claw-smart-context",
    "canonicalUrl": "https://clawhub.ai/Joe3112/claw-smart-context",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/claw-smart-context",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claw-smart-context",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "claw-smart-context",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T09:22:03.026Z",
      "expiresAt": "2026-05-07T09:22:03.026Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claw-smart-context",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claw-smart-context",
        "contentDisposition": "attachment; filename=\"claw-smart-context-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "claw-smart-context"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/claw-smart-context"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/claw-smart-context",
    "downloadUrl": "https://openagent3.xyz/downloads/claw-smart-context",
    "agentUrl": "https://openagent3.xyz/skills/claw-smart-context/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claw-smart-context/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claw-smart-context/agent.md"
  }
}
```
## 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.
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: Joe3112
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-04-30T09:22:03.026Z
- Expires at: 2026-05-07T09:22:03.026Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/claw-smart-context)
- [Send to Agent page](https://openagent3.xyz/skills/claw-smart-context/agent)
- [JSON manifest](https://openagent3.xyz/skills/claw-smart-context/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/claw-smart-context/agent.md)
- [Download page](https://openagent3.xyz/downloads/claw-smart-context)