# Send Mlscp 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": "mlscp",
    "name": "Mlscp",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/sirkrouph-dev/mlscp",
    "canonicalUrl": "https://clawhub.ai/sirkrouph-dev/mlscp",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/mlscp",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mlscp",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "mlscp",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-02T10:47:15.758Z",
      "expiresAt": "2026-05-09T10:47:15.758Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mlscp",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mlscp",
        "contentDisposition": "attachment; filename=\"mlscp-0.1.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "mlscp"
      },
      "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/mlscp"
    },
    "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/mlscp",
    "downloadUrl": "https://openagent3.xyz/downloads/mlscp",
    "agentUrl": "https://openagent3.xyz/skills/mlscp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mlscp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mlscp/agent.md"
  }
}
```
## Documentation

### MLSCP Skill

MLSCP (Micro LLM Swarm Communication Protocol) is a token-efficient command language for agent-to-agent communication. This skill lets you parse, validate, and generate MLSCP commands without any LLM overhead.

### Why Use MLSCP?

Natural LanguageMLSCPSavings"Please modify the file src/chain_orchestrator.py by adding retry logic at line 47"F+ s/co > ln47 + 'retry logic'~75%"Read the contents of utils/file_manager.py from lines 10 to 50"F? u/fm > ln10-50~80%"Delete the variable 'temp_cache' from config.py"V- c/c > 'temp_cache'~70%

### Parse a Command

./scripts/mlscp.sh parse "F+ s/co > ln47 + 'retry logic'"

### Validate Syntax

./scripts/mlscp.sh validate "F+ s/co > ln47 + 'retry logic'"

### Generate Vocabulary

./scripts/mlscp.sh vocab /path/to/project

### Compress Natural Language

./scripts/mlscp.sh compress "Add error handling to the main function in app.py"

### Operations

CodeMeaningExampleF+File add/insertF+ s/app > ln10 + 'new code'F~File modifyF~ s/app > ln10-20 ~ 'updated code'F-File deleteF- s/app > ln10-15F?File query/readF? s/app > ln1-100V+Variable addV+ s/app + 'new_var = 42'V~Variable modifyV~ s/app > 'old_var' ~ 'new_value'V-Variable deleteV- s/app > 'temp_var'V?Variable queryV? s/app > 'config_*'

### Location Specifiers

ln47 - Single line
ln10-50 - Line range
fn:main - Function name
cls:MyClass - Class name

### Context Blocks

CTX{"intent":"resilience","priority":"high","confidence":0.9}

### Scripts

mlscp.sh - Main CLI tool
vocab.py - Vocabulary generator (Python)

### With Other Agents

When receiving commands from MLSCP-enabled agents:

./scripts/mlscp.sh parse "$INCOMING_COMMAND"

### Sending Commands

Generate compact commands for other agents:

./scripts/mlscp.sh compress "Your natural language instruction"

### API (Python)

from mlscp import parse, MLSCPParser

# Quick parse
cmd = parse("F+ s/co > ln47 + 'retry logic'")
print(cmd.operation)  # OperationType.FILE_ADD
print(cmd.target)     # "s/co"

# With vocabulary
parser = MLSCPParser(vocab_lookup)
cmd = parser.parse("F+ s/co > ln47 + 'code'")
full_path = vocab_lookup.get("s/co")  # "src/chain_orchestrator.py"

### Resources

GitHub: https://github.com/sirkrouph-dev/mlcp
Grammar Spec: See references/grammar.abnf
Protocol Definition: See references/protocol.md
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: sirkrouph-dev
- Version: 0.1.0
## 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: 2026-05-02T10:47:15.758Z
- Expires at: 2026-05-09T10:47:15.758Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/mlscp)
- [Send to Agent page](https://openagent3.xyz/skills/mlscp/agent)
- [JSON manifest](https://openagent3.xyz/skills/mlscp/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/mlscp/agent.md)
- [Download page](https://openagent3.xyz/downloads/mlscp)