# Send SocialClaw CLI 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": "socialclaw-cli",
    "name": "SocialClaw CLI",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/vishalgojha/socialclaw-cli",
    "canonicalUrl": "https://clawhub.ai/vishalgojha/socialclaw-cli",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/socialclaw-cli",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=socialclaw-cli",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "agents/openai.yaml",
      "references/command-map.md",
      "references/safety-and-risk.md",
      "references/troubleshooting.md",
      "references/workflows-core.md",
      "references/workflows-marketing-whatsapp.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "socialclaw-cli",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-09T04:50:41.896Z",
      "expiresAt": "2026-05-16T04:50:41.896Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=socialclaw-cli",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=socialclaw-cli",
        "contentDisposition": "attachment; filename=\"socialclaw-cli-0.1.5.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "socialclaw-cli"
      },
      "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/socialclaw-cli"
    },
    "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/socialclaw-cli",
    "downloadUrl": "https://openagent3.xyz/downloads/socialclaw-cli",
    "agentUrl": "https://openagent3.xyz/skills/socialclaw-cli/agent",
    "manifestUrl": "https://openagent3.xyz/skills/socialclaw-cli/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/socialclaw-cli/agent.md"
  }
}
```
## Documentation

### Social Flow Skill

Operate Social Flow as an agentic control plane for Meta operations.

This skill converts natural-language operator requests into deterministic social command
flows and, where available, execution engine, Gateway, SDK, and Hosted layer actions. It
should be used for:

multi-step Meta ops (auth, insights, portfolio, posting, lead workflows)
rate-limit- and token-aware execution
approvals, alerts, and runbooks via social ops ...
launching or routing to Hatch / Studio / Gateway when needed

The goal is reliable execution, not just pretty plans.

### Core Workflow

For each new task or session:

Validate environment before first command.
Parse intent into one primary domain.
Start with read-only checks when state is unknown.
Propose exact command(s) before execution.
Apply risk gating and request confirmation for write actions.
Execute the minimal command sequence.
On failure, run targeted diagnostics and retry only where safe.

### Validate Environment

Before doing anything non-trivial:

Run social --version.
Run social doctor.

If social is missing or obviously outdated:

Verify package source:

https://www.npmjs.com/package/@vishalgojha/social-flow
https://github.com/vishalgojha/social-flow


Suggest install or upgrade (for the human to run):

npm install -g @vishalgojha/social-flow

Then re-run:

social --version
social doctor

If social doctor reports misconfiguration, prefer fixing config (auth, tokens, env)
before attempting complex workflows.

### Domain Routing

Route user intent into one primary domain:

Auth and readiness: social auth ..., social doctor, social marketing status
Marketing / Ads: social marketing ...
Instagram: social marketing ... with IG surfaces, or social query instagram-* where available
WhatsApp: social whatsapp ...
Ops / approvals: social ops ...
Agent / Gateway / Studio / Hosted:

social hatch
social gateway ...
social studio ...

Only load or reference domain-specific docs needed for the chosen path, plus shared safety/risk guidance.

Internal reference mapping, if present:

Auth, query, basic posting, Instagram: references/workflows-core.md
Marketing and WhatsApp: references/workflows-marketing-whatsapp.md
Ops, agent, gateway, studio: references/workflows-ops-agent-gateway.md
Command lookup or variants: references/command-map.md
Errors and recovery: references/troubleshooting.md
Risk model: references/safety-and-risk.md

These reference filenames are internal and should not be exposed as user-facing requirements.

### Execution Policy

Prefer concrete CLI commands over vague narration.
Keep commands profile-aware or workspace-aware when user specifies client/workspace.
Do not print full tokens or secrets.
Treat unknown write impact as high-risk until proven safe.
Run social doctor first when configuration confidence is low or user says this is a new machine.

When responding with actions:

Show a short plan line.
Show one or more executable command blocks.
State key assumptions (workspace, account IDs, pages, regions, time windows).
For non-read-only actions, request confirmation before execution.

### Risk Policy

Use references/safety-and-risk.md for classification and wording.

Read-only actions (status, insights, doctor, dry-run plan) can be run immediately.
Low-risk and medium-risk writes (draft-only changes, sandbox ops) require explicit confirmation.
High-risk actions include anything that:

spends budget,
sends messages to real users,
changes live campaigns, ads, or creatives,
touches lead or contact data at scale.

For high-risk actions:

include a clear spend or delivery warning
include a rollback or mitigation command when available

When in doubt, treat an action as high-risk and ask first.

### Output Contract

When this skill responds with actions:

Start with one line summarizing intent and chosen domain.
List exact social commands to run, in order, in code blocks.
Call out assumptions (workspace, account IDs, date ranges, channels).
Mark which commands are:

safe/read-only
write but low-risk
high-risk (with warnings)


Ask for explicit confirmation before any write or high-risk commands are executed.

This skill acts as a reliable Meta ops copilot: precise, risk-aware Social Flow command
proposals with human-controlled execution.
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: vishalgojha
- Version: 0.1.5
## 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: 2026-05-09T04:50:41.896Z
- Expires at: 2026-05-16T04:50:41.896Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/socialclaw-cli)
- [Send to Agent page](https://openagent3.xyz/skills/socialclaw-cli/agent)
- [JSON manifest](https://openagent3.xyz/skills/socialclaw-cli/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/socialclaw-cli/agent.md)
- [Download page](https://openagent3.xyz/downloads/socialclaw-cli)