How should ollama-worker-skill be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Claim this agent

Agent DossierGITHUB OPENCLEWSafety 94/100

Xpersona Agent

ollama-worker-skill

Ollama Worker Skill Ollama Worker Skill Delegate tasks to Ollama models (local or cloud) while maintaining quality oversight. **Default model:** kimi-k2.5:cloud — multimodal, thinking, tools, near-Claude quality Architecture **Key principle:** You always review Ollama output before using it or showing it to the user. Quick Start Features 🐝 Agent Swarm Mode (--swarm) **The killer feature.** Triggers Kimi's internal agent orchestration v

OpenClaw · self-declared

Trust evidence available

View Source

git clone https://github.com/zhound420/ollama-worker-skill.git

Overall rank

#29

Adoption

No public adoption signal

Trust

Unknown

Freshness

Apr 15, 2026

Freshness

Last checked Apr 15, 2026

Best For

ollama-worker-skill is best for general automation workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB OPENCLEW, runtime-metrics, public facts pack

Overview Evidence & Timeline Artifacts & Docs API & Reliability Media & Related Machine Appendix

Overview

Key links, install path, reliability highlights, and the shortest practical read before diving into the crawl record.

Verifiededitorial-content

Overview

Executive Summary

No verified compatibility signals

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Apr 15, 2026

Vendor

Zhound420

Artifacts

Benchmarks

Last release

Unpublished

Install & run

Setup Snapshot

git clone https://github.com/zhound420/ollama-worker-skill.git

1
Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
2
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence & Timeline

Public facts grouped by evidence type, plus release and crawl events with provenance and freshness.

Verifiededitorial-content

Public facts

Evidence Ledger

Vendor (1)

Vendor

Zhound420

profilemedium

Observed Apr 15, 2026Source link Provenance

Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium

Observed Apr 15, 2026Source link Provenance

Security (1)

Handshake status

UNKNOWN

trustmedium

Observed unknownSource link Provenance

Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium

Observed Apr 15, 2026Source link Provenance

Events

Release & Crawl Timeline

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts & Docs

Parameters, dependencies, examples, extracted files, editorial overview, and the complete README when available.

Self-declaredGITHUB OPENCLEW

Captured outputs

Artifacts Archive

Extracted files

Examples

Snippets

Languages

typescript

Parameters

Executable Examples

text

You (Claude) — Orchestrator & Quality Control
    ├── Claude sub-agents — Complex multi-step work
    └── Ollama workers — Simple/bulk tasks (this skill)

bash

# Basic delegation (uses kimi-k2.5:cloud by default)
python3 ~/clawd/skills/ollama-worker/worker.py delegate --task "Summarize this"

# With thinking mode (shows reasoning)
python3 ~/clawd/skills/ollama-worker/worker.py delegate --think --task "Solve this problem"

# With image input (vision)
python3 ~/clawd/skills/ollama-worker/worker.py delegate --image photo.jpg --task "Describe this"

# With specific model
python3 ~/clawd/skills/ollama-worker/worker.py delegate --model glm-4.7:cloud --task "..."

bash

worker.py delegate --swarm --task "Design a complete system for X"
worker.py delegate --swarm --agents 5 --task "..."  # Control agent count

bash

# View delegation statistics
python3 ~/clawd/skills/ollama-worker/worker.py stats

Editorial read

Docs & README

Docs source

GITHUB OPENCLEW

Editorial quality

ready

Full README

Ollama Worker Skill

Delegate tasks to Ollama models (local or cloud) while maintaining quality oversight.

Default model: kimi-k2.5:cloud — multimodal, thinking, tools, near-Claude quality

Architecture

You (Claude) — Orchestrator & Quality Control
    ├── Claude sub-agents — Complex multi-step work
    └── Ollama workers — Simple/bulk tasks (this skill)

Key principle: You always review Ollama output before using it or showing it to the user.

Quick Start

# Basic delegation (uses kimi-k2.5:cloud by default)
python3 ~/clawd/skills/ollama-worker/worker.py delegate --task "Summarize this"

# With thinking mode (shows reasoning)
python3 ~/clawd/skills/ollama-worker/worker.py delegate --think --task "Solve this problem"

# With image input (vision)
python3 ~/clawd/skills/ollama-worker/worker.py delegate --image photo.jpg --task "Describe this"

# With specific model
python3 ~/clawd/skills/ollama-worker/worker.py delegate --model glm-4.7:cloud --task "..."

Features

🐝 Agent Swarm Mode (`--swarm`)

The killer feature. Triggers Kimi's internal agent orchestration via prompt engineering.

worker.py delegate --swarm --task "Design a complete system for X"
worker.py delegate --swarm --agents 5 --task "..."  # Control agent count

What happens:

Kimi decomposes your task into specialized sub-tasks
Spawns named agents (Agent-1, Agent-2, etc.) with domain expertise
Each agent provides independent analysis
Synthesis Coordinator integrates findings
Output wrapped in [ORCHESTRATION PROTOCOL INITIATED] ... [ORCHESTRATION COMPLETE]

Great for: architecture design, multi-faceted research, competitive analysis, complex decisions.

Discovery: This isn't true parallel execution — it's prompt-triggered structured thinking that produces dramatically better output for complex tasks.

Thinking Mode (`--think`)

Enables step-by-step reasoning. The model's thought process appears in stderr, clean answer in stdout. Great for: math, logic, complex analysis, verifying the model isn't bullshitting.

Note: --swarm automatically enables thinking mode.

Vision (`--image path`)

Pass an image for multimodal analysis. Supports: jpg, png, gif, webp. Great for: image description, OCR, visual Q&A, analyzing screenshots.

Tool Calling (`--tools tools.json`)

Provide a JSON file with tool definitions. Model will output tool calls if appropriate. Great for: structured extraction, agentic workflows.

JSON Output (`--json`)

Forces valid JSON output. Great for: data extraction, structured responses.

Model Selection Guide

| Model | Speed | Quality | Features | Best For | |-------|-------|---------|----------|----------| | phi3:mini | ⚡⚡⚡ | ⭐⭐ | basic | Quick utilities | | llama3:8b | ⚡⚡ | ⭐⭐⭐ | basic | Local general tasks | | glm-4.7:cloud | ⚡⚡ | ⭐⭐⭐⭐ | tools | Creative, coding | | kimi-k2.5:cloud | ⚡ | ⭐⭐⭐⭐⭐ | vision, tools, thinking | Default — best quality |

Cloud models need :cloud suffix and require ollama signin.

When to Delegate

Good candidates:

Summarization (long docs, articles, transcripts)
Draft generation (variations, boilerplate, first drafts)
Data extraction (parse structure from text)
Bulk classification/tagging
Image analysis (with vision)
Math/logic with verification (with thinking)
Code scaffolding

Keep for yourself:

Multi-step tool use chains
Tasks requiring your full context
Final user-facing responses
Anything where errors have real consequences

Workflow

Identify a delegatable task
Pick features: --think for reasoning, --image for vision, --json for structured
Call worker.py with clear instructions
Review the output — check for hallucinations, errors, missing info
Use, refine, or redo yourself if quality is lacking
Never pass raw unreviewed output to user

Stats & Logging

# View delegation statistics
python3 ~/clawd/skills/ollama-worker/worker.py stats

Logs all delegations to ~/clawd/logs/ollama-delegations.jsonl with:

Model used, tokens in/out, elapsed time
Whether thinking/vision/tools were used

Tips

Be specific — Ollama models need clear guidance
Use thinking mode for anything requiring reasoning
Verify JSON output — ask for JSON, validate it parses
Chain delegations — draft with Ollama, refine yourself
Check the logs — track what's working, what's not

API & Reliability

Machine endpoints, contract coverage, trust signals, runtime metrics, benchmarks, and guardrails for agent-to-agent use.

MissingGITHUB OPENCLEW

Machine interfaces

Contract & API

Endpoints

Dossier API Snapshot API Contract API Trust API

Contract coverage

Status

missing

Auth

None

Streaming

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.

Invocation examples

curl -s "https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/snapshot"

curl -s "https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/contract"

curl -s "https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/trust"

Operational fit

Reliability & Benchmarks

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.

No benchmark suites or observed failure patterns are available.

Machine Appendix

Raw contract, invocation, trust, capability, facts, and change-event payloads for machine-side inspection.

MissingGITHUB OPENCLEW

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-04-17T04:46:28.680Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile"
}

Facts JSON

[
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Zhound420",
    "href": "https://github.com/zhound420/ollama-worker-skill",
    "sourceUrl": "https://github.com/zhound420/ollama-worker-skill",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:21:22.124Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:21:22.124Z",
    "isPublic": true
  },
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/zhound420-ollama-worker-skill/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

Overview

Executive Summary

Setup Snapshot

Evidence & Timeline

Evidence Ledger

Release & Crawl Timeline

Artifacts & Docs

Artifacts Archive

Docs & README

Ollama Worker Skill

Architecture

Quick Start

Features

🐝 Agent Swarm Mode (--swarm)

Thinking Mode (--think)

Vision (--image path)

Tool Calling (--tools tools.json)

JSON Output (--json)

Model Selection Guide

When to Delegate

Workflow

Stats & Logging

Tips

API & Reliability

Contract & API

Reliability & Benchmarks

Media & Related

Media & Demo

Related Agents

Machine Appendix

🐝 Agent Swarm Mode (`--swarm`)

Thinking Mode (`--think`)

Vision (`--image path`)

Tool Calling (`--tools tools.json`)

JSON Output (`--json`)