Agent skill

Task Queue By Model Source

by LeoYeAI in LeoYeAI/openclaw-master-skills

Multi-queue task orchestration system. An agent skill from LeoYeAI/openclaw-master-skills.

MITAuto-check passedBackend & APIs

Install Task Queue By Model Source

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill task-queue-by-model-source -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills task-queue-by-model-source --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/model-queue .claude/skills/task-queue-by-model-source && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
task-queue-by-model-source
GitHub stars
2.2k
Token cost
~4.2k tokens
SKILL.md length
789 words
Files
5
Skills in repo
1,215
Repo updated
First seen
Licence
MIT

At a glance

Multi-queue task orchestration system. An agent skill from LeoYeAI/openclaw-master-skills.

  • Works in 12 steps: First Run Setup → Parse User Message → Handle Control Commands → …
  • Tasks that involve Background jobs
  • SKILL.md covers Core Concepts, Task Object Schema, Task Statuses and Two Operating Modes, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Task Queue By Model Source is an agent skill from LeoYeAI/openclaw-master-skills. Multi-queue task orchestration system. Tasks are routed to queues by model source, with support for task dependencies, context passing, and failure handling. Each model source has its own FIFO queue, executing one task at a time.

Its SKILL.md is about 4.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `STATUS.json`, `_meta.json` and `queue-schema.md`).

It sits in Backend & APIs, covering Background jobs. It works with Ollama. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • Tasks that involve Background jobs

Example prompts

  • “/task-queue-by-model-source”

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. First Run Setup
  2. Parse User Message
  3. Handle Control Commands
  4. Determine Model Source
  5. Determine Dependencies
  6. Assign Task ID
  7. Build Task Object
  8. Append to Queue
  9. Confirm to User
  10. Run DISPATCHER
  11. Scan All Queue Files
  12. Check Running Tasks

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Task Queue By Model Source loads about 4.2k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 789 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~4.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 789 words, ~4,216 tokens.

Download SKILL.mdSave it as .claude/skills/task-queue-by-model-source/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
task-queue-by-model-source
description
Multi-queue task orchestration system. Tasks are routed to queues by model source, with support for task dependencies, context passing, and failure handling. Each model source has its own FIFO queue, executing one task at a time.
metadata.author
openclaw
metadata.version
1.0.0
metadata.tier
general

Model Queue Skill

A multi-queue task orchestration system where tasks are routed to queues based on their target model source. Supports task dependencies, context passing between tasks, and configurable failure handling.


Core Concepts

Model Source Mapping

Models are grouped by their underlying source (e.g., local Ollama, remote Ollama, cloud API). All tasks targeting models on the same source share a single queue.

Configuration in TOOLS.md:

MODEL_SOURCE_OLLAMA_LOCAL=ollama/llama3,ollama/qwen2.5,ollama/mistral
MODEL_SOURCE_OLLAMA_REMOTE=ollama-remote/qwen3.5:27b,ollama-remote/llama3:70b
MODEL_SOURCE_CLOUD_NVIDIA=nvidia/z-ai/glm5,nvidia/llama3
Queue Isolation

Each model source has its own queue file:

  • ${MODEL_QUEUES_DIR}/ollama-local.json
  • ${MODEL_QUEUES_DIR}/ollama-remote.json

Queues are independent — a blocked task in one queue doesn't affect other queues.


Task Object Schema

json
{
  "id": "T-001",
  "queue": "ollama-local",
  "model": "ollama/qwen2.5",
  "description": "Analyze the sales data",
  "goal": "Generate a summary of Q1 sales performance",
  "status": "pending",
  "priority": 0,
  "depends_on": null,
  "on_depends_fail": "block",
  "context_input": null,
  "result": null,
  "result_status": null,
  "result_summary": null,
  "retries": 0,
  "maxRetries": 3,
  "subagent_session": null,
  "added_at": "2026-03-04T16:51:00Z",
  "started_at": null,
  "completed_at": null
}

Task Statuses

StatusDescription
pendingReady to be dispatched (no dependencies or resolved)
waitingHas dependency, waiting for it to complete
runningCurrently executing via subagent
doneCompleted successfully
failedFailed after max retries
blockedDependency failed, waiting for user action
skippedSkipped by user or due to dependency failure

Two Operating Modes

ModeTriggerPurpose
INTAKEUser message containing task intentParse message → route to queue → confirm → immediately run DISPATCHER
DISPATCHERAfter INTAKE (primary) · Heartbeat/cron (backup)Check queues → dispatch pending tasks → report completions

A1 — Triggers

Model Source Configuration

REQUIRED: Configure model sources in TOOLS.md before first use.

Add to your TOOLS.md:

markdown
## Model Queue Configuration

MODEL_QUEUES_DIR=~/.openclaw/model-queues/
MODEL_QUEUE_MAX_RETRIES=3
MODEL_QUEUE_ARCHIVE_DAYS=7

# Model Source Mappings (REQUIRED)
# Format: MODEL_SOURCE_{NAME}=model1,model2,model3
MODEL_SOURCE_OLLAMA_LOCAL=ollama/llama3,ollama/qwen2.5,ollama/mistral
MODEL_SOURCE_OLLAMA_REMOTE=ollama-remote/qwen3.5:27b,ollama-remote/llama3:70b
MODEL_SOURCE_CLOUD_NVIDIA=nvidia/z-ai/glm5,nvidia/llama3

# Default model source when not specified (optional)
DEFAULT_MODEL_SOURCE=ollama-remote
How Model Source is Determined
  1. Explicit model: User says "用 qwen2.5 分析..." → find qwen2.5's source
  2. Explicit source: User says "send to remote..." → use default model for that source
  3. No specification: Use DEFAULT_MODEL_SOURCE, or ask user
INTAKE Triggers

Activate INTAKE mode when user message matches:

PatternExamples
Explicit task"add task", "new task", "queue this"
Delegation"do this for me", "handle this"
Model-specific"用 qwen3.5 分析这个", "用远程模型处理"
Dependency"然后", "after that", "next"
Status check"task status", "show queue", "队列状态"
Control"cancel T-001", "retry T-002", "skip T-003"

Do NOT activate INTAKE for:

  • Simple one-sentence questions
  • Pure scheduling requests without tasks
  • Single web searches
DISPATCHER Triggers
  • Immediately after INTAKE (primary path)
  • HEARTBEAT.md check during heartbeat poll (backup)
  • systemEvent: "MODEL_QUEUE_DISPATCH: check queues and run pending tasks" (backup)

Mode 1: INTAKE — Step-by-Step

Step 0 — First Run Setup

Run this check before anything else, every INTAKE invocation:

CHECK whether ${MODEL_QUEUES_DIR}/ exists and has queue files
IF no queue files exist:
  → This is the first run. Auto-configure.
  
  [1] Create directory:
      exec: mkdir -p ${MODEL_QUEUES_DIR}
  
  [2] For each MODEL_SOURCE_* in TOOLS.md:
      CREATE ${MODEL_QUEUES_DIR}/{source_name}.json:
      {
        "version": "1.0",
        "source": "{source_name}",
        "models": [list of models],
        "maxConcurrent": 1,
        "maxRetries": ${MODEL_QUEUE_MAX_RETRIES},
        "lastId": null,
        "tasks": []
      }
  
  [3] Register heartbeat entry:
      READ HEARTBEAT.md
      IF "Model Queue Dispatcher" NOT in file:
        APPEND:
        ## Model Queue Dispatcher
        Every heartbeat: check ${MODEL_QUEUES_DIR} for pending/running tasks
        - If tasks exist → run DISPATCHER mode
        - If nothing pending → HEARTBEAT_OK
  
  [4] Register backup cron job:
      CALL cron tool:
        action: "add"
        job:
          name: "Model Queue Dispatcher"
          schedule: { kind: "every", everyMs: 900000 }
          payload: { kind: "systemEvent", text: "MODEL_QUEUE_DISPATCH: check queues and run pending tasks" }
          sessionTarget: "main"
          enabled: true
  
  [5] Notify user:
      "⚙️ Model Queue initialized. N queues ready."
  
  → THEN continue with normal INTAKE steps.

IF queue files already exist:
  → Skip Step 0. Proceed to Step 1.
Step 1 — Parse User Message

Parse the message to extract:

  1. Tasks: Split by numbered lists, bullets, "然后", "and then", "next"
  2. Model/Source: Look for model names or source keywords
  3. Dependencies: "然后", "after that", "based on that" implies dependency on previous task
  4. Control commands: "cancel T-XXX", "retry T-XXX", "show status"
Step 2 — Handle Control Commands
CommandAction
cancel T-XXXSet status = "skipped", save, confirm
retry T-XXXReset status = "pending", retries = 0, save, confirm
skip T-XXXSet status = "skipped", save, confirm
show status / task statusRender queue status table (see Output Templates)
show queue {source}Show specific queue details
Step 3 — Determine Model Source

For each task:

IF user specified model explicitly (e.g., "用 qwen2.5"):
  FIND model in MODEL_SOURCE_* configs
  SET task.model = specified model
  SET task.queue = source containing that model

ELSE IF user specified source (e.g., "用远程", "send to remote"):
  FIND matching MODEL_SOURCE_*
  SET task.queue = that source
  SET task.model = first model in that source (or ask)

ELSE:
  IF DEFAULT_MODEL_SOURCE configured:
    SET task.queue = DEFAULT_MODEL_SOURCE
    SET task.model = first model in that source
  ELSE:
    ASK user: "Which model/source should handle this task?"
Step 4 — Determine Dependencies
IF task contains dependency indicators ("然后", "after that", "based on that"):
  IF previous task in same message:
    SET task.depends_on = previous_task.id
    SET task.on_depends_fail = "block" (default)
  ELSE:
    ASK user: "This task depends on which previous task?"

IF user explicitly specified dependency ("depends on T-XXX"):
  SET task.depends_on = specified_id
Step 5 — Assign Task ID
READ queue file for task.queue
IF queue.lastId is null:
  task.id = "T-001"
ELSE:
  PARSE number from queue.lastId (e.g., "T-005" → 5)
  INCREMENT number
  FORMAT as T-NNN (e.g., 6 → "T-006")
  task.id = formatted ID
Show full SKILL.md (333 more words)Show less
Step 6 — Build Task Object

Create task object with:

  • id, queue, model, description, goal
  • status: "pending" if no dependency, "waiting" if has dependency
  • priority: 0 (default) or user-specified
  • depends_on, on_depends_fail
  • retries: 0, maxRetries: from config
  • added_at: current timestamp
  • All other fields: null
Step 7 — Append to Queue
READ queue file for task.queue
APPEND task to queue.tasks[]
UPDATE queue.lastId = task.id
WRITE queue file
Step 8 — Confirm to User

Single task:

📋 Added T-001 to queue [ollama-local]
Model: ollama/qwen2.5
Task: Analyze the sales data
Queue position: 1

Multiple tasks:

📋 Added 3 tasks to queue [ollama-local]:
• T-001: Analyze the sales data
• T-002: Generate report (depends on T-001)
• T-003: Send to team (depends on T-002)

Starting dispatcher now...
Step 9 — Run DISPATCHER

Immediately after confirming, run DISPATCHER mode (see below).

Do not exit and wait for heartbeat. Tasks must start executing immediately.


Mode 2: DISPATCHER — Step-by-Step

Step 1 — Scan All Queue Files
LIST all *.json files in ${MODEL_QUEUES_DIR}/
FOR EACH queue file:
  READ queue data
Step 2 — Check Running Tasks

For each queue:

running_tasks = tasks where status = "running"

FOR EACH running_task:
  IF running_task.subagent_session is set:
    CALL subagents(action="list") to check session status
    
    IF session is DONE:
      READ result from session
      SET running_task.status = "done"
      SET running_task.result = full result
      SET running_task.result_summary = extract summary
      SET running_task.completed_at = now()
      NOTIFY user: "✅ {running_task.id} done — {summary}"
    
    ELSE IF session is FAILED or ERROR:
      IF running_task.retries < running_task.maxRetries:
        INCREMENT running_task.retries
        SET running_task.status = "pending"
        LOG: "Retrying {running_task.id} (attempt {retries+1})"
      ELSE:
        SET running_task.status = "failed"
        SET running_task.completed_at = now()
        NOTIFY user: "❌ {running_task.id} failed after {retries} attempts"
    
    ELSE IF session is STILL RUNNING:
      LEAVE as-is (check again next heartbeat)
Step 3 — Check Waiting Tasks

For each task with status = "waiting":

IF task.depends_on is set:
  FIND dependency task in ANY queue (cross-queue lookup allowed)
  
  IF dependency.status == "done":
    SET task.status = "pending"
    SET task.context_input = {
      "source_task": dependency.id,
      "result_summary": dependency.result_summary,
      "result_status": dependency.result_status,
      "included_at": now()
    }
    LOG: "{task.id} dependency satisfied, ready to run"
  
  ELSE IF dependency.status in ["failed", "blocked"]:
    SWITCH task.on_depends_fail:
      CASE "block":
        SET task.status = "blocked"
        SET task.blocked_reason = "Dependency {dependency.id} failed"
        NOTIFY user: "⚠️ {task.id} blocked — dependency {dependency.id} failed"
      
      CASE "skip":
        SET task.status = "skipped"
        SET task.skipped_reason = "Dependency {dependency.id} failed"
        NOTIFY user: "⏭️ {task.id} skipped — dependency {dependency.id} failed"
      
      CASE "continue":
        SET task.status = "pending"
        SET task.context_input = {
          "warning": "Dependency {dependency.id} failed",
          "included_at": now()
        }
        LOG: "{task.id} continuing despite failed dependency"
  
  ELSE IF dependency.status in ["pending", "waiting", "running"]:
    LEAVE task.status = "waiting"
Step 4 — Dispatch Pending Tasks

For each queue:

pending_tasks = tasks where status = "pending"
running_count = count of tasks where status = "running"

IF running_count >= queue.maxConcurrent:
  SKIP this queue (no slots available)

ELSE:
  slots_available = queue.maxConcurrent - running_count
  
  SORT pending_tasks by:
    1. priority (DESC)
    2. added_at (ASC)
  
  FOR EACH pending_task, up to slots_available:
    DISPATCH task:
      [1] BUILD subagent prompt:
          "You are executing task {task.id} for model-queue.
          
          Target Model: {task.model}
          Task: {task.description}
          Goal: {task.goal}
          
          {% if task.context_input %}
          Context from previous task {task.context_input.source_task}:
          {task.context_input.result_summary}
          {% endif %}
          
          Execute this task. When complete, report:
          1. The result (full output)
          2. A brief summary (1-2 sentences)  
          3. Status: success, partial, or failed
          4. If failed, explain why and suggest what might help
          
          Focus only on this task. Do not start other tasks."
      
      [2] CALL sessions_spawn:
          task: subagent prompt
          model: task.model (or default for queue)
          mode: "run"
          timeoutSeconds: appropriate timeout
      
      [3] UPDATE task:
          SET task.status = "running"
          SET task.subagent_session = spawned session ID
          SET task.started_at = now()
Step 5 — Save All Queues
FOR EACH modified queue file:
  WRITE queue data to disk
Step 6 — Return Appropriate Response
IF any notifications were sent (done/failed/blocked):
  RETURN the notifications (active heartbeat response)

ELSE IF tasks were dispatched:
  RETURN "Dispatched N tasks across M queues."

ELSE IF nothing to do (no pending, no running):
  RETURN "HEARTBEAT_OK"

Output Templates

Task Added
📋 Added {task.id} to queue [{queue}]
Model: {task.model}
{task.description}
{% if task.depends_on %}
Depends on: {task.depends_on} (block on failure)
{% endif %}
Queue position: {position}
Task Completed
✅ {task.id} done — {task.result_summary}
Queue: {task.queue} | Duration: {duration}
Task Failed
❌ {task.id} failed after {task.retries} attempts
Queue: {task.queue}
Error: {task.error_message}

To retry: "retry {task.id}"
Queue Status
📊 Queue Status

[{source-1}] {pending} pending, {running} running, {done} done
  {T-XXX} 🔄 running: {description} (started {time} ago)
  {T-XXX} ⏳ pending: {description}
  {T-XXX} ⏳ waiting: {description} (depends on {T-YYY})
  {T-XXX} 🚫 blocked: {description} — {blocked_reason}

[{source-2}] {pending} pending, {running} running, {done} done
  (empty)

A5 — Configuration Reference

TOOLS.md Settings
VariableDefaultDescription
MODEL_QUEUES_DIR~/.openclaw/model-queues/Directory for queue files
MODEL_QUEUE_MAX_RETRIES3Max retry attempts per task
MODEL_QUEUE_ARCHIVE_DAYS7Days before archiving completed tasks
MODEL_SOURCE_*(required)Model source mappings
DEFAULT_MODEL_SOURCE(optional)Default source when not specified
Queue File Structure
json
{
  "version": "1.0",
  "source": "ollama-local",
  "models": ["ollama/llama3", "ollama/qwen2.5"],
  "maxConcurrent": 1,
  "maxRetries": 3,
  "lastId": "T-005",
  "tasks": [...]
}

A6 — Heartbeat Integration

Heartbeat and cron setup is automatic. Step 0 of INTAKE mode handles this.

HEARTBEAT.md Entry (auto-injected)
markdown
## Model Queue Dispatcher

Every heartbeat: check ${MODEL_QUEUES_DIR} for pending/running tasks
- If tasks exist → run DISPATCHER mode (model-queue skill)
- If nothing pending → HEARTBEAT_OK
Backup Cron Job (auto-registered)
every 15 min → systemEvent: "MODEL_QUEUE_DISPATCH: check queues and run pending tasks"
sessionTarget: main

A7 — Edge Cases

SituationBehavior
Model not in any MODEL_SOURCE_*Ask user to specify source
Dependency cycle detectedReject task with error message
Dependency in different queueAllow (cross-queue dependencies supported)
Multiple dependenciesNot supported in v1 (single dependency only)
Task times out (subagent)Mark as failed, trigger retry logic
Queue file corrupt/invalid JSONAlert user, do not overwrite; ask to inspect
All tasks blockedNotify user with suggestions
20+ tasks added at onceProcess in order, dispatch one at a time
Subagent session ID lostMark task as pending, re-dispatch

A8 — File Organization

${MODEL_QUEUES_DIR}/
  ollama-local.json
  ollama-remote.json
  cloud-nvidia.json
  archive/
    ollama-local/
      2026-03.json
    ollama-remote/
      2026-03.json

Future Enhancements (v2)

  • Multiple dependencies per task
  • Task groups (batch operations)
  • Priority boost for urgent tasks
  • Queue pause/resume
  • Task result caching
  • Cross-queue result sharing
  • Scheduled task execution (run at specific time)
  • Task templates (reusable task definitions)

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files in skills/model-queue of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • STATUS.json
  • _meta.json
  • queue-schema.md
  • skill.yml

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Task Queue By Model Source next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Task Queue By Model Source compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Task Queue By Model Source this skillLeoYeAI/openclaw-master-skills2.2k—~4.2kAutomated safety check: PassMIT
Opsguaardvark/guaardvark251—~779Automated safety check: PassMIT
Trigger.dev Configurationpapermark/papermark9.2k—~1.2kAutomated safety check: PassCustom licence
FoundatioFoundatioFx/Foundatio2.1k—~3.9kAutomated safety check: PassApache-2.0
FastapiOpen-TutorAi/open-tutor-ai-CE1082 repos~2.6kAutomated safety check: PassBSD-3-Clause
AI Model NodejsTencentCloudBase/CloudBase-AI-Toolkit1.1k3 repos~5kAutomated safety check: PassMIT

Similar skills

  • Ops

    guaardvark/guaardvark

    Operate a running Guaardvark: GPU and VRAM state, plugin start/stop, logs, Celery tasks, the Interconnector sync to other machines, overnight RAG autoresearch, and infographics.

    251 GitHub stars~779 tokensUpdated today
    Media & CreativeAuto-check passed
  • Trigger.dev Configuration

    papermark/papermark

    Configures Trigger.dev projects through trigger.config.ts, with build extensions for Prisma, Playwright, Puppeteer, FFmpeg, Python and system packages.

    9.2k GitHub stars~1.2k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Foundatio

    FoundatioFx/Foundatio

    A skill your agent uses when working with Foundatio infrastructure abstractions for .NET -- caching, queuing, messaging, file storage, distributed locking, or background jobs.

    2.1k GitHub stars~3.9k tokensUpdated today
    Backend & APIsAuto-check passed
  • Fastapi

    Open-TutorAi/open-tutor-ai-CE

    FastAPI best practices and conventions. An agent skill from Open-TutorAi/open-tutor-ai-CE.

    108 GitHub starsUsed in 2 repos~2.6k tokens
    Backend & APIsAuto-check passed
  • AI Model Nodejs

    TencentCloudBase/CloudBase-AI-Toolkit

    A skill your agent uses for Node.js backend AI via @cloudbase/node-sdk (=3.16.0) — cloud functions, CloudRun, Express/Koa/NestJS, serverless APIs, scheduled jobs, LLM proxies, agent orchestration.

    1.1k GitHub starsUsed in 3 repos~5k tokens
    Backend & APIsAuto-check passed
  • Trigger.dev Realtime

    papermark/papermark

    Shows how to subscribe to Trigger.dev task runs from the backend and from React for progress indicators, live dashboards, AI response streams and approval waits.

    9.2k GitHub stars~1.7k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,215 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Categories

Questions about Task Queue By Model Source

What does Task Queue By Model Source do?

Multi-queue task orchestration system. An agent skill from LeoYeAI/openclaw-master-skills. Task Queue By Model Source is an agent skill from LeoYeAI/openclaw-master-skills. Multi-queue task orchestration system.

When should I use Task Queue By Model Source?

Task Queue By Model Source fits situations like: tasks that involve Background jobs.

How do I install Task Queue By Model Source in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill task-queue-by-model-source -a claude-code`. Or copy the skill folder (skills/model-queue in LeoYeAI/openclaw-master-skills) into .claude/skills/task-queue-by-model-source in your project. Claude Code loads it when a task matches its description.

How do I install Task Queue By Model Source in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill task-queue-by-model-source -a codex`. Or copy the skill folder (skills/model-queue in LeoYeAI/openclaw-master-skills) into .agents/skills/task-queue-by-model-source in your project. Codex loads it when a task matches its description.

Can I use Task Queue By Model Source in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill task-queue-by-model-source -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/task-queue-by-model-source, .gemini/skills/task-queue-by-model-source, .github/skills/task-queue-by-model-source and .opencode/skills/task-queue-by-model-source in your project.

What does Task Queue By Model Source need to run?

SKILL.md names no scripts, command-line tools or credentials: Task Queue By Model Source is instructions for the agent only.

Does Task Queue By Model Source access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Task Queue By Model Source safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Task Queue By Model Source use?

Task Queue By Model Source is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Task Queue By Model Source use?

About 4.2k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Task Queue By Model Source?

Skills that share tags, products or a category with Task Queue By Model Source: Ops (guaardvark/guaardvark, 251 stars), Trigger.dev Configuration (papermark/papermark, 9.2k stars), Foundatio (FoundatioFx/Foundatio, 2.1k stars) and Fastapi (Open-TutorAi/open-tutor-ai-CE, 108 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Task Queue By Model Source?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,158 GitHub stars. The repository holds 1,215 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.