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.
Multi-queue task orchestration system. An agent skill from LeoYeAI/openclaw-master-skills.
$ npx skills add LeoYeAI/openclaw-master-skills --skill task-queue-by-model-source -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills task-queue-by-model-source --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-srcUse ~/.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/
Install the "task-queue-by-model-source" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/model-queue into .claude/skills/task-queue-by-model-source/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-queue-by-model-source", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/model-queueType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill task-queue-by-model-source -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills task-queue-by-model-source --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/model-queue .agents/skills/task-queue-by-model-source && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "task-queue-by-model-source" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/model-queue into .agents/skills/task-queue-by-model-source/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-queue-by-model-source", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill task-queue-by-model-source -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills task-queue-by-model-source --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/model-queue .cursor/skills/task-queue-by-model-source && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "task-queue-by-model-source" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/model-queue into .cursor/skills/task-queue-by-model-source/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-queue-by-model-source", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/model-queue--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill task-queue-by-model-source -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills task-queue-by-model-source --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/model-queue .gemini/skills/task-queue-by-model-source && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "task-queue-by-model-source" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/model-queue into .gemini/skills/task-queue-by-model-source/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-queue-by-model-source", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills task-queue-by-model-sourceInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill task-queue-by-model-source -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/model-queue .github/skills/task-queue-by-model-source && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "task-queue-by-model-source" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/model-queue into .github/skills/task-queue-by-model-source/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-queue-by-model-source", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill task-queue-by-model-source -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills task-queue-by-model-source --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/model-queue .opencode/skills/task-queue-by-model-source && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "task-queue-by-model-source" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/model-queue into .opencode/skills/task-queue-by-model-source/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-queue-by-model-source", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
task-queue-by-model-sourceMulti-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. 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.
12 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
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.
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.
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.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 789 words, ~4,216 tokens.
.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.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.
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/llama3Each model source has its own queue file:
${MODEL_QUEUES_DIR}/ollama-local.json${MODEL_QUEUES_DIR}/ollama-remote.jsonQueues are independent — a blocked task in one queue doesn't affect other queues.
{
"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
}| Status | Description |
|---|---|
pending | Ready to be dispatched (no dependencies or resolved) |
waiting | Has dependency, waiting for it to complete |
running | Currently executing via subagent |
done | Completed successfully |
failed | Failed after max retries |
blocked | Dependency failed, waiting for user action |
skipped | Skipped by user or due to dependency failure |
| Mode | Trigger | Purpose |
|---|---|---|
| INTAKE | User message containing task intent | Parse message → route to queue → confirm → immediately run DISPATCHER |
| DISPATCHER | After INTAKE (primary) · Heartbeat/cron (backup) | Check queues → dispatch pending tasks → report completions |
REQUIRED: Configure model sources in TOOLS.md before first use.
Add to your TOOLS.md:
## 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-remoteActivate INTAKE mode when user message matches:
| Pattern | Examples |
|---|---|
| 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:
"MODEL_QUEUE_DISPATCH: check queues and run pending tasks" (backup)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.Parse the message to extract:
| Command | Action |
|---|---|
cancel T-XXX | Set status = "skipped", save, confirm |
retry T-XXX | Reset status = "pending", retries = 0, save, confirm |
skip T-XXX | Set status = "skipped", save, confirm |
show status / task status | Render queue status table (see Output Templates) |
show queue {source} | Show specific queue details |
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?"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_idREAD 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 IDCreate task object with:
id, queue, model, description, goalstatus: "pending" if no dependency, "waiting" if has dependencypriority: 0 (default) or user-specifieddepends_on, on_depends_failretries: 0, maxRetries: from configadded_at: current timestampREAD queue file for task.queue
APPEND task to queue.tasks[]
UPDATE queue.lastId = task.id
WRITE queue fileSingle task:
📋 Added T-001 to queue [ollama-local]
Model: ollama/qwen2.5
Task: Analyze the sales data
Queue position: 1Multiple 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...Immediately after confirming, run DISPATCHER mode (see below).
Do not exit and wait for heartbeat. Tasks must start executing immediately.
LIST all *.json files in ${MODEL_QUEUES_DIR}/
FOR EACH queue file:
READ queue dataFor 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)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"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()FOR EACH modified queue file:
WRITE queue data to diskIF 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"📋 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.id} done — {task.result_summary}
Queue: {task.queue} | Duration: {duration}❌ {task.id} failed after {task.retries} attempts
Queue: {task.queue}
Error: {task.error_message}
To retry: "retry {task.id}"📊 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)| Variable | Default | Description |
|---|---|---|
MODEL_QUEUES_DIR | ~/.openclaw/model-queues/ | Directory for queue files |
MODEL_QUEUE_MAX_RETRIES | 3 | Max retry attempts per task |
MODEL_QUEUE_ARCHIVE_DAYS | 7 | Days before archiving completed tasks |
MODEL_SOURCE_* | (required) | Model source mappings |
DEFAULT_MODEL_SOURCE | (optional) | Default source when not specified |
{
"version": "1.0",
"source": "ollama-local",
"models": ["ollama/llama3", "ollama/qwen2.5"],
"maxConcurrent": 1,
"maxRetries": 3,
"lastId": "T-005",
"tasks": [...]
}Heartbeat and cron setup is automatic. Step 0 of INTAKE mode handles this.
## 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_OKevery 15 min → systemEvent: "MODEL_QUEUE_DISPATCH: check queues and run pending tasks"
sessionTarget: main| Situation | Behavior |
|---|---|
| Model not in any MODEL_SOURCE_* | Ask user to specify source |
| Dependency cycle detected | Reject task with error message |
| Dependency in different queue | Allow (cross-queue dependencies supported) |
| Multiple dependencies | Not supported in v1 (single dependency only) |
| Task times out (subagent) | Mark as failed, trigger retry logic |
| Queue file corrupt/invalid JSON | Alert user, do not overwrite; ask to inspect |
| All tasks blocked | Notify user with suggestions |
| 20+ tasks added at once | Process in order, dispatch one at a time |
| Subagent session ID lost | Mark task as pending, re-dispatch |
${MODEL_QUEUES_DIR}/
ollama-local.json
ollama-remote.json
cloud-nvidia.json
archive/
ollama-local/
2026-03.json
ollama-remote/
2026-03.json© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files in skills/model-queue of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Task Queue By Model Source this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.2k | Automated safety check: Pass | MIT | |
| Opsguaardvark/guaardvark | 251 | — | ~779 | Automated safety check: Pass | MIT | |
| Trigger.dev Configurationpapermark/papermark | 9.2k | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| FoundatioFoundatioFx/Foundatio | 2.1k | — | ~3.9k | Automated safety check: Pass | Apache-2.0 | |
| FastapiOpen-TutorAi/open-tutor-ai-CE | 108 | 2 repos | ~2.6k | Automated safety check: Pass | BSD-3-Clause | |
| AI Model NodejsTencentCloudBase/CloudBase-AI-Toolkit | 1.1k | 3 repos | ~5k | Automated safety check: Pass | MIT |
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.
papermark/papermark
Configures Trigger.dev projects through trigger.config.ts, with build extensions for Prisma, Playwright, Puppeteer, FFmpeg, Python and system packages.
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.
Open-TutorAi/open-tutor-ai-CE
FastAPI best practices and conventions. An agent skill from Open-TutorAi/open-tutor-ai-CE.
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.
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.
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.
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.
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.
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.
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.
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.
Works with
Categories
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.
Task Queue By Model Source fits situations like: tasks that involve Background jobs.
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.
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.
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.
SKILL.md names no scripts, command-line tools or credentials: Task Queue By Model Source is instructions for the agent only.
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.
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.
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.
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.
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.
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.