菜单
Persistent JSON-backed job queue for scheduling shell commands without raw cron — supports one-shot (run at a time) and recurring (cron schedule) tasks. Use when asked to schedule or run a job at/every some interval, list or cancel queued tasks, or check task status.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | task-queue |
| description | Persistent JSON-backed job queue for scheduling shell commands without raw cron — supports one-shot (run at a time) and recurring (cron schedule) tasks. Use when asked to schedule or run a job at/every some interval, list or cancel queued tasks, or check task status. |
| category | productivity |
| maturity | stable |
| tags | ["task-queue","scheduling","cron","pipelines","job-runner"] |
A persistent, JSON-backed job queue. Lets Kite schedule and manage shell commands without raw cron. One-shot tasks (run at a specific time) and recurring tasks (cron schedule) are both supported.
| File | Purpose |
|---|---|
${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/queue.json | Task store (source of truth) |
${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs | CLI tool for managing tasks |
${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/runner.cjs | Runner — executes due tasks |
${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/runner.log | Runner output log |
Skill copies live in ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/task-queue/scripts/.
# Add one-shot task
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs add "name" "command" --at "2026-02-21T18:00:00"
# Add recurring task (every 15 min)
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs add "name" "command" --every "*/15 * * * *"
# Add immediate task (runs next runner tick)
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs add "name" "command"
# List all / filter
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs list
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs list --status pending
# Details for one task
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs status <id>
# Cancel / mark done
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs cancel <id>
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs done <id>
# Housekeeping
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs clear --done
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs clear --failed
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs clear --all
# Run runner manually (normally cron does this)
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/runner.cjs
# Tail log
tail -f ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/runner.log
* * * * * /usr/bin/node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/runner.cjs >> ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/runner.log 2>&1
{
"id": "a1b2c3d4",
"name": "human name",
"command": "echo hello",
"type": "one-shot | recurring",
"status": "pending | running | done | failed | cancelled",
"scheduled_at": "2026-02-21T18:00:00.000Z",
"cron_expr": "*/15 * * * *",
"created_at": "...",
"started_at": "...",
"finished_at": "...",
"last_run_at": "...",
"output": "...",
"error": "..."
}
*, */N, N-M, N,M,… for each fieldpending after each run so they fire again next cycledone (or failed) after their single executionPipelines are multi-step tasks where each step is checkpointed. On failure, retry skips already-completed steps and resumes from where it left off.
| File | Purpose |
|---|---|
${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/pipelines.json | Pipeline store |
${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/pipeline-runner.cjs | Cron runner for pipelines (every minute) |
${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/pipeline-runner.log | Pipeline runner log |
# Add a pipeline (steps as inline JSON)
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs pipeline add "Deploy app" \
--steps '[{"name":"Run tests","command":"cd ~/myapp && npm test"},{"name":"Push","command":"cd ~/myapp && git push"}]'
# Add a pipeline from a steps file
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs pipeline add "Deploy app" --steps-file /path/to/steps.json
# List all pipelines (shows step progress)
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs pipeline list
# Detailed status (per-step output and errors)
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs pipeline status <id>
# Retry a failed pipeline (skips done steps, re-runs from failure point)
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs pipeline retry <id>
# Cancel / delete
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs pipeline cancel <id>
node ${TASK_QUEUE_HOME:-$HOME/projects/task-queue}/cli.cjs pipeline delete <id>
[
{ "name": "Step 1", "command": "echo hello", "timeout_ms": 60000 },
{ "name": "Step 2", "command": "echo world" }
]
{
"id": "abc12345",
"name": "My pipeline",
"status": "queued | running | done | failed | cancelled",
"current_step": 1,
"steps": [
{
"id": "step-1",
"name": "Step name",
"command": "shell command",
"status": "pending | running | done | failed | skipped",
"timeout_ms": 600000,
"started_at": null,
"finished_at": null,
"output": null,
"error": null
}
]
}
Double-model verification gate before declaring a build/research/refactor "done". Runs a fresh Anthropic (Claude) review AND an independent OpenAI/Azure critic against the stated goal + criteria, then reconciles. Use before announcing completion of medium/major builds, refactors, major fixes, research deliverables, frontend work, or trade-decision rigor — and on demand via /verify. Skip for small Q&A and trivial edits.
Record and retrieve Architecture Decision Records — log a decision's context, options, rationale, and tradeoffs, then list/search them. Use when making a non-trivial design or architecture decision, choosing between tools/approaches, or asked 'why did we do it this way?'
Queue an external action (Telegram message, shell command, GitHub comment, PR merge, file write) for the user's explicit approval before it runs. Use when you want to take an outward-facing or irreversible action that needs sign-off first.
Run a structured multi-position debate over an analytical question, spawning sub-agents to argue each option and counter confirmation bias. Use when comparing options or tradeoffs — 'which is better', 'should we', 'what's the risk', 'evaluate', 'compare options'.
Ingest documents (URLs, local files, PDFs) into a searchable local knowledge base and query stored knowledge. Use when ingesting or storing documents, searching previously stored knowledge, or building research context.
Collect macro market and economic-calendar data (yfinance + FairEconomy API) into a SQLite DB and generate a formatted macro briefing for Telegram. Use when producing a macro/markets briefing or collecting macro market data.