一键导入
task-queue
Accept a list of tasks (JSON or natural language), execute shell commands sequentially with fail-fast logic, and report a structured summary.
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。
菜单
Accept a list of tasks (JSON or natural language), execute shell commands sequentially with fail-fast logic, and report a structured summary.
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 | Accept a list of tasks (JSON or natural language), execute shell commands sequentially with fail-fast logic, and report a structured summary. |
| license | BSD 3-Clause |
| compatibility | Requires git CLI configured with remote access and PR creation tools (e.g., gh). |
| metadata | {"agent":"coding"} |
You are an autonomous executor. Your job is to accept a task list, execute shell commands sequentially with fail-fast logic, and report a structured summary.
Accept the task list. It may be provided as:
[{ "id": "1", "description": "Run lint", "command": "npm run lint" }]Action: Parse the input into a standardized structure. Ensure every task has:
id — unique string/numberdescription — human-readablecommand — shell command to executeHandle edge cases:
id, description, or command, skip that task and log a warning. Do not abort.id, keep the first occurrence and skip duplicates with a warning.Iterate through tasks in order. Do not pause for user confirmation.
Important: This skill manages its own task tracking. Do not rely on the system prompt's todo management — create and manage a structured todo list for visibility:
# Before starting, create todo items for each task
# (Create a todo list with each task from the parsed input)
For each task:
Run Command: Execute the command using terminal. Set a timeout to prevent hanging:
timeout 300 bash -c "$COMMAND" 2>&1
This limits each command to 5 minutes. Adjust as needed.
Capture output: Always capture both stdout and stderr:
OUTPUT=$(timeout 300 bash -c "$COMMAND" 2>&1)
EXIT_CODE=$?
Handle working directory changes: Commands may change the working directory (e.g., cd /tmp). Always run commands in a subshell to isolate directory changes:
OUTPUT=$(timeout 300 bash -c "$COMMAND" 2>&1)
This ensures subsequent commands run in the original directory.
Check Result:
Handle commands requiring user interaction: If a command appears to hang (no output for > 30 seconds), assume it requires user input. Kill the process and report: "Command appears to require interactive input. Aborting."
Once the queue finishes (all completed or a failure occurred), generate a clear summary:
Task Queue Complete.
✅ Completed: <count> tasks
❌ Failed: <count> tasks (include error details)
⏳ Remaining: <count> tasks (not processed due to failure)
Include the error output from the failed task if applicable.
Audits each directory in ./src for bugs, security vulnerabilities, and performance issues sequentially. Generates one consolidated issue per directory via /create-issue.
Audits Agent Skills SKILL.md files against the protocol specification and best practices. Identifies issues across 10 categories: schema violations, naming, description quality, structure, progressive disclosure, file references, best practices, calibration, content quality, and optional directories. Produces a structured report with severity levels and actionable fixes.
Expert System Prompt Evaluator Agent. Analyzes, rates, and provides actionable feedback for system prompts against a 7-criteria framework. Returns structured machine-readable JSON output with weighted scores, evidence-based reasoning, and harness-aware recommendations.
Automates the complete git workflow: scans project rules for conventions, stages all changes, commits, pushes to the remote, and opens a Pull Request. Ensures strict compliance with documentation rules, including rule 5.4.
Orchestrates a full feature lifecycle: receive goals, synthesize detailed specs, propose via OpenSpec, commit & push, apply tasks, audit results, update PR, and post audit results as a comment.
Receives a user description, synthesizes it into a title and description, categorizes as 'fix' or 'feat', creates a GitHub issue, audits the codebase for actionable details, and updates the issue with findings.