菜单
Run before marking any task as done. Parses the task spec for output file paths and verifies each file actually exists on disk. If any required file is missing, requeues the task instead of closing it. Skip for tasks with no file output.
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
Activate for ANY request involving specialist delegation — single or multi-step. Contains the complete orchestration SOP: plan-and-confirm format, sequential execution rules, how to write a complete `request` argument, recovery from errors, retry limits, file delivery rules, and output presentation.
Activate when a multi-agent orchestration goes wrong. Contains: recovery from `ValueError: Tool '<name>' not found`, the full forbidden-tool reference for each specialist, retry limits and abandon criteria, recovery if you accidentally invoked two specialists in parallel, and the catalogue of historically-reproduced mistakes. Pair with `multi-agent-chain` (the always- loaded core skill) — that one has the happy-path rules; this one has the escape hatches.
Use when delegating report generation, PDF creation, chart visualization, or data interpretation to the business analysis expert. Load this skill before calling `business_analysis(request='...')` so you know what to send, what it returns, and which tools are internal to that specialist (and must NEVER be called directly).
Use when delegating any task to the coding expert — Python scripting, data analysis, SVM / ML algorithms, file I/O, package installation, git operations, or running tests. Load this skill before calling `coding(request='...')` so you know what to send and how to read the response.
Use when a task involves database operations — SQL queries, schema inspection, data retrieval, record insertion/update/deletion, or database health checks. Load this skill before calling `database(request='...')`. IMPORTANT: This specialist may not be deployed — check the registered tool spec first.
Activate before executing any substantive work that produces artifacts or requires multi-step execution (coding, data analysis, report generation, multi-agent chains). Guides you to check past epics for context, register a new Epic/Story/Task when none exists, mark tasks as doing before execution, and close them after completion.
| name | acceptance-check |
| description | Run before marking any task as done. Parses the task spec for output file paths and verifies each file actually exists on disk. If any required file is missing, requeues the task instead of closing it. Skip for tasks with no file output. |
Activate in assess-and-register Step 3 — before calling update_task_status(task_id, "done") — whenever the task spec contains a line matching:
- [ ] File exists at /app/data/shared/...
Skip this skill for:
Scan the task spec for lines in this exact format:
- [ ] File exists at /app/data/shared/<agent>/<filename>
Extract each absolute path. If no such lines exist → skip acceptance check, proceed to mark done.
For each extracted path, call:
list_data_files(path="<absolute_path>")
Interpret the result:
[EXISTS] <path> → file confirmed ✅[NOT FOUND] <path> → file missing ❌[ERROR] ... → treat as missing ❌All files exist:
update_task_status(task_id, "done")add_task_comment(task_id, type="result", content="Acceptance check passed. All output files verified.")Any file missing:
update_task_status(task_id, "queued") — requeue for re-executionadd_task_comment(task_id, type="issue", content="Acceptance check failed. Missing files: <list of missing paths>. Re-executing task.")<agent_name>(request='...')) with the original task spec verbatim.update_task_status(task_id, "failed") and report to user honestly.