The first real handover (MEK Charge Reconciliation) came out at 9 pages. Ops want it short: which URL to open and what to click, what shows where after the click, what to do when an exception comes, and how to email us. - Output is "<Project Name> Handover SOP" (HANDOVER-SOP.md + .docx) with 5 sections: how to run, what you see while it runs, result, when something goes wrong, email us. HANDOVER-DEV.md is dropped; dev-team findings go in the chat. - At most ~1,400 words; to_docx.py prints the word count and flags overflow, and renders *italic* for the variable parts of messages. - Every quoted message, label and URL is checked against the code. The SOP must say what clicking Run again does to the data. - One scan subagent; failure classes stay as a scan checklist. - Tebra reference rewritten in the SOP format; test, README, glossary updated; ADR-0005 supersedes ADR-0004. The handoff eval runner (tests/evals/run_handoff_eval.py) still grades an older 13-section format and was already out of date; not touched here. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
rpa-bot-handoff
A Claude skill that writes a short Handover SOP for an RPA bot that is being handed over to an ops team.
What you get
<Project Name> Handover SOP.docx (and HANDOVER-SOP.md): at most 4 pages, in plain words, for operators who don't read code:
- How to run: the URL or shortcut, what to click, and what a new click does to the previous results
- What you see while it runs: what shows where, a normal run, how long each step may take
- Result: how a good run ends, where the report is, what each status means
- When something goes wrong: how it shows, each message (E01, E02...) with what to do, the don'ts, how to stop it
- Email us: the address, when to email, and the email to copy
Problems the scan finds for the dev team are listed in the chat, not in the SOP.
Install
Copy this folder to ~/.claude/skills/rpa-bot-handoff/.
Use
In your bot project, ask Claude: "write the handover SOP for this bot" or "document this bot for handover". The skill:
- Scans the code with a subagent. It never runs the bot.
- Asks up to two things: the email group ops writes to, and where ops runs the bot.
- Writes the SOP, checks every quoted message and label against the code, and keeps it under 1,400 words.
- Turns it into the Word file you give to ops.
Files
| File | What it is |
|---|---|
SKILL.md |
Steps Claude follows |
templates/HANDOVER-SOP.md |
The SOP skeleton |
templates/failure-classes.md |
12 failure classes from Tebra's first months with ops, used as a scan checklist |
templates/reference/tebra-auto-post.md |
The SOP filled in for Tebra, scrubbed |
templates/to_docx.py |
Turns the SOP into Word and prints the word count (--selfcheck tests it) |