- name
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add kharmanskyi/open-steps --skill os-check-work -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add kharmanskyi/open-steps --skill os-check-work -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add kharmanskyi/open-steps --skill os-check-work -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add kharmanskyi/open-steps --skill os-check-work -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/kharmanskyi/open-steps/tree/HEAD/skills/os-check-workFrom the publisher
You are the receiving party: another session says it finished, and your job is to find out whether that is true. Reports run optimistic - they are written by whoever did the work. Triggers live in the description above; one more is taking over work you did not do.
Write in the language the user speaks in this session, detected from the conversation. Code, file names and identifiers stay English.
Plural is a sweep: every sibling session, one line each, statuses only.
Singular - "accept this", a named session or pull request - is an accept:
full verification, then acceptance. A sweep that finds verified-ready work
rolls into accepting it - the accept steps run first, never skipped. Where
your tool cannot list other sessions, sweep the open pull requests instead
(gh pr list) and say so.
One line per session, one call per pull request - the reader skims these and reads the closing block. No table:
<name a person recognises (#PR)> - ; <all done? plus proof in 2-4 words, or what is missing>; <archive: yes / not yet>.
Find the claim. Read the transcript tail where tools allow - the last message is the report; read it once, do not quote it back. No tools → the pull request is the artefact; say so.
Verify each claim at its source.
Prefer numbers to words. Check what the report did not mention: scope creep and missing tests are never claimed - they are found.
Name the gaps - the deliverable. One line each: Claimed: … Measured: ….
No gaps → say so in one line; a clean intake is a real result.
Accept, hand back, or unblock.
Clean up. Remove its leavings - working copy, branch, temp files; ask before deleting what is not certainly its. Archive verdict → closing block.
When a checked session needs to hear something back - a defect, a question, a decision - write the reply in the same pass; do not leave the translation to the user.
**To <session name>** - paste this:
<the instruction, verbatim>
os-ask-simple.Both modes end the same way, always last, nothing after it:
| | |
|---|---|
| **Still open** | <what remains, or "nothing"> |
| **Do this next** | <the one action> - <one clause of reasoning> |
| **On your word** | <what you will do once they say it> |
os-whats-next.os-step-by-step).os-whats-next.>-
---name: os-check-workdescription: >----# skills/os-check-work/SKILL.mdFAQ
Download skills/os-check-work/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/kharmanskyi/open-steps.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.