agentleFS
Sign inStart free
assisjpassisjp/specflow/skills/engineering/takeover/SKILL.md

takeover

Skill17 starsChanged 3 months agoMITView on GitHub

Take over an existing branch, pull request, worktree, or agent handoff while preserving the original goal, contributor credit, and concurrent work. Use when the user asks to take over, finish, rescue, or continue someone else's implementation. Do not use to replace a clear request to start new work.

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the goal is obsolete, already delivered elsewhere, or directionally wrong, report that with evidence instead of polishing it.

    line 22
  2. Distinctive:

    When parallel contributors must edit the same surface, serialize integration or use authorized isolation.

    line 28

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Takeover

Finish the original goal based on the current code and repository state, not on a handoff's claims. Preserve human contributor credit and do not defend an inherited implementation merely because it already exists.

1. Establish the source of truth

Record the requested outcome, source PR/branch/worktree/handoff, current checkout, base and head SHAs, git status, existing reviews/checks, and later user corrections. Read the full candidate diff and relevant source/acceptance criteria. Treat handoffs, comments, and agent transcripts as context; verify them against the actual files and live PR state.

Do not discard, stash, overwrite, rebase, or publish user/contributor work without authorization. If the active checkout is dirty or in use by another task, use an authorized isolated worktree or stop with the concrete conflict. Re-check the source before delivery: it may have moved while you worked.

2. Recover intent before changing code

State the smallest coherent goal the inherited work was trying to achieve, what is complete, what remains, and whether the implementation still matches current architecture. Read changed contracts, callers, tests, linked issues, review threads, and applicable repository instructions. Separate observed facts from assumptions and material decisions.

If the goal is obsolete, already delivered elsewhere, or directionally wrong, report that with evidence instead of polishing it. Use $pr-maintenance when the question is whether an existing PR should be updated, reworked, or superseded. Do not silently expand into unrelated cleanup.

3. Continue with clear ownership

Reuse valid checks and accepted decisions whose candidate, dependencies, and environment remain unchanged. Implement only the necessary continuation. Follow spec-execution for bounded implementation, code-review for ordinary review, and $review-loop when the user requests iterative convergence or it is recommended for a consequential change.

When parallel contributors must edit the same surface, serialize integration or use authorized isolation. Define owned paths/responsibilities and one integration owner. An inherited branch is not permission to overwrite concurrent edits.

4. Preserve attribution and delivery boundaries

Preserve existing commit authorship and verified co-author trailers. Do not invent names, email addresses, or credit. If you create a successor PR, explain its relationship to the original in the description when the user authorizes publication.

Do not update, close, merge, rebase, force-push, comment on, or change the base of a PR unless the task and repository policy authorize that action. $file-pr can create or update an authorized PR; $pr-maintenance can monitor an authorized PR. Neither substitutes for publication or merge permission.

5. Report the takeover

Report the inherited source and measured state, recovered goal, work completed, preserved attribution, checks/evidence, changed or unresolved decisions, and delivery status. If work pauses, use session-handoff with the source identity, current snapshot, concurrent-work constraints, and one concrete next action.

Download now (ZIP)

  • Other versions6 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 6

    1. t3dotgg/tstack★ 2.5ksame name
    2. mneves75/skills★ 3same name
    3. Dhruv2mars/skills★ 2same name
    4. oubakiou/skills★ 1same name
    5. luisgui1757/sentinel★ 0same name
    6. shubrt/skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use leaving-pr-comments, full-stop and 5 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • Dhruv2marsSkill

      leaving-pr-comments

      Format and post agent-authored GitHub pull request

      Also in 5 projects that use this

    • Nexus-Organization-InfosecSkill

      full-stop

      Shut down the Full Control phone-bridge completely — end Claude's watch loop, stop the bridge server (server.py started via ensure_server.ps1), and mark Claude offline in the app. Use whenever the user invokes /full-stop or says "stop full control", "stop the watch loop", "shut down the bridge/server", or "stop the ps1". Counterpart of [[full-control]], which starts everything.

      Also in 5 projects that use this

    • salalaslamSkill

      sol-loop

      Use when the user says "sol loop", or when another skill (such as full-stop) asks for a sol loop. Not for a one-off review; that's interrogate.

      Also in 4 projects that use this

    • garrytanSkill

      modernize

      Bring an aging pull request onto its current base and decide whether it should still exist: MODERNIZE, REWORK or CLOSE, with range-diff proof before any push. (gstack)

      Also in 4 projects that use this

    • shhacSkill

      full-send

      Complete an explicitly assigned task autonomously through parallel agents, peer-reviewed decisions, and automatic retries of temporary blockers. Use only when the user explicitly invokes Full Send.

      Also in 4 projects that use this

    • owidSkill

      babysit-pr

      Spawn a background agent that babysits an open PR — triggers a Codex review, watches CI, judges and fixes valid findings, replies to and resolves review threads, and loops to a cap. Never merges. Trigger when the user asks to "babysit the PR", "ask for codex review(s) and watch CI", or after pushing a substantial chunk to a PR branch.

      Also in 5 projects that use this

  • In this repository14 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free