agentleFS
aicodekingaicodeking/deepseek-stack/skills/ds-revive/SKILL.md

ds-revive

Skill80 starsChanged 15 days agoMITView on GitHub

Brings an old PR up to date by checking if its idea still fits the current code, then rebasing, reworking or recommending it be closed. Use when asked to rebase, refresh, update or revive a stale PR, or /ds-revive.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Update the idea, not only the branch.

    line 6
  2. Distinctive:

    Write the PR's goal in one sentence.

    line 12
  3. Distinctive:

    Run git range-diff on the old and new series.

    line 25
  4. Distinctive:

    Run the focused checks for the touched area.

    line 26
  5. Distinctive:

    Treat a dirty worktree as the user's.

    line 38
  6. Distinctive:

    Never merge, close or change the base branch.

    line 39
  7. Distinctive:

    No conflicts in Git does not mean the PR is current.

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Update the idea, not only the branch. A clean rebase does not prove the PR still belongs.

Steps

  1. Fetch the latest base, the PR head and any related branches.
  2. Record the PR URL, state, base, head branch, head SHA, author, checks and review state. Read the title, body, linked issues, commits, threads and full diff.
  3. Write the PR's goal in one sentence.
  4. Find the merge base. Read what landed on the base branch since then. Search merged and open PRs for the same problem.
  5. Answer each question with evidence (commit, PR or file path):
    • Has this problem already been solved?
    • Did the APIs, types, schemas or structure it relies on change?
    • Was the code it edits moved, deleted or simplified?
    • Would landing it bring back old behavior or make two ways to do one thing?
    • Is the benefit still worth the upkeep?
  6. Pick one verdict:
    • REVIVE: goal and shape still fit. Go to step 7.
    • REWORK: goal fits, shape does not. Describe the smallest rewrite and stop, unless the user also asked for the rework.
    • CLOSE: superseded or no longer worth it. Cite the evidence and stop. Do not close it yourself.
  7. For REVIVE: work in a clean worktree at the recorded head. Rebase onto the fresh base. Resolve conflicts by the PR's goal and the base's newer rules.
  8. Run git range-diff on the old and new series. Confirm no intended change was lost and nothing already landed came back.
  9. Run the focused checks for the touched area. Mark each failure as real, pre-existing or infrastructure.
  10. Push with --force-with-lease=<branch>:<old head SHA>.
  11. Report the verdict first, then base changes, conflicts, push result, checks and the remaining decision with the PR link.

Stop when

  • The report is written after any of the three verdicts.
  • A conflict shows a product or design disagreement. Stop and reconsider the verdict.
  • The lease fails. Fetch again and redo steps 4 to 6 once. If it fails again, report.

Rules

  • Treat a dirty worktree as the user's. Never stash or discard it.
  • Never merge, close or change the base branch. Never force-push without a lease.
  • No conflicts in Git does not mean the PR is current.
  • Separate facts you checked from your judgment.
  • Post PR comments only when asked, through ds-pr-comments.

Download now (ZIP)

Does it work?

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

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.