$ loading_
Drives one selected APM PR from review handling to merge readiness.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "shepherd-driver" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/apm/main/packages/shepherd-driver/SKILL.md 2. Save it as ~/.claude/skills/shepherd-driver/SKILL.md 3. Reload skills and tell me it's ready
You are shepherd-driver. Operate only on this single open PR already selected by the parent orchestrator in microsoft/apm. Classify copilot-pull-request-reviewer[bot] inline comments, run apm-review-panel, fold recommendations by default within the PR's stated scope, push to the head branch, and report the current state: ready-to-merge, advisory-with-deferred, superseded, or blocked.
A PR handling result summarizing applied changes, deferred items, and final merge-readiness status.
As shepherd-driver, continuously watch CI for this selected PR; if it fails, diagnose the failure and submit minimal-scope fixes within fixed iteration caps until CI turns green or the PR is clearly marked blocked, while preserving authorship metadata.
A record of CI-fix iterations and a conclusion on whether the PR has reached the mergeability gate.
You are shepherd-driver. Run cross-PR conflict checks and the mergeability gate for this selected PR; if a superseding PR or follow-up commit is needed, preserve original authorship using commit trailers and return a final recommendation such as superseded or ready-to-merge.
A conflict-resolution plan, authorship-preservation notes, and a final superseded or merge-ready determination.
This SKILL.md is the natural-language module derived from a genesis design packet; refactors re-run the genesis skill from that packet.
This skill is a COMPOSED BUILDING BLOCK, not a user-facing entrypoint. It was extracted (genesis R3 EXTRACT) from batch-bug-shepherd when a second consumer (apm-issue-autopilot) needed the same per-PR convergence loop. Both orchestrators COMPOSE this skill; neither re-implements the loop. It in turn COMPOSES the apm-review-panel skill for the review pass -- it does NOT re-implement panel review.
DOES: take ONE PR that already exists and drive it to a terminal
landing-ready state; resolve cross-PR merge conflicts; emit the
PR-facing advisory and supersede comments; return a schema-valid
completion_return.
Does NOT: triage issues, decide which issues are worth fixing, open the first PR for an issue, choose the batch, or maintain the orchestrator's ground-truth table. Those are the parent orchestrator's responsibility. If you find yourself triaging or opening greenfield PRs, you are in the wrong skill.
The parent orchestrator, for each PR in its batch, spawns ONE
shepherd-driver subagent with the spawn body in
assets/shepherd-driver-prompt.md.
The orchestrator passes the inputs that prompt declares (PR_NUMBER,
ISSUE_NUMBER, AUTHOR, HEAD_REPO, HEAD_BRANCH, MAINTAINER_CAN_MODIFY,
REPO_ROOT, ORIGIN, optional PANEL_PRIOR). The subagent owns the whole
convergence loop end-to-end and returns a completion_return.
After every shepherded PR returns ready-to-merge, the orchestrator
runs the conflict-resolution phase: probe mergeability and, on
DIRTY / BEHIND / CONFLICTING, spawn one conflict-resolution subagent
per assets/conflict-resolution-prompt.md.
The step-by-step gate procedure is in
references/mergeability-gate.md
(load it when entering that phase).
This skill is a same-repo LOCAL SIBLING. A consuming orchestrator MUST declare the dependency at its own distribution surface and PROBE for this skill before spawning. The probe is a tool call, not an assertion from recall (A9 SUPERVISED EXECUTION; truth #2 CONTEXT EXPLICIT):
test -f ../shepherd-driver/assets/shepherd-driver-prompt.md \
&& test -f ../shepherd-driver/assets/completion-schema.json \
&& echo "shepherd-driver present" \
|| echo "MISSING shepherd-driver - stop and ask the operator"
On a probe MISS the orchestrator stops and asks the operator rather than re-implementing the loop inline (avoids HAND-ROLLED HALLUCINATION and PHANTOM DEPENDENCY).
This skill itself COMPOSES apm-review-panel.
A consuming orchestrator inherits that transitive dependency; the
spawned shepherd-driver subagent PROBES for it at preflight (all
load-bearing panel assets under
$REPO_ROOT/.agents/skills/apm-review-panel/) and returns
status: blocked ONLY on a genuine asset MISS, before any checkout
(see the spawn body Step 0.0). Note: a missing skill TOOL is NOT a
miss -- in the normal subagent context the panel is executed INLINE
from its on-disk SKILL.md + schemas (Step X.1.1), which is a
first-class path, not a fallback.
The shepherd-driver subagent runs this loop (full detail in the spawn body):
copilot-pull-request-reviewer[bot]
inline review per
assets/copilot-classification-prompt.md.apm-review-panel against the PR: via the
skill tool if present, otherwise (the normal subagent case)
execute it INLINE from its on-disk SKILL.md + schemas. Both paths
produce the same single recommendation comment.…
Guide APM positioning, release communication, and breaking-change strategy decisions.
Audit an entire docs corpus against code and propose precise fixes.
Improve CLI output, logs, errors, and terminal diagnostic user experience.
Triages bug batches and drives related PRs to a mergeable state.
Plan doc TOC changes and outline stubs when PRs require structural updates.
Triage APM issues in batches and drive approved ones to mergeable PRs.
Run a multi-expert advisory review for labelled microsoft/apm pull requests.
Helps teams handle APM positioning, release communication, and breaking-change decisions.
Triage microsoft/apm issues and produce one unified resolution comment.
Install, configure, author, and troubleshoot APM agent packages and CLI workflows.