batch-bug-shepherd

Solid

Use this skill to drive a batch of suspected bugs in microsoft/apm from raw issue list to mergeable PR queue. Fan out one triage subagent per issue (LEGIT / UNCLEAR / FIXED-AT-HEAD), cross-reference legit issues against open PRs, then branch: in-flight community PR -> shepherd via the apm-review-panel skill; no PR -> fix session with TDD and a mutation-break gate. Dispatch one completion subagent per shepherd verdict to resolve panel follow-ups, FOLD non-blocking recommendations into the same PR by default (DEFER cross-cutting items to tracking issues), push to the contributor fork (preserving author via commit trailers), and post one ready-to-merge confirmation. Maintain a single plan.md ground-truth table as canonical session state. Activate when the maintainer asks to triage issues, sweep the bug queue, shepherd bug-flagged issues, run a weekly community sweep, or drive in-flight community PRs to merge -- even if "shepherd" or "batch" is not named.

AI & Automation 2,694 stars 216 forks Updated today MIT

Install

View on GitHub

Quality Score: 91/100

Stars 20%
100
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# batch-bug-shepherd - Outer-loop bug-queue orchestrator This skill is an A10 ORCHESTRATOR-SAGA over five fan-out waves (triage, strategic-alignment, shepherd-or-fix, completion, conflict-resolution) with a persisted ground-truth table between phases. It COMPOSES the [apm-review-panel](../apm-review-panel/SKILL.md) skill -- it does NOT re-implement panel review. It also COMPOSES the `apm-ceo` persona (host-repo agent at `.apm/agents/apm-ceo.agent.md`) for the strategic-alignment gate, which checks every LEGIT bug against `PRINCIPLES.md` before allowing shepherd / fix work to proceed. Per-PR shepherding is delegated; per-issue verification, strategic alignment, PR-in-flight branching, fix dispatch, completion, post-wave mergeability re-probe, and the cross-session table are owned here. The skill is ADVISORY at the panel layer and EXECUTIVE at the orchestrator layer: it WILL push commits, open PRs, post comments, close superseded PRs. Every consequential write goes through a deterministic CLI (`gh`, `git`, `uv run ruff`) wrapped in plan + execute + verify (A9 SUPERVISED EXECUTION). ## Architecture invariants - **Fan-out, not serial.** Triage, shepherd, fix, and completion all run as parallel child threads via the runtime's `task` affordance. A single-loop variant of this skill is an anti-pattern -- it collapses the context-isolation win. - **Verify before fix.** No fix subagent is dispatched until the issue is reproduced on HEAD (verdict `LEGIT`). `UNCLEAR` issues ...

Details

Author
microsoft
Repository
microsoft/apm
Created
8 months ago
Last Updated
today
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

Testing & QA Listed

fix-bug

Resolves a single bug from any starting evidence — Dash0 telemetry (span / log / web event / RUM error link), raw stack trace, error message, code pointer (file:line), screen recording, Linear ticket URL, or free-text symptom. Classifies the input, **triages complexity** (Phase 0.5) to pick between a fast lane and a full holistic-analysis lane, runs a pre-flight sweep, locks a failing reproduction (delegating to /tdd, /e2e-testing, or /e2e-testing-mobile by layer), delegates root-cause analysis to holistic-analysis on complex bugs (or runs a lightweight in-skill analysis on simple ones), gates on confidence(analysis), and on >= 92 % hands off **without human confirmation**: simple bugs take the fast lane (/fix-bug → aw-create-plan → aw-executor, no aw-planner) and complex bugs take the standard lane (aw-planner → aw-executor), both with a CEGIS refinement contract. Fast-lane round-3 CEGIS failure falls back to standard-lane via aw-planner. An independent bug-fix-verifier agent grades the PR before undrafting;

4 Updated yesterday
mthines
Code & Development Listed

running-bug-review-board

Runs a real-user manual QA pass against any web/mobile/desktop app and turns the results into a Bug Review Board (BRB) feedback loop. Use whenever the user says "QA this", "test phase N", "run a manual test plan", "act as a real user", "find UX bugs", "sign off this build", "file a bug report", or "is this ready to ship?" — even if they only describe the symptoms ("the signup flow feels broken", "check what's wrong before we move on", "we finished feature X"). Drives the trifecta: PM (verifies user-promise), QA (executes scenarios from a real user's perspective), and Engineer (flags invalidated assumptions). Repo-agnostic, browser-tool-agnostic, scaffolds folders for bug reports + run reports + coordinator merges with P0/P1/P2 priorities. Works alongside cursor-ide-browser, browser-use, Playwright, manual driving, or any future browser tool.

5 Updated today
RayFernando1337
AI & Automation Solid

apm-review-panel

Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. The panel fans out to five mandatory specialists plus a test-coverage specialist (active on every PR that touches src/) plus three conditional specialists (auth, doc-writer, performance-expert), all running in their own agent threads, and a CEO synthesizer. The orchestrator is the sole writer to the PR: ONE recommendation comment, no verdict labels, no merge gating. The panel is advisory -- it surfaces findings, prioritizes follow-ups, and renders a ship-recommendation that the maintainer and author weigh. Activate when a non-trivial PR needs a cross-cutting recommendation (architecture, CLI logging, DevX UX, supply-chain security, growth/positioning, optionally auth, docs, perf, and test coverage, with CEO arbitration).

2,694 Updated today
microsoft
AI & Automation Solid

docs-sync

Use this skill whenever a pull request is opened, reopened, or synchronized in microsoft/apm to assess whether and how the documentation corpus must change to stay truthful with the proposed code change. Activate even when the PR title or body says nothing about docs -- the skill must run on every PR to detect silent drift between code and docs. Classifies impact as no-change, in-place edit (one to a few paragraphs), or structural change (new page or TOC reshape), then orchestrates a CDO + doc-writer + python-architect + editorial-owner + growth-hacker loop to produce a patch-ready advisory. Does NOT review code quality, security, or test coverage. Does NOT auto-merge or auto-push doc edits.

2,694 Updated today
microsoft
AI & Automation Listed

issue-fix-workflow

For a single triaged `<issue-tracker>` issue confirmed as a bug or feature, draft a fix against `<upstream>` on `<default-branch>`. Produces the failing test, the smallest production change, the targeted+module test runs, and the commit. The PR is NOT opened on autopilot; the human committer reviews, signs, and pushes. Hand-back artefact summarises branch, commits, test results, and scope.

17 Updated today
apache