
Claude Skills by microsoft
github.com/microsoftActivate when reviewing or modifying dependency resolution, lockfile schema, package downloaders, signature/integrity checks, file integration cleanup, or anything that could expose APM to dependency confusion, typosquatting, malicious packages, or token leakage.
Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY DEFAULT on any doubt (needs-design, decline, duplicate, defer, auto-handle, breaking- change, auth/security/governance surface, low arbiter confidence, unbounded scope, or a missing ...
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 ...
Use this skill to triage one microsoft/apm issue selected by the daily sweep, the `status/needs-triage` fast path, or manual dispatch. Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action.
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), gate every legit bug against PRINCIPLES.md via an apm-ceo strategic-alignment pass, cross-reference legit issues against open PRs, then open a fix PR (TDD + mutation-break gate) for greenfield bugs. Drive every PR -- community in-flight and own fix alike -- to mergeable by composing the shepherd-driver skill: one...
User: sweep the bug queue and drive whatever's mergeable to a ready-to-ship state. Orchestrator (activates batch-bug-shepherd skill by name; loads its SKILL.md as the working spec, including the operator-visibility contract in `assets/progress-diagram.md`, the Phase 1.5 strategic gate, and the composed shepherd-driver drive wave).
User: sweep the bug queue and drive whatever's mergeable to a ready-to-ship state. Orchestrator (no skill loaded; improvising from prose). OK, let me see what's in the bug queue. I'll start with the oldest open bug. Reading issue #134... it's about a CLI flag. Reading the code... this might be a quick fix. Let me try. Wrote a patch. Pushing. Now #156. This one looks like a config issue. Let me reproduce... yes, reproduces. Patching. check before patching #134 and #156. Let me check now. #134 ...
User: triage these bugs: #311 (CLI crash on empty config), #312 (auth: PAT lookup intermittent), #313 (deprecated --token-source still in help text). Orchestrator (activates batch-bug-shepherd skill by name; loads its SKILL.md as the working spec, including the operator-visibility contract in `assets/progress-diagram.md`, the strategic-alignment Phase 1.5 gate, and the composition edge to `../shepherd-driver/assets/shepherd-driver-prompt.md`).
User: triage these bugs: #311 (CLI crash on empty config), #312 (auth: PAT lookup intermittent), #313 (deprecated --token-source still in help text). Orchestrator (no skill loaded; improvising from prose). Let me look at #311 first. I'll fetch the issue body and see what's going on. `gh issue view 311` ... the user says the CLI crashes when the config file is empty. I'll try to reproduce... it does crash. I think I can patch the loader to handle empty input. Let me write a fix. Wrote a patch ...
Use this skill to write the PR description (PR body) for any pull request opened against microsoft/apm. Produces one self-sufficient GitHub-Flavored Markdown artifact: TL;DR, Problem (WHY), Approach (WHAT), Implementation (HOW), 1-3 validated mermaid diagrams, explicit trade-offs, validation evidence, and a How-to-test section -- with every WHY-claim backed by a verbatim quote from PROSE or Agent Skills. Activate when the user asks to "write a PR description", "draft a PR body", "open a PR", ...
refactor(auth): centralize token resolution behind AuthResolver
This PR refactors authentication. It centralizes token resolution into a new AuthResolver class and removes the --token-source flag.
chore(deps): bump click 8.1.7 -> 8.2.1
This bumps click from 8.1.7 to 8.2.1. I also adjusted a type hint in cli.py because click.Context is now generic. The lockfile was regenerated. This is a game-changing dependency upgrade for our type-checking story. Tests pass.
docs(quickstart): add 5-minute getting-started guide
Adds a quickstart guide to the docs.
Use only as the composed drive-to-merge stage of an APM batch orchestrator (batch-bug-shepherd, apm-issue-autopilot) that has already selected ONE open pull request in microsoft/apm. Do NOT use for user-facing requests to triage issues, sweep a queue, or open PRs -- the parent orchestrator owns those. Spawn one shepherd-driver subagent per PR: it classifies copilot-pull-request-reviewer[bot] inline review, runs the apm-review-panel, folds (by default) every recommendation inside the PR's stat...
Hermetic Agent Plugins lifecycle contract
A test skill from a marketplace plugin
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
No description provided
Test fixture for target resolution suite.
Best practices for building CLI applications with Click including commands, groups, options, and testing.
Best practices for Django web development including models, views, templates, and testing.
Best practices for Flask web development including routing, blueprints, and testing.