Long-running task loop using /loop (Claude Code dynamic mode) and ScheduleWakeup to re-enter with fresh context on each wake-up. Internally invokes harness-work through Agent. Trigger: long-running, loop, wake-up, autonomous. Do NOT load for: one-shot task execution, review, release, planning.

Team execution mode — backward-compatible alias for harness-work with team orchestration. Composer/composer 2.5 maps to the cursor backend.

Manage SSOT, memory, and cross-tool memory search. Guardian of decisions.md and patterns.md. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, migration, SSOT promotion, sync memory, save learnings, memory search, harness-mem, past decisions, or record this. Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging.

File cleanup and archiving. Tidies up bloated Plans.md, session-log.md, old logs, and state files. Trigger: /maintenance, cleanup, archive, organize, split session-log. Do NOT load for: implementation, review, release, new feature development.

HAR: Execute Plans.md tasks from single task to full parallel team run. Trigger: implement, execute, do everything, breezing, team run, parallel, composer, composer 2.5. Do NOT load for: planning, review, release, setup.

HAR: Sync Plans.md with implementation. Drift detect, marker update, retrospective. Trigger: sync-status, where am I, check progress. --snapshot for snapshots. Do NOT load for: planning, implementation, review, release.

HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI/Codex setup, harness-mem, mirror. Do NOT load for: implementation, review, release, planning.

HAR: Codex-native long-running loop runner. Uses a real background runner that executes one ready batch per cycle through Breezing by default, with status/stop controls. Trigger: long-running, loop, autonomous, background, Codex. Do NOT load for: one-shot implementation, normal review, release.

Extract recurring failure patterns from breezing orchestration logs and Judgment Ledger, emit failure-rule.v1 proposals with confidence scores. SSOT promotion to patterns.md or decisions.md is proposal-only — human-approval-required. Use when user mentions failure codifier, failure patterns, self-learning loop, codify failures, or failure-rule proposals. Do NOT load for: direct SSOT edits, auto-promotion, or implementation unrelated to failure analysis.

Configure and verify the Cursor backend for Claude Code Harness. Use when user invokes cursor:setup, wants Cursor as the local default implementation backend, or asks to check Cursor plugin/agent readiness. Distribution default remains opt-in; only local env/user settings are changed when explicitly requested.

Run a Cursor Composer review as an advisory second opinion while keeping the primary review verdict on the host brain. Use when user invokes cursor:review, asks Cursor to review, or wants composer to sanity-check a diff. Cursor never owns APPROVE/REQUEST_CHANGES.

Delegate a single write task to Cursor Composer via cursor-companion.sh inside an isolated worktree, then Lead-review the diff and cherry-pick. Use when user invokes cursor:do, says delegate to cursor, have composer write it, refactor with cursor, hand a file edit to Composer. Do NOT load for: planning, code review only, read-only investigation, or multi-task team runs (use breezing --cursor or cursor:ask instead).

Read-only delegate to cursor-agent (Composer) for questions, investigation, design discussion, and adversarial sanity checks. No worktree, no cherry-pick, no Lead diff review — cursor-agent is locked to ask mode and cannot write. Use when user says: ask cursor, cursor sanity check, get a second opinion, adversarial review, design discussion, investigate with cursor, cursor:ask. Do NOT load for: implementation, refactor, file edits, commit/push work, anything requiring write access (use cursor:do or breezing --cursor instead).

CI red? Call us. Pipeline fire brigade deploys. Use when user mentions CI failures, build errors, test failures, or pipeline issues. Do NOT load for: local builds, standard implementation work, reviews, or setup.

Quality guardrail for Claude/Codex update integration. Detects doc-only Feature Table additions and requires implementation or explicit planning. Internal use only.

Team execution mode (Codex host) — backward-compatible alias for harness-work with backend selection, including opt-in Cursor worker delegation. Composer/composer 2.5 maps to the cursor backend.

Browser automation through the repo agent-browser CLI. Explicit helper for navigation, forms, screenshots, scraping, and web-app checks. Prefer Browser Use or Playwright when available. Do NOT load for: sharing URLs, embedding links, or editing screenshot files.

Update the `@azure-tools/openai-typespec` package that supplies OpenAI TypeSpec definitions and views used by this repo. WHEN: "update OpenAI TypeSpec definitions", "bump openai-typespec", "refresh OpenAI TypeSpec models/views", "upgrade @azure-tools/openai-typespec". DO NOT USE FOR: general `.tsp` authoring, changing service APIs, or SDK generation. ALWAYS install with `npm i @azure-tools/openai-typespec --save-exact` (or `npm i @azure-tools/openai-typespec@<version> --save-exact`). WARN the user if the dependency version spec contains a caret (`^`).

Conversational agent that guides developers through creating complete Azure PowerShell cmdlet design specifications. Walks through an interactive interview covering service release details, contacts, scenarios, cmdlet syntax, parameter sets, piping, test cases, and spec links. Validates against PowerShell design guidelines, pre-populates fields from TypeSpec, and files the design as a GitHub Issue in Azure/azure-powershell-cmdlet-review-pr. USE FOR: 'create PowerShell design', 'PS design review', 'cmdlet design', 'PowerShell cmdlet review', 'submit PS design'. DO NOT USE FOR: SDK generation, TypeSpec authoring, releasing packages.

Turn a mission or lab idea into a fully researched GitHub issue spec on microsoft/agent-academy, then post it with the GitHub CLI. Use this skill whenever the user wants to propose new Agent Academy content before writing it — course missions (Recruit, Operative, Commander), standalone Special Ops, or Cowork Collective missions. Trigger whenever the user says "write a spec for a mission", "create an issue for a new lab", "I want to propose a Special Ops", "file a mission proposal", "spec out a lab", "open an issue for a new module", or hands over Microsoft Learn URLs and asks to turn them into an Agent Academy lab. This skill handles: mining source documentation, interviewing for scope, repo reconnaissance and duplicate detection across both docs and existing issues, frontmatter and tag validation, writing-style conformance, drafting the issue body, title conventions, milestone and assignee metadata, and posting plus verifying the issue via `gh`.