agent-team-foundation

Bootstrap a team's Context Tree from readable source repos — for an onboarding "build / set up the Context Tree" task on a tree that has no domain structure yet: either no tree exists (creates and binds it) or a bound-but-empty tree (fills it). Supports clean explicit-Team invocation without a Workspace manifest, managed briefing, or prior setup-chat transcript, while preserving managed-workspace compatibility. Proposes an initial top-level + second-level domain structure for approval, then drafts initial leaf content — each as a reviewable PR/MR. Refuses unrelated re-seeding once the tree has domain structure and recovers Phase 2 from durable merged Tree state plus the same explicit sources.

Source-driven Context Tree write workflow for managed workspaces and clean BYO invocations. Use when a concrete source artifact such as a PR/MR, forge Issue, design doc, meeting note, review thread, or pasted source material should be reflected into the Context Tree. A clean BYO write also requires an explicit Team, an exact tree-read snapshot, current source/target context, and write intent. If no source artifact is available, there is no write task; ask the user for one.

Read the current repo's Context Tree before acting. Use when the user provides a task, topic, file path, feature name, bug, error, repo area, owner, or other signal and Codex needs to locate and read the relevant context files. Supports an explicit-Team BYO activation with one online authority check, one strict fetch, and one exact task snapshot, while preserving managed-workspace compatibility. Do not use for a Context Tree PR review or an explicit broad audit of stored tree content; `context-tree-review` and `context-tree-audit` exclusively own those snapshots.

Review a pull request against the workspace's bound Context Tree when a managed Context Review task supplies reviewPacketV1, a legacy Cloud App review wake-up arrives for an unmanaged PR, or a human explicitly asks to review a Context Tree PR. Managed tasks may repair within the PR author's declared scope and exact-head squash-merge after a complete successor-head review. Do not use for code PRs, ordinary tree reads or writes, or main-branch audits.

Use for a First Tree onboarding first chat, especially natural opening messages like "welcome aboard", "Please help me get started with First Tree", or "Please help me get settled into this team on First Tree." Also covers the production-scan fix first chat ("fix the launch blockers found by my production readiness scan"). Do not use for dedicated tree setup chats, ordinary chats, PR/MR reviews, repo scans, tree writes, or maintenance.

Act as an independent QA engineer for a software repository. Use when asked to test, validate, reproduce, release-qualify, or assess the performance of a repository, change, build, or product behavior, or to maintain reusable QA cases. Establish a complete runnable QA harness before scoping execution, validate real product behavior, report evidence honestly, and do not modify the product under test.

Audit stored normal content on the bound Context Tree's current default branch when a human explicitly asks to audit the whole tree, a domain, or specific normal paths for drift, contradictions, duplication, density, metadata, placement, or relationship problems. Do not use for ordinary task reads, source-backed writes, Context Tree PR reviews, or empty-tree setup.

File a GitHub issue about a defect in First Tree itself — the CLI, agent runtime, chat, web app, GitHub integration, or Context Tree tooling — onto First Tree's own GitHub-hosted public tracker (agent-team-foundation/first-tree). Use only when the user reports that First Tree the platform is broken, errored, crashed, or misbehaving and wants it reported (e.g. "First Tree has a bug", "chat send keeps failing", "the CLI crashed", "给 First Tree 开个 issue 反馈这个 bug"). The skill gathers reproduction steps, the First Tree client/CLI version, the chat ID, the reporting user's ID, OS, and error output, then opens the issue with the user's `gh` CLI. NOT for filing an issue into the user's own or bound source repo — that is an ordinary source-repo issue using the target forge CLI (`gh` for GitHub, `glab` for GitLab), not this skill — and not for bugs in the user's project code or third-party tools.

Canonical whitepaper and routing skill for First Tree. Explains what belongs in a Context Tree, how source or workspace roots, tree repos, and bindings relate, and how the current `first-tree tree` and `first-tree github scan` surfaces fit together. Use when you need shared First Tree concepts, need to choose between onboarding, sync, write, or GitHub notification workflows, or need the high-level CLI map before acting.

One-shot onboarding command for First Tree. Drives a repo or workspace from "no first-tree" all the way to "tree bound, real content drafted, daemon running, agent templates confirmed" — end to end, in one skill invocation. Trigger this skill when the user invokes `/first-tree-onboarding`, says "onboard this repo to first-tree", "set up first-tree here", "complete first-tree onboarding", or runs first-tree against an unbound repo or workspace. Also trigger when re-running on an already-bound repo to refresh skills, draft missing content, or reverify the daemon. Use this skill instead of running `first-tree tree init` from raw memory; it owns role-by-role branching, the initial-content drafting phase the CLI does NOT do, and the final doctor checks.

Audit and repair drift between merged code and the Context Tree in both directions — tree→code (does code still support tree facts?) and code→tree (does the tree register everything code now contains?). Use when the tree may be stale, wrong, outdated, or missing coverage for recent code changes; after a large merge; before release; on a freshly onboarded tree; or when a GitHub notification was routed `route=sync`. Sync owns broad drift discovery, structural skeleton repair, and substantive write hand-off across one tree. Use `first-tree-write` instead when the user already gave you a specific PR / doc / note to write into the tree.

Operate the `first-tree github scan` CLI — the GitHub notification daemon and inbox runtime. Use whenever you need to run, start, stop, inspect, poll, or debug github-scan; view or respond to GitHub-triggered work from the terminal; or wire up the github-scan statusline hook.

Agent skill for handling a single GitHub notification spawned by the First Tree github-scan daemon. Use when an agent needs to decide how to tag, comment on, escalate, or hand off a PR, issue, review request, mention, or CI event, and when it needs to choose between handling on GitHub or routing to `first-tree-sync` / `first-tree-write`. This is the agent behavior spec, not the human CLI operations guide for the daemon — for that, run `first-tree github scan --help`.

Write Context Tree updates from explicit source material — code PRs, design docs, meeting notes, raw text. Use when the user gives you a concrete source and wants the right durable tree change drafted, linked, and reviewed. This skill is source-driven and targeted; use `first-tree-sync` instead for broad drift audits with no specific source.

GitHub notifications in Claude Code. See your notifications in the statusline, browse your inbox, get AI-powered summaries and suggested actions, and respond without leaving your terminal. Use when: "notifications", "inbox", "github messages", "what needs my attention", "check my PRs", "check my reviews".

Update breeze to the latest version. Pulls from main (or latest release tag when available). Re-runs setup if needed. Use when: "update breeze", "breeze update", "upgrade breeze", "pull latest".

Open a live activity log for breeze notifications. Shows all events (new notifications, status changes, agent actions) streaming in real time with clickable GitHub links. Runs in a new terminal window. Use when: "watch", "breeze watch", "show log", "activity log", "notification log".

Scan a React or Next.js repository before launch for high-confidence visible UI and interaction combinations that make a product feel like an uncustomized AI/default template. Use for source-based AI-tell, AI-slop, vibe-code polish, or pre-release credibility reviews of static JSX, CSS, and Tailwind, including a read-only rescan after fixes. Report product-facing tells only; never infer AI authorship, provenance, or an AI percentage.