agent-team-foundation

first-tree-github

Follow / unfollow a GitHub entity (PR, Issue, Discussion, Commit) so its webhook events route into the current chat. Following your own just-created PR or issue is the DEFAULT: use IMMEDIATELY after you create one through any path (`gh pr create`, curl, GitHub MCP, the web UI) — creation never follows for you. Also use when the user asks to watch / track / follow / 关注 / 盯着 a PR or issue; when your current task is blocked on an upstream entity's progress; or to unfollow when the user explicitly asks to stop tracking (unfollow / 取消关注 / stop watching) or the task no longer concerns a followed entity.

first-tree-seed

One-time bootstrap for a brand-new, still-empty Context Tree. Delivers an initial top + second-level domain skeleton drawn from the bound source repos (PR1, user approves), then initial leaf-node content for each approved domain with explicit coverage reporting (PR2). Use right after Cloud onboarding provisions the workspace and tree repo. Refuses on any populated tree. Do not use to write an incremental update from a specific PR / doc / note — that is `first-tree-context`. Do not use to audit drift on an existing tree — that is `first-tree-sync`.

first-tree-context

Context Tree concept and writing guide. Covers what a Context Tree is, the source-system boundary, authorship read-discipline, and how to write tree updates from a specific source (PR / doc / note). Use `first-tree-read` for task-scoped tree reads before acting; use this skill when the user asks to reflect a PR / doc / note into the tree, update the tree from source material, or write a decision to the tree.

first-tree-onboarding

One-shot onboarding command for First Tree. Drives a repo or workspace from "no first-tree" all the way to "workspace.json bound, real content drafted, automation rule layer checked" — 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", "migrate this workspace to W1", 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 setup. Use this skill instead of running `first-tree tree init` from raw memory; it owns the initial-content drafting phase the CLI does NOT do, the W1 migration of legacy multi-mode workspaces, the Tier 0 / Tier 2 GitHub rule-layer install, and the final doctor checks. Agent-driven automation (AI PR review, agent template management, daemon install) is out of scope — owned by `first-tree cloud` and operator tooling.

first-tree-sync

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; or on a freshly onboarded tree. Sync owns broad drift discovery, structural skeleton repair, and substantive write hand-off across one tree. Use `first-tree-context` instead — not this skill — when the user has already named a specific PR / doc / note as the source material.

Code & Development Listed

first-tree-github-scan

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`.

first-tree-write

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 (link, paste, file) and wants the right durable tree change drafted, linked, and reviewed. This skill is source-driven and targeted. Use `first-tree-sync` instead — not this skill — when the user is asking "is the tree up to date?" with no specific source attached.

first-tree-cloud

Workspace collaboration skill — how an agent uses the First Tree CLI to talk to other agents in the workspace (`chat send` / `chat invite` / `chat history` / `chat list`), manage its own daemon and config, and connect a machine to First Tree Cloud (`login`). Includes the canonical Agent-to-Agent Communication Rules — when to wake another agent vs. when your final text is enough, plus the chat-context-missing fallback. Use whenever you need to send a chat message, decide whether another agent will see your output, install or operate the local daemon, or change a running agent's model / prompt / MCP / env / repos. For asking humans, use plain `chat send` for now — the dedicated NHA / `first-tree attention` CLI was removed in PR #747 and is being rebuilt as a message archetype by the `group-chat-unified-send` proposal.

Code & Development Listed

github-scan

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.

attention

How to ask humans well — when to raise an NHA, how to write the body, how to wait, what to do on no-response. Use whenever you (an agent) are about to ask a human something, escalate a decision, or notify a human that something already happened. NHA replaces ad-hoc "can someone…" chat messages with a typed event that has a target, a subject, a body, an optional response expectation, and a lifecycle.

first-tree

Read and update the Context Tree — the living source of truth for cross-domain decisions, constraints, and ownership in this organization. Use whenever a task touches strategic choices, cross-domain relationships, workspace-wide context, or Context Tree onboarding.

first-tree-read

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 from the bound context repo. Always inspect `first-tree tree tree --help` in the context repo first, then use `first-tree tree tree` filtering options to select candidate files; read the selected file contents with the agent's native file-reading capability.