← ClaudeAtlas

first-tree-github-scanlisted

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`.
agent-team-foundation/first-tree · ★ 7 · Code & Development · score 74
Install: claude install-skill agent-team-foundation/first-tree
# First Tree Github Scan Read these first: - `../first-tree/SKILL.md` - `../first-tree/references/functions.md` - `../first-tree/references/anti-patterns.md` ## What This Skill Does This skill is loaded by the daemon every time a new GitHub notification arrives and a per-task agent is spawned. The agent's job is to: 1. classify the notification 2. set the right `github-scan:*` label and post any necessary comment 3. choose exactly one of four routes (`reply` / `human` / `sync` / `write`) 4. emit a `GITHUB_SCAN_RESULT:` line so the daemon can dispatch downstream work This is not the operator-facing daemon guide. Humans running `first-tree github scan install` / `start` / `doctor` should use the CLI help, not this skill. ## When To Use This Skill | Use this skill | Use a different skill | | ------------------------------------------------ | ------------------------------------------------------------------------- | | The daemon spawned an agent for one notification | A user wants to onboard a repo → `first-tree-onboarding` | | You need the tag table or comment template | A user wants to audit drift → `first-tree-sync` | | You need the route taxonomy | A user wants to write tree content from a source → `first-tree-write` | | You need to decide whether to involve a human | An operator is debugging the daemon