ai-onboard
$
npx mdskill add arcasilesgroup/ai-engineering/ai-onboard``` /ai-onboard tour # architecture overview /ai-onboard find auth # find where auth happens /ai-onboard history DEC-003 # decision archaeology /ai-onboard onboard # structured new-member onboarding ```
SKILL.md
.github/skills/ai-onboardView on GitHub ↗
--- name: ai-onboard description: "Onboards humans to a project: architecture tours, topic search, decision archaeology, structured new-team-member orientation. Read-only — never modifies code. Trigger for 'where does auth happen', 'what is the architecture here', 'history of this decision', 'onboard me to this repo', 'tour the codebase'. Not for agent session bootstrap; use /ai-start instead. Not for code-level explanation; use /ai-explain instead." effort: mid argument-hint: "tour|find [topic]|history [decision]|onboard" mode: agent tags: [onboarding, architecture, teaching, archaeology] model_tier: sonnet mirror_family: copilot-skills generated_by: ai-eng sync canonical_source: .claude/skills/ai-onboard/SKILL.md edit_policy: generated-do-not-edit --- # Onboard ## Quick start ``` /ai-onboard tour # architecture overview /ai-onboard find auth # find where auth happens /ai-onboard history DEC-003 # decision archaeology /ai-onboard onboard # structured new-member onboarding ``` ## Workflow Project onboarding, architecture tours, and decision archaeology. Optimized for the human, not the code. Reads everything, modifies nothing. Teaches understanding, not artifacts. 1. **`tour`** — Glob/identify directories, entry points, config; detect stack; present overview with ASCII diagram (component boundaries, dependencies, data flow); explain key patterns; `git log --oneline` for evolution; flag gotchas; suggest next paths. 2. **`find [topic]`** — Grep/Glob across source/config/docs; check `decision-store.json` and `.ai-engineering/specs/`; present file:line refs and context; answer "where does X happen?". 3. **`history [decision]`** — search `decision-store.json`, `git log --all --grep`, and `specs/`; reconstruct what was known, constraints, alternatives considered; assess current relevance; **do NOT recommend** — present analysis, let developer decide. 4. **`onboard`** — map structure; identify stack; discover patterns; find key files; review `.ai-engineering/standards/`; Socratic checkpoint per phase; personalize path to developer's interest. ## Dispatch threshold Dispatch the `ai-onboard` agent for any human-onboarding, archaeology, or codebase-tour request. Strictly read-only. The agent file (`.github/agents/onboard.agent.md`) is the dispatch handle; mode procedures and pedagogical principles live here. ## When to Use - New to a project and need orientation. - Want to understand component relationships and data flow. - Asking "why was X chosen over Y?". - NOT for writing code — use `/ai-build`. - NOT for generating docs — use `/ai-prose`. ## Common Mistakes - Making decisions for the developer — present tradeoffs, let them decide. - Writing code during a tour — guide is strictly read-only. - Over-quizzing — max 2 Socratic questions per interaction. - Teaching below the developer's level — match cues to Bloom's taxonomy. ## Examples ### Example 1 — onboard a new team member User: "give me an architecture tour of this repo, I'm new" ``` /ai-onboard tour ``` High-level overview, module ownership map, key boundaries, suggested deeper-dive paths. Read-only. ### Example 2 — decision archaeology User: "why did we choose hexagonal architecture for this codebase?" ``` /ai-onboard history hexagonal-architecture ``` Reads `decision-store.json` for the matching record, surfaces the original tradeoffs, links to the spec or commit that ratified it. ## Integration Calls: `/ai-explain` (3-tier depth). Reads: `decision-store.json`, `framework-events.ndjson`, `manifest.yml`. See also: `/ai-start` (agent session bootstrap), `/ai-explain` (code-level), `/ai-research` (external evidence). ## References - `.github/skills/ai-explain/SKILL.md` -- 3-tier depth model. - `.ai-engineering/manifest.yml` -- governance structure. - `.ai-engineering/state/decision-store.json` -- decision records. $ARGUMENTS
More from arcasilesgroup/ai-engineering
- ai-adviseProactive governance advisor — checks standards, decisions, and quality trends during development. Always advisory, NEVER blocks. Three modes: `advise` (post-edit), `gate` (pre-dispatch), `drift` (on-demand decision audit). Trigger for 'governance check', 'advise on this change', 'check for drift', 'is this aligned with active decisions', 'shift-left advisory'. Not for blocking gates — use /ai-verify. Not for narrative code review — use /ai-review.
- ai-analyze-permissionsUse when Claude Code keeps asking to approve commands you have already approved, when settings.local.json has grown large, or when you want to consolidate permission grants into wildcard patterns. Trigger for 'too many permission prompts', 'clean up permissions', 'audit my settings', 'consolidate allow rules'. Claude Code only — not available in GitHub Copilot, Antigravity, or Codex.
- ai-animationDesigns motion, transitions, and micro-interactions for UI components: spring animations, gestures, easing, staggers — taste-driven detail compounding. Trigger for 'animate this', 'add transitions', 'micro-interactions for', 'gesture design', 'swipe to dismiss', 'easing for this', 'stagger the'. Not for design systems; use /ai-design instead. Not for visual art; use /ai-visual instead. Not for testing animation code; use /ai-test instead.
- ai-autopilotDelivers large multi-concern specs and backlog runs autonomously: decomposes specs into sub-specs (or normalizes work items into a backlog DAG), deep-plans with parallel agents, builds a dependency DAG, implements in waves, runs a single final quality loop with one bounded quality-remediation pass (verify+guard+review on full changeset), delivers via PR. Trigger for 'implement spec-NNN end to end', 'autopilot this', 'autonomous delivery', 'decompose and ship', 'run the backlog', 'execute these GitHub issues', 'process the sprint backlog'. Invocation is the approval gate. Not for small or single-concern tasks; use /ai-build instead. Not for ambiguous requirements; use /ai-brainstorm first.
- ai-boardOperates the project board (GitHub Projects v2 or Azure DevOps): discovers configuration after install (fields, state mappings, process templates) and syncs work-item state at lifecycle transitions. Trigger for 'set up the board', 'configure our ADO board', 'discover board fields', 'move this issue to in-review', 'update the board', 'mark as in progress', 'sync the work item state'. Two subcommands: `discover` (post-install configuration write) and `sync` (lifecycle state transitions). Auto-invoked via `sync` by /ai-brainstorm, /ai-build, and /ai-pr; fail-open. Not for backlog execution; use /ai-autopilot --backlog instead.
- ai-brainstormForces rigorous design interrogation BEFORE any code: explores approaches, surfaces ambiguity, gathers evidence, produces an approved spec that becomes the contract for /ai-plan. Trigger for 'lets add X', 'how should we handle Y', 'whats the best approach', 'I am thinking about', 'what should we build for'. Not for existing approved specs; use /ai-plan instead. Not for execution; use /ai-build instead.
- ai-branch-cleanupCleans branches safely: switches to the default branch, prunes merged and squash-merged branches, syncs to remote, sweeps stale specs, rotates `.ai-engineering/runtime/` per retention policy. Trigger for 'tidy up', 'tidy branches', 'sync to main', 'delete old branches', 'start fresh', 'rotate runtime'. Auto-invoked by /ai-pr after merge. Not for committing changes; use /ai-commit instead. Not for code-level dead-code removal; use /ai-simplify instead.
- ai-buildCanonical implementation gateway: reads approved plan.md, resolves stack from manifest, deterministic-routes each task to its adapter, dispatches the build agent in an isolated worktree, runs TDD self-validation per task, then a single final quality loop with one bounded quality-remediation pass on the full changeset before /ai-pr. Trigger for 'go', 'start building', 'execute the plan', 'implement it', 'lets do this', 'build the plan', 'resume', 'continue'. Not without an approved plan; run /ai-plan first. Not for multi-concern specs needing decomposition; use /ai-autopilot instead. Not for a single function or subcomponent; use /ai-code.
- ai-codeWrites production code that satisfies stack-context standards on the first pass: interface-first design, backward-compatibility checks, lightweight self-review. Trigger for 'implement this', 'write the code for', 'add X to Y', 'build this function', 'make this work'. Not for tests; use /ai-test instead. Not for debugging; use /ai-debug instead. Not for refactoring; use /ai-simplify instead. Not for executing an approved plan end-to-end; use /ai-build (the gateway).
- ai-commitRuns the governed commit pipeline: auto-branches from protected, stages selectively, formats and lints, scans for secrets, gates docs, composes a conventional message, pushes. Trigger for 'commit my changes', 'save my work', 'push this to remote', 'stage these files', 'ship it'. Not for opening a PR; use /ai-pr instead. Not for branch hygiene; use /ai-branch-cleanup instead.