ai-board
$
npx mdskill add arcasilesgroup/ai-engineering/ai-board``` /ai-board discover # one-time configuration discovery /ai-board discover --refresh # force re-discovery /ai-board sync in_progress #45 # transition GitHub issue /ai-board sync in_review AB#100 # transition Azure Boards work item ```
SKILL.md
.github/skills/ai-boardView on GitHub ↗
--- name: ai-board description: "Operates 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." effort: cheap argument-hint: "discover [--refresh] | sync <phase> <work-item-ref> [--comment text]" mode: agent tags: [board, discovery, sync, work-items, configuration] model_tier: haiku mirror_family: copilot-skills generated_by: ai-eng sync canonical_source: .claude/skills/ai-board/SKILL.md edit_policy: generated-do-not-edit --- # Board ## Quick start ``` /ai-board discover # one-time configuration discovery /ai-board discover --refresh # force re-discovery /ai-board sync in_progress #45 # transition GitHub issue /ai-board sync in_review AB#100 # transition Azure Boards work item ``` ## Subcommands `/ai-board` carries two subcommands that previously lived as separate skills (`/ai-board discover` and `/ai-board sync` — collapsed in spec-127 D-127-10 to a single skill with subcommand routing). | Subcommand | Detail file | Purpose | | ---------- | ----------- | ------- | | `discover` | [`discover.md`](discover.md) | Post-install discovery of board configuration (fields, state mappings, process templates) — writes atomically to `manifest.yml`. | | `sync` | [`sync.md`](sync.md) | Lifecycle state transitions on the project board (`refinement` → `ready` → `in_progress` → `in_review` → `done`). Auto-invoked by `/ai-brainstorm`, `/ai-build`, and `/ai-pr`. Fail-open: never blocks the calling workflow. | ## Workflow The skill body owns the user-facing routing contract. Detail files own the per-subcommand procedure. Step 0 (load contexts): read `.ai-engineering/manifest.yml` `providers.stacks`; load `.ai-engineering/overrides/<stack>/conventions.md` for each stack and `.ai-engineering/overrides/_shared/conventions.md`; load `.ai-engineering/team/*.md` for team conventions. 1. Detect subcommand from the first positional argument. 2. If `discover`: read [`discover.md`](discover.md) and execute. Returns when manifest is updated atomically (or aborts with no partial write on failure). 3. If `sync`: read [`sync.md`](sync.md) and execute. Returns the configured state transition result; fail-open on auth, network, or missing-mapping errors. 4. If neither: print the subcommand table above and ask the user which mode to use. ## When to Use - After initial framework install (`ai-eng install`) — run `/ai-board discover`. - When board configuration changes (new project, new fields) — run `/ai-board discover --refresh`. - At lifecycle transitions — run `/ai-board sync <phase> <ref>` (or rely on auto-invocation from `/ai-brainstorm`, `/ai-build`, `/ai-pr`). - Suggested by `/ai-start` when board config is missing. ## Examples ### Example 1 — first-time discovery on GitHub project User: "configure board sync for our GitHub Projects v2 board" ``` /ai-board discover ``` Detects the active Projects v2 board, queries Status field options, infers mapping from canonical phases (refinement/ready/in_progress/in_review/done), writes the config block atomically into `manifest.yml`. ### Example 2 — manual transition to in-review User: "move issue #123 to in-review on the board" ``` /ai-board sync in_review #123 ``` Looks up the project item, applies the configured state transition, optionally posts a comment with context. Fail-open if provider CLI is not authenticated. ## Common Mistakes - Calling `/ai-board` without a subcommand — the skill needs `discover` or `sync` to dispatch. - Treating `sync` failures as blockers — the subcommand is fail-open by design; calling skills should log and proceed. - Running `discover` without authentication — `gh auth status` or `az account show` must succeed first. ## Integration Called by: user directly (both subcommands); `/ai-start` (suggests `discover` when config missing); `/ai-brainstorm`, `/ai-build`, `/ai-pr` (auto-invoke `sync` for lifecycle transitions). Reads + writes: `.ai-engineering/manifest.yml` `work_items` section. Pairs with: GitHub CLI (`gh`), Azure CLI (`az`). See also: `/ai-autopilot --backlog` (consumes the configured board to absorb backlog items). $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-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.
- ai-constitutionInterviews the operator to produce a project-identity CONSTITUTION.md (Mission / Stakeholders / Vocabulary / Prohibitions / Compliance gates / Anti-goals / Boundaries / Escalation / Language / Lifecycle phase). Trigger for 'set up the constitution', 'define project identity', 'who is this project for', 'what does this project never do', 'amend the constitution'. Not for AI-behaviour rules — those live in CANONICAL.md / AGENTS.md. Not for spec governance; use /ai-governance instead.