Emasoft

Animation sandbox — ONE transition shown in isolation with live duration + easing tuners, a Replay button, and an export of the tuned {duration, easing} values. Moving the slider or easing select re-runs the transition live; the tuned values export through the runtime selection channel. Light + dark, reduced-motion-aware. Use when tuning a transition, dialling in animation timing, picking an easing curve, or building an easing/duration playground. Trigger with 'animation sandbox', 'tune a transition', 'easing tuner', 'duration slider', 'easing playground', 'pick an easing curve'.

Code diff surface — unified + split diff blocks, twin-column gutter, semantic diff tints, PR review pages with line-anchored comments. Use when scaffolding a code diff, a side-by-side review, a PR / postmortem / changelog page. Trigger with 'diff', 'split diff', 'unified diff', 'PR review', 'code review', 'pull request', 'postmortem', 'hunk', 'line-diff'.

Code-as-data and editable-fence surface — distinguishes pre tag as code vs data (CSV/JSON/YAML), the data-ve-no-gutter opt-out, and the contenteditable code-editor family. Use when scaffolding a CSV/JSON data block, a live editor, an opt-out gutter block, or deciding fenced vs free-form. Trigger with 'CSV', 'JSON data', 'YAML data', 'data fence', 'opt-out gutter', 'contenteditable', 'JSON editor', 'live edit code', 'no-gutter'.

Router skill for the code-display surface — dispatches to 4 sibling skills: code-syntax, code-diff, code-snippets, code-fences. Use when scaffolding ANY code-display surface and you don't yet know which sub-surface fits. Trigger with 'code', 'code block', 'syntax highlight', 'diff', 'PR review', 'walkthrough', 'tabbed code', 'CSV data', 'JSON editor'.

Multi-perspective code composition surface — collapsed walkthroughs, snippet-on-hover, tabbed multi-perspective panels, click-step-to-code, N-column compare layouts. Use when scaffolding a code walkthrough, explainer, tutorial, or click-driven code reveal. Trigger with 'walkthrough', 'tabbed code', 'click reveal code', 'snippet', 'explainer', 'tutorial steps', 'compare approaches'.

Visual chrome + inline hand-wrap for code blocks — block 3-state hover/select model, blueprint theme, slate-bg panel, file-path / tab-bar headers, inline code chip, 4-class hand-wrap palette, keyword-arrow highlight, plus the author-vs-runtime + light/dark cross-cutting discipline. Use when styling a code block's container, adding a file-path or tab-bar header, hand-wrapping inline code without the JS tokenizer, or wiring light/dark token mirrors. Trigger with 'block hover state', 'blueprint theme', 'slate panel', 'file-path header', 'tab-bar', 'inline code chip', 'hand-wrap', 'keyword highlight', 'light dark code mirror', 'author vs runtime'.

Tokenizer + runtime engine for syntax-highlighted code — dependency-free 7-language tokenizer, 12-token palette, per-line gutter, copy button, drag-paint selection, byte-fidelity integrity probe. Use when configuring tokenizer / language detection, defining the 12 `ve-tok-*` token roles, or debugging gutter / copy-button / line-selection chrome. Trigger with 'tokenizer', 'language detect', 'line numbers', 'copy code button', 'gutter', 'token palette', 'code line selection', 'integrity probe', 'highlightLine'.

Syntax-highlight surface — dependency-free tokenizer, 12-token palette, gutter, copy, light + dark themes. Use when scaffolding a syntax-highlighted code block, configuring tokenizer / language detection, defining `--ve-code-*` theme tokens, or debugging gutter / copy / selection chrome. Trigger with 'syntax highlight', 'code block', 'tokenizer', 'line numbers', 'copy code button', 'gutter', 'token palette', 'language detect'.

Orchestrator for any web, UI, slide, prototype, or design task. Enforces three hard rules — (1) gather context, (2) produce ≥3 variants, (3) reject AI-slop — and routes to executors. Triggers on "design a page", "landing page", "mockup", "UI for", "prototype", "wireframe", "slide deck", "dashboard", "website". Plan phase runs in ASCII via /amw-sketch; HTML follows approval. Use when the user requests any visual design artifact. Trigger with /amw-sketch.

Author, lint, extract, audit, and convert DESIGN.md design-system specifications. Triggers on "create DESIGN.md", "lint DESIGN.md", "extract DESIGN.md from URL/Tailwind/codebase", "audit DESIGN.md", "DESIGN.md companions". Does NOT trigger on generic "design system", "extract design tokens" — those route to amw-design-principles or amw-design-extract. Use when authoring, linting, or converting a DESIGN.md spec. Trigger with /amw-design-md-create.

Convert a free-text system description into a layered architecture diagram (graph JSON, SVG, or PNG). Triggers on "draw my architecture", "architecture diagram for X", "layered diagram", "export architecture as SVG/PNG", "component diagram". Does NOT trigger on "design", "sketch the UI" — routes to design-principles / diagram-editorial. For Mermaid, use `amw-mermaid-diagram`. Use when converting a system description into a layered diagram. Trigger with /amw-create-or-modify-svg-diagram.

Structural comparison of two diagrams — diff two flowcharts, compare v1/v2, find what changed, cross-format diagram diff. Triggers on "compare these diagrams", "diff two flowcharts", "what changed between v1 and v2", "structural diff of two diagrams". Source formats may differ (ASCII vs Mermaid is valid). PNG-as-input is refused. Does NOT claim generic design vocabulary — those route to design-principles. Use when comparing two diagrams structurally. Trigger with /amw-compare-diagrams.

Cross-format diagram conversion — convert a diagram from one format to another across the 5-format matrix (ASCII, HTML, SVG, Mermaid, PNG). Triggers on "convert this diagram to X", "turn my ASCII into SVG", "convert flowchart to mermaid", "export diagram as PNG". PNG-as-source is refused. Does NOT claim generic design vocabulary — those route to design-principles. Use when converting a diagram across the 5-format matrix. Trigger with /amw-convert-any-diagram-format.

Editorial-quality HTML+SVG diagrams with brand-matched styling — 13 types (architecture, flowchart, sequence, state, ER, timeline, swimlane, quadrant, nested, tree, layer, Venn, pyramid/funnel). Triggers on "sequence diagram", "ER diagram", "blog-ready architecture diagram". NOT for generic design, freeform SVG, or graph JSON — routes to design-principles / svg-creator / diagram-architecture. Use when creating an editorial diagram. Trigger with /amw-create-or-modify-html-diagram.

Authoritative spec for ASCII / HTML / SVG / Mermaid formats, IR schema, conversion matrix, validation dispatcher, modify/diff pipelines. Triggers on "diagram IR schema", "format detection", "conversion matrix", "IR-level diff", "Mermaid format spec". Does NOT trigger on diagram creation — routes to ascii-creator / svg-diagram / html-diagram. References-only — NEVER emits diagrams. Use when looking up IR schema or format specs. Trigger with "diagram IR schema".

Natural-language request to SVG diagram primitives — flowcharts, architecture diagrams, system illustrations with nodes, edges, arrowheads. Triggers on "draw a flowchart of X", "SVG diagram of X", "render data flow as SVG", "draw the architecture as SVG", "node-and-arrow diagram". Does NOT trigger on broad design vocabulary — those route to `design-principles`. Use when authoring an SVG flowchart or architecture diagram. Trigger with /amw-create-or-modify-svg-diagram.

Add a new component (skill / agent / command / hook / mcp) to an existing plugin. Use when scaffolding a single component into a plugin without re-running the generator. Used dynamically via the-skills-menu (TRDD-478d9687).

Add plugin dependencies to a target plugin (explicit --add specs or --from copy from another plugin's plugin.json). Use when adding/copying plugin.json::dependencies entries with atomic rollback on regression. Used dynamically via the-skills-menu (TRDD-478d9687).

Add a new hook entry to hooks/hooks.json in an existing plugin (idempotent — skips duplicate entries; cross-platform-aware). Use when adding a new event-handler that must run identically on Linux/macOS/Windows. Used dynamically via the-skills-menu (TRDD-478d9687).

Bump plugin version and run the full publish pipeline (plugin.json, pyproject.toml, README badge, CHANGELOG, push, release). Use when bumping version + publishing the current plugin via publish.py. Used dynamically via the-skills-menu (TRDD-478d9687).

Routes the /cpv-main-menu Stop-hook menu via scripts/print_menu.py + claude-menu-system. Used dynamically via the-skills-menu (TRDD-478d9687) — used by the /cpv-main-menu flow. Use when navigating CPV's many commands via a single entry point.

Deterministic codemod CLI — bulk-fix backtick-path to markdown-link, add TOC stubs, dedup blank lines, and other mechanical text transforms (issue 17). Zero LLM cost. Use when mechanical fixes outnumber semantic ones. Used dynamically via the-skills-menu (TRDD-478d9687).

Link an existing plugin to an existing marketplace (local or GitHub source). Use when appending an existing plugin to a marketplace.json. Used dynamically via the-skills-menu (TRDD-478d9687).

Pack a folder of standalone components (skill/agent/command/hook/mcp/lsp/monitor/output-style) into a new installable plugin. Use when bundling loose components into a single publishable plugin. Used dynamically via the-skills-menu (TRDD-478d9687).

Control the janitor's never-stop continue-nudge for this session — every due heartbeat prints a resume cue telling the agent to keep working on its pending task instead of silently idling between turns. The nudge is ON BY DEFAULT (user directive 2026-07-16); this skill re-asserts it after an opt-out, or turns it off. Trigger with /janitor-keep-going, "keep going", "never stop", "don't stall between turns"; add "off" to disable this session's full-mode nudge.

MEMORIZE — capture a durable decision/fact into the project's memory WIKI as a navigable page, not a loose note. Use after a bug-autopsy gotcha, a design/architecture decision, a project constraint not derivable from code, a confirmed user preference, or when the user says "remember this", "memorize this", "save a memory". Finds the right existing wikimem page first so it never duplicates; only when none fits, creates a HUB / ASPECT / COMPONENT page via the expand/reduce decision, wires it into the See-also web, and indexes it by symptom. The MEMORIZE leg of the wiki-memory protocol.

CONSOLIDATE (MERGE) executor — fuses two duplicate memory notes about the SAME subject + same type into one page (dedup lessons, redirect backlinks, keep the oldest origin date), through the crash-safe transaction core, never editing a live page. ABSTAINS on uncertainty, cross-type/cross-scope/two-hub, or a third page sharing the subject. Use on a [janitor-memory-consolidate] marker, or "consolidate / merge / deduplicate the memory", "two notes cover the same thing", "fold these memory pages together".

ATOMIZE executor — the autonomous pass that migrates a FREE-PROSE wikimem page into first-class ATOMS: inserts a LEADING block-property marker `^<id> [keywords: …]` above each durable fact so memgrep recalls it individually by its keywords and returns its full per-atom record. Purely ADDITIVE + transaction-gated + verified — never drops or rewords a fact. Runs on a [janitor-memory-atomize] marker, or "atomize this page", "give the memory facts their atom markers".

HARVEST executor — the daily NON-DESTRUCTIVE chore that MIRRORS newly-created harness BUFFER memories into the curated wiki. MEMORY.md + the raw notes at the scope root are the harness-owned buffer (auto-loaded each session); the janitor never touches them. For each RAW buffer note not yet mirrored, RECALL its subject across memory/wikimem/ then UPDATE-or-CREATE a curated wikimem/<name>.md copy and stamp a watermark. The buffer is left 100% intact (separate parallel copies coexist). Use on a [janitor-memory-harvest] marker, or "harvest the memory", "mirror new MEMORY.md memories into the wiki".

Arms or renews the ai-maestro-janitor heartbeat cron. Use when first installing the plugin, upgrading from pre-stub (≤ v0.4.10), or in response to a [janitor-renew] nudge before the 7-day auto-expiry. Trigger with /janitor-arm or "arm the janitor heartbeat".

Stops the ai-maestro-janitor heartbeat cron. Use when pausing janitor activity without uninstalling, debugging heartbeat behaviour, or switching projects. Trigger with /janitor-disarm, "stop the janitor", or "kill the heartbeat".

The janitor's support-ticket console (TRDD-CGYMUKO6). Inspect the incident queue: what the janitor has found, what it is repairing, what failed, what needs a human, and how much of the daily dispatch budget is left. Also retry a stuck ticket or cancel one you do not want. Use when the user asks what the janitor is working on, when a `[ticket]` line appears in the heartbeat, or when a ticket is reported as NEEDS A HUMAN.

Use when managing design document states or lifecycle transitions. Trigger with design lifecycle or state transition request. Loaded by ai-maestro-architect-agent-main-agent

Use when handling edge cases or shared operations in architect communication. Trigger with communication ops request. Loaded by ai-maestro-architect-agent-main-agent

Use when implementing inter-agent messaging or design document protocols. Trigger with communication pattern or messaging request. Loaded by ai-maestro-architect-agent-main-agent

Use when persisting decisions, patterns, and constraints across sessions. Trigger with session memory or handoff request. Loaded by ai-maestro-architect-agent-main-agent

Use when recording stack choices, constraints, or managing handoffs. Trigger with session memory ops request. Loaded by ai-maestro-architect-agent-main-agent

Use when researching external APIs, libraries, and services. Trigger with API research request or library investigation task. Loaded by ai-maestro-architect-agent-main-agent

Use when designing CI/CD pipelines, GitHub Actions, or release automation. Trigger with CI/CD design request or pipeline task. Loaded by ai-maestro-architect-agent-main-agent

Use when creating, searching, or validating design documents. Trigger with document management or UUID generation request. Loaded by ai-maestro-architect-agent-main-agent

Design, generate, evaluate, and ship Apple-platform APP ICONS — from a conversion-optimized 1024×1024 master to an iOS 26 Icon Composer .icon bundle (light/dark/tinted/clear variants), AppIcon.appiconset, or macOS .icns — plus IN-APP icon glyphs (SF Symbols / Iconify imagesets). Covers small-size readability and App Store tap-through (TTR) A/B testing. Use when asked for: "app icon", "icon design", "generate app icon", "AppIcon.appiconset", ".icns", "Icon Composer", "liquid glass icon", ".icon package", "ictool", "actool icon", "dark/tinted icon variant", "icon A/B test", "validate app icon", "icon white border", "missing icon size", "SF Symbol to SVG", "menu bar icon", "imageset".

App Store Optimization (ASO) for iOS App Store and Google Play — keyword research and placement, metadata writing within exact character limits, screenshot/icon/preview conversion, review tactics, competitor intelligence, localization, A/B testing, and store-policy compliance, with App Store Connect API (asc CLI) and iTunes Search API recipes. Use when asked to improve app discoverability, rank for keywords, optimize a title / subtitle / keywords field, audit a listing, or raise install conversion. Triggers: "ASO", "keyword research", "rank in the app store", "optimize my app listing", "app store keywords", "screenshot conversion", "increase installs", "will this get rejected".

Build, archive, validate, upload, and submit iOS/iPadOS/macOS/visionOS apps to App Store Connect via fastlane (match/gym/pilot/deliver), xcrun altool, or EAS (eas build / eas submit) for native Swift, React Native, Expo, Flutter, and Capacitor projects. Covers .xcarchive, ExportOptions.plist, code signing, PrivacyInfo.xcprivacy, TestFlight, ASC REST API metadata and screenshots, JWT-signed API keys, App Review submission, rejections, ITMS-XXXXX errors, macOS notarization (notarytool), and Xcode Cloud. Use when asked to submit to the App Store, ship to TestFlight, archive and upload, fastlane release, eas submit, fix code signing or ITMS-90xxx, notarize a Mac app, or respond to a rejection.

Design, build, review, or AUDIT interfaces that follow Apple's Human Interface Guidelines (HIG) for iOS 26, iPadOS, macOS, watchOS, tvOS, visionOS — Liquid Glass era, Swift 6 / SwiftUI, UIKit, AppKit. Use for any request to make a UI feel native to Apple — even when "HIG" is not said — including web/Figma mockups and Flutter/React Native Cupertino UI. TRIGGER on: "iOS app", "macOS app", "visionOS", "SwiftUI", "HIG", "Apple design", "SF Symbols", "Dynamic Type", "Dark Mode", "Liquid Glass", "safe area", "accessibility review", "tap target", "audit my UI against the HIG", "should I use a modal here". Run Phase 0 (targeting + project-context check) before generating code or a spec.

Translate Figma designs into native SwiftUI code (iOS 26 / Swift 6) by reading the Figma file directly through the Figma MCP — no PNG exports or screenshots. Sets up the MCP read→build→preview→compare→iterate loop, maps Figma layout/tokens to native components and HIG values, enumerates screen states, and verifies results numerically with accessibility frames. Use when building or matching Figma frames in SwiftUI, polishing a screen to a comp, batch-importing designed screens, or extracting design tokens. Triggers: "build this Figma frame", "match this Figma design in SwiftUI", "turn my Figma into iOS code", "figma to swiftui", "extract design tokens from Figma".

Apple-platform accessibility (a11y) for SwiftUI, UIKit, and AppKit — iOS/iPadOS 17–26, macOS, watchOS, tvOS, visionOS, Swift 6. VoiceOver (labels, hints, traits, custom actions, rotors), Dynamic Type and @ScaledMetric, WCAG 2.1/2.2 color contrast, Reduce Motion, 44pt touch targets, Assistive Access, NSAccessibility, automated audits (Accessibility Inspector, performAccessibilityAudit, CI). Use when implementing or auditing accessibility, adding VoiceOver support, handling Dynamic Type, or asked "is this accessible?" / "audit my UI for a11y", or for App Store / ADA / EAA compliance. Triggers: accessibility, a11y, VoiceOver, accessibilityLabel, screen reader, WCAG, Dynamic Type.

Choose and implement the right iOS/macOS app architecture (Swift 6 / iOS 26 era). A decision compass for picking a stack (MVC / MVVM+Coordinator / MVVM+Router / Clean / VIPER / MVI / TCA) plus implementation guidance — ViewModels, Use Cases, Repository, reducers, navigation (Coordinator vs NavigationStack/Router), dependency injection (manual / Factory / Swinject), SPM modularization, and @MainActor/actor/Task concurrency placement. Use when asked "which architecture should I use", "MVVM or Clean", "how do I structure this iOS app", "set up Clean Architecture", "add a Coordinator", "refactor this Massive View Controller", or when starting a new iOS/macOS project and the stack is undecided.

Grow an iOS/iPadOS app: paid UA and ad attribution under ATT (SKAdNetwork v4, AdAttributionKit, AppsFlyer/Adjust/Branch/Singular, Apple Search Ads, Meta/TikTok/Google), subscription pricing and paywall price display (StoreKit 2 + RevenueCat), PPP territory pricing, CRO, launch (Product Hunt, App Store featuring), referral/viral loops (K-factor), retention/churn/LTV, marketing psychology. Use when: "market my app", "grow my app", "user acquisition", "paid ads", "ROAS", "CAC", "ATT", "SKAdNetwork", "conversion value", "MMP", "Apple Search Ads", "pricing strategy", "paywall", "free trial", "PPP pricing", "referral program", "launch strategy", "retention", "churn", "LTV".

Drive an agent's HTML dashboard side panel via the frozen aimaestro-panel.sh CLI — push HTML or a live URL, open/close/refresh the panel, check how many dashboard clients are connected, and drain feedback events the panel's HTML posted back. Use when an agent wants to render a status view, a form, or a live page in its own dashboard panel. Trigger with /ama-panel, 'show this in my side panel', 'push this HTML to my panel', 'check if anyone is watching my panel', 'read panel feedback'. CRITICAL gotcha: 'delivered: 0' from open/set means the content was DROPPED, not queued — always check status first when delivery matters. Loaded by ai-maestro-plugin

Drive an agent's own terminal and read its own activity state via the frozen aimaestro-session.sh CLI — send or enqueue an allowlisted slash command (works even while busy/hibernated), type raw text into a live pane, read the 5-state activity, and read/answer a pending permission or AskUserQuestion prompt. Use when an agent must act on itself: arm its janitor heartbeat, answer a pending prompt, check if idle/busy, or queue work for later. Trigger with /ama-session, 'queue a command for when I'm idle', 'answer my pending prompt'. Not for reconfiguring an agent (role/plugin/team) — that is ai-maestro-agents-management. Loaded by ai-maestro-plugin

Search, read, verify, and server-mediated mutate TRDDs via the aimaestro-trdd.sh CLI — the AI Maestro dashboard's authorization-aware view of the design/ corpus. Write verbs (edit / approve / refuse / promote / archive) are STRICT, gated by each TRDD's min-approval-requirement with a hard self-approval ban. Use when server-mirrored state or server-side authorization matters: the dashboard kanban, approving a proposal, confirming an approval is real. Trigger with /ama-trdd-server, 'approve this TRDD', 'search TRDDs on the dashboard'. For local design/ file editing use ama-trdd-find/write/update/transition. Loaded by ai-maestro-plugin

Recall prior knowledge from the markdown wiki-memory corpus via memgrep and the janitor's global recall skills. Use before acting on a recurring problem, a design decision, or a repeated alert. Trigger with /memory-search. Loaded by ai-maestro-plugin

Manage AI agent lifecycle via CLI. Use when creating, listing, deleting, configuring, or looking up an agent's consolidated config (launch args, title, role-plugin, teams, GitHub repo, Docker, pending tasks, AID public key). Trigger with /ai-maestro-agents-management. Loaded by ai-maestro-plugin

Use when managing teams or governance titles. Trigger with /team-governance. Loaded by ai-maestro-plugin

Manage team kanban boards and tasks. Use when creating, moving, filtering, getting, or editing tasks. Trigger with /team-kanban. Loaded by ai-maestro-plugin

RETIRED — the AI Maestro docs indexing backend (the docs-search/docs-index shell wrappers) is permanently gone. Use the tldr CLI (tldr-code skill) for codebase docs/signatures instead. Trigger with /docs-search. Loaded by ai-maestro-plugin

Use when sending inter-agent messages. Trigger with task assignment, status report, or escalation needs. Loaded by ai-maestro-orchestrator-agent-main-agent

Use when managing modules during Orchestration Phase. Trigger with module add, modify, or reassign requests. Loaded by ai-maestro-orchestrator-agent-main-agent

Use when breaking down tasks for human developers. Trigger with task decomposition requests. Loaded by ai-maestro-orchestrator-agent-main-agent

Use when coordinating remote AI agents via AI Maestro messaging. NOT for human coordination. Trigger with agent delegation or multi-agent requests. Loaded by ai-maestro-orchestrator-agent-main-agent

Use when verifying implementations. Trigger with verification, testing, or evidence requests. Loaded by ai-maestro-orchestrator-agent-main-agent

Use when running Plan-then-Execute workflows. Trigger with plan-execute or two-phase requests. Loaded by ai-maestro-orchestrator-agent-main-agent

Use when running orchestration phase commands. Trigger with start, monitor, or cancel orchestration requests. Loaded by ai-maestro-orchestrator-agent-main-agent

Use when applying GitHub labels. Trigger with label query or assignment requests. Loaded by ai-maestro-orchestrator-agent-main-agent

Use when applying or checking GitHub labels for agent assignment and status tracking. Trigger with label management or taxonomy lookup requests. Loaded by ai-maestro-chief-of-staff-main-agent

CHIEF-OF-STAFF's role in the PRRD / TRDD / Kanban workflow. COS does NOT own kanban columns directly — it ROUTES messages and proposals between the team layer (ORCH/ARCH/INT/MEMBER) and the governance layer (MANAGER). Use when COS forwards a PRRD proposal, relays approval decisions, broadcasts TRDD status updates, or aggregates team status for AMAMA.

Use when sending failure notifications after operation errors. Trigger with failure events, error reporting, or incident notification. Loaded by ai-maestro-chief-of-staff-main-agent

Use when managing team registry, inter-agent messaging, role boundaries, or sub-agent delegation. Trigger with team coordination tasks. Loaded by ai-maestro-chief-of-staff-main-agent

Use when requesting or processing agent acknowledgments before proceeding with operations. Trigger with acknowledgment requests or ACK timeout handling. Loaded by ai-maestro-chief-of-staff-main-agent

Use when replacing a failed agent with a new instance. Trigger with agent replacement or failover events. Loaded by ai-maestro-chief-of-staff-main-agent

Use when handling emergency work handoff from failed agents. Trigger with agent failure handoff or task blocker routing. Loaded by ai-maestro-chief-of-staff-main-agent

Use when detecting or classifying agent failures. Trigger with health check failures, heartbeat timeouts, or error events. Loaded by ai-maestro-chief-of-staff-main-agent

Use when performing structured AI-driven PR reviews — 8-dimensional rubric (correctness, security, performance, test coverage, maintainability, docs, style, dependencies) with verdict ladder (approve/request-changes/comment) and severity classification. Trigger with /amia-ai-pr-review, 'review this PR', or any PR-evaluation request. Loaded by ai-maestro-integrator-agent-main-agent.

Use when integrating GitHub Projects. Trigger with GitHub sync, label setup, or PR workflow requests. Loaded by ai-maestro-integrator-agent-main-agent.

Use when retrieving PR context including metadata, diff, and changed files for code review planning. Trigger with /review-pr [PR_NUMBER]. Loaded by ai-maestro-integrator-agent-main-agent.

Use when composing inter-agent handoff payloads, session state snapshots, multi-agent coordination protocols, or referencing shared message templates / record-keeping formats. Trigger with handoff, delegation, acknowledgment, completion report, blocker escalation, or routing decision requests. Loaded by ai-maestro-integrator-agent-main-agent.

GitHub label taxonomy reference for the Integrator Agent. Use when managing PR reviews, updating PR status, or applying review labels. Trigger with review label requests. Loaded by ai-maestro-integrator-agent-main-agent.

Use when diagnosing CI/CD failures. Trigger with CI failure logs or pipeline errors. Loaded by ai-maestro-integrator-agent-main-agent.

Use when reviewing pull requests. Trigger with PR review or code quality requests. Loaded by ai-maestro-integrator-agent-main-agent.

Use when processing parallel PRs. Trigger with git worktree or parallel development requests. Loaded by ai-maestro-integrator-agent-main-agent.

Quality gate enforcement for PR integration. Use when verifying code through pre-review, review, pre-merge, or post-merge checkpoints. Trigger with /eia-enforce-gates.

Software release management and coordination. Use when creating releases, bumping versions, or rolling back deployments. Trigger with release tasks or /eia-create-release.

Use when managing team tasks through GitHub Projects V2 or synchronizing project state via GraphQL API. Trigger with /sync-projects or when updating project items.

Use when diagnosing CI/CD failures. Trigger with CI failure logs or pipeline errors.

Use when processing parallel PRs. Trigger with git worktree or parallel development requests.

Use when managing GitHub Issues including creation, labels, milestones, assignees, and comments using gh CLI. Trigger with create issue, set labels, assign milestone.

Use when monitoring PR checks. Trigger with CI status, check verification, or PR readiness requests.

Use when retrieving PR context including metadata, diff, and changed files for code review planning. Trigger with /review-pr [PR_NUMBER].

GitHub Projects V2 kanban board management. Use when creating boards, adding columns, moving items. Trigger with kanban or column requests.

Agent progress monitoring via state-based detection. Use when tracking task completion, detecting stalls, or escalating unresponsive agents. Trigger with progress checks.

Use when coordinating work among multiple developers. Trigger with orchestration requests.

Use when replacing agents. Trigger with agent replacement or handoff requests.

Use when compiling verification checklists from requirements including module completion, quality gates, and test coverage checklists. Trigger with checklist compilation requests.

Trigger with developer communication needs. Use when communicating with human developers in code reviews, issues, technical discussions, and status updates. Covers effective communication patterns.

Trigger with Claude Code action requests. Use when setting up Claude Code in GitHub Actions for automated PR reviews, @claude mention responses, and issue triage.

Interview protocols for task verification. Use when checking implementer readiness or approving PR creation. Trigger with task assignment.