Provides Site Reliability Engineering best practices for SLOs, SLIs, SLAs, error budgets, toil reduction, reliability reviews, and capacity planning. Use when defining service objectives, measuring reliability, reducing toil, planning capacity, or when user mentions 'SRE', 'SLO', 'SLI', 'SLA', 'error budget', 'toil', 'reliability', 'on-call', 'capacity planning'.

Provides web accessibility best practices for semantic HTML, ARIA, keyboard navigation, color contrast, and screen reader patterns. Use when building UI components, reviewing accessibility, or when user mentions 'a11y', 'accessibility', 'ARIA', 'screen reader', 'keyboard navigation', 'WCAG'.

Provides dependency management and supply chain security practices for auditing vulnerabilities, checking licenses, assessing dependency health, and managing upgrades safely. Use when auditing packages, reviewing security, managing dependencies, or when user mentions 'audit', 'vulnerability', 'dependency', 'supply chain', 'npm audit', 'license', 'bundle size'.

Polya's four-phase method applied to mathematical problems, extended with Schoenfeld's control/monitoring layer. Covers understand, devise plan, carry out, look back. Includes heuristics specific to math (specialize, generalize, vary the problem, introduce auxiliary elements) and the metacognitive discipline that separates routine computation from genuine problem solving.

Quality assurance and continuous improvement for software projects. Covers Deming's 14 Points for Management, PDCA cycle (Plan-Do-Check-Act), Six Sigma DMAIC, total quality management (TQM), quality metrics (defect density, code coverage, MTBF), testing strategies (unit, integration, system, acceptance), verification and validation (V&V), peer review and inspection, continuous improvement (kaizen), root cause analysis (5 Whys, fishbone), quality gates, definition of done, technical debt management, and Hamilton's priority display concept from Apollo as error prevention through system design.

Retrospective facilitation and organizational learning for project teams. Covers retrospective formats (Start/Stop/Continue, 4Ls, timeline, sailboat), blameless postmortems, lessons learned databases, knowledge management, organizational learning theory (Senge's Fifth Discipline, Argyris's double-loop learning), after-action reviews (military AAR heritage), GSD's session-to-session retrospective pattern, metrics-driven improvement, celebration of success, psychological safety for honest retrospectives, and cross-project pattern recognition.

Research methodology in psychology. Covers experimental design (independent/dependent variables, random assignment, control conditions, between/within-subjects designs), research ethics (informed consent, deception, debriefing, IRB review, APA ethical principles), statistical methods in psychology (null hypothesis significance testing, p-values, effect sizes, confidence intervals, power analysis), and the replication crisis (publication bias, p-hacking, questionable research practices, preregistration, open science). Use when designing psychological research, evaluating study quality, interpreting statistical findings, or discussing methodological rigor in psychology.

Experimental design principles for scientific inquiry. Covers variable identification and control, control groups (positive and negative), randomization, blinding, sample size and power, replication strategies, factorial designs, quasi-experimental approaches, and common design pitfalls. Use when designing, reviewing, or teaching about controlled experiments in any scientific discipline.

Principles and practices of communicating science to diverse audiences. Covers the CER (claims-evidence-reasoning) framework, lab report structure, peer review, scientific argumentation, audience adaptation, the baloney detection kit for evaluating sources, and the art of making complex ideas accessible without sacrificing accuracy. Use when writing, presenting, evaluating, or teaching science communication at any level.

Design heuristics for immersive environments — VR worlds, AR scenes, CAVE installations, responsive rooms. Covers scale and presence, lighting and atmosphere, sight-line composition, acoustic design, comfort-first layout, player/visitor flow, environmental storytelling, and the boundary between stage and audience. Includes Krueger's VIDEOPLACE heritage, Furness's Super Cockpit discipline, and contemporary guidelines for VR level design. Use when authoring or reviewing any environment whose purpose is to be experienced from within.

Issue triage and PR review — scans issues, triages, fixes, submits PRs, then adversarially reviews all open PRs. Parallel agent dispatch with worktree isolation.

Expository and argumentative prose techniques for nonfiction. Covers essay structure (thesis-driven, exploratory, lyric), argumentation (claim-evidence-reasoning, counterargument, concession, Toulmin model), paragraph architecture (topic sentences, development, transitions, coherence), clarity and precision (Orwell's six rules, plain language, jargon management), research integration (source synthesis, attribution, paraphrase vs. quotation), and nonfiction forms (personal essay, op-ed, critical review, academic paper, reported piece). Use when writing nonfiction prose, constructing arguments, or analyzing expository structure.

Research writing conventions for academic and professional contexts. Covers the research process (question formation, literature review, methodology, evidence evaluation), academic genres (research paper, literature review, annotated bibliography, thesis/dissertation, conference paper), citation and attribution (MLA, APA, Chicago, IEEE, in-text vs. footnote, bibliography construction), source evaluation (CRAAP test, peer review, primary vs. secondary, bias detection), research argument construction (hypothesis-driven, question-driven, thesis as evolving claim), and ethical research practices (plagiarism, paraphrase integrity, IRB considerations, data transparency). Use when writing research papers, evaluating sources, constructing academic arguments, or teaching research methodology.

Reviews knowledge pack quality: educational accuracy, grade-level appropriateness, accessibility compliance, learning pathway coherence, assessment alignment, and parallel instruction pattern conformance. Use when reviewing pack content after validation.

Reviews code for bugs, style, and best practices. Use when reviewing PRs or checking code quality.

GSD tutorial, command reference, and workflow explainer. Explains what a GSD workflow command does before you run it. Activates when user is new to GSD, asks about commands, wants to understand workflows, or mentions preview.

Unit Circle Laboratory + sc-dev-team autonomous mission control. Provides human-in-the-loop automation layer, pipeline management, context lifecycle, stuck-state prevention. UC re-execution series and dev branch milestones. Adapted from uc-lab pattern for code plan/execute/verify/complete. Auto-activates during UC milestone work; trigger: user says 'bring up the dev team'.

Load, validate, and use DACP bundles as structured execution context. Detects .bundle/ companion directories, validates integrity (manifest schema, fidelity, provenance), loads typed data, and builds ExecutionContext for receiving agents. Scripts are NEVER auto-executed. Use when processing incoming DACP bundles, interpreting .bundle/ directories alongside .msg files, validating bundle integrity, or building execution context from bundle payloads.

Reviews code for quality, best practices, and potential issues. Use when asked to review, audit, or check code for problems.

Full review lifecycle — request reviews, handle feedback with technical rigor, and complete branch integration. Use when completing tasks, receiving feedback, or finishing feature branches.

Use when you need to interact with the MCP engineering bridge tools (cm_plan, cm_review, cm_qa, cm_deploy, cm_search).

Use when you need a cross-model review or second opinion on a diff or code change.

Operational health review for CodyMaster skills using current repo signals: validate-skills, suggest, retro logs, memory, and test gates.

Package, review, export, and import CodyMaster skill folders safely across machines or teams.

Use to run the full sprint pipeline: brainstorm → plan → design → tdd → build → review → qa → security → ship → monitor → retro.

Master Design Skill. Orchestrates AI-powered UI generation using Google Stitch MCP, guided by cm-ux-master intelligence and professional prompt enhancement pipelines. Implements the 'Stitch Build Loop', 'Prompt Optimization Structure', and strict design system adherence to generate production-ready UI previews before coding.

Garnish — Craft CMS's built-in JavaScript UI toolkit for the control panel. Covers the full Garnish surface: class system (Garnish.Base.extend, init, setSettings, addListener, on/off/trigger, destroy), UI widgets (Modal, HUD, DisclosureMenu, MenuBtn, CustomSelect, ContextMenu, Select), drag system (BaseDrag, DragSort, DragDrop, DragMove), form widgets (NiceText, CheckboxSelect, MixedInput, MultiFunctionBtn), utilities (key constants, ARIA helpers, focus management), and Craft integration (GarnishAsset, webpack externals, Craft.* class pattern). Triggers on: Garnish.Base.extend, Garnish.Modal, Garnish.HUD, Garnish.DragSort, Garnish.Select, Garnish.DisclosureMenu, Garnish.MenuBtn, Garnish.CustomSelect, addListener, removeListener, removeAllListeners, Garnish.ESC_KEY, Garnish.RETURN_KEY, activate event, textchange event, UiLayerManager, registerShortcut, trapFocusWithin, garnishjs, GarnishAsset, CpAsset, CP JavaScript, control panel JS, drag and drop, sortable, modal dialog, HUD popover, disclosure menu, menu button, Craft.CP, Craft.Slideout, Craft.ElementEditor, onSortChange, onOptionSelect, onSelectionChange, aria-modal, focus trap, keyboard navigation CP, this.base(), window.Garnish, expose-loader, CP memory leak, event listener cleanup, jQuery .on() in CP, selection interface, multi-select grid. Always use when writing, editing, or reviewing JavaScript that runs in the Craft CMS control panel — including plugin CP assets, custom field type JS, element index JS, CP webpack config, or code that imports garnishjs or references window.Garnish. Also trigger for Craft CP accessibility, keyboard interactions, drag-sort behavior, or CP JS memory issues. Do NOT trigger for front-end JavaScript (Alpine, Vue, htmx) or Twig templates.

Craft CMS 5 PHP coding standards and conventions. ALWAYS load this skill when writing, editing, reviewing, or discussing any PHP file in a Craft CMS plugin or module — even for small edits. Also load when running ECS, PHPStan, or scaffolding with ddev craft make. Covers: PHPDoc blocks (@author, @since, @throws chains, documenting exceptions), section headers (=========), class organization, naming conventions (services, queue jobs, records, events, enums), defineRules() and validation, beforePrepare() and addSelect(), MemoizableArray, DateTimeHelper vs Carbon, strict_types and declare(strict_types=1) usage, short nullable notation (?string), typed properties, void return types, control flow patterns (early returns, match over switch), CP Twig template conventions, form macros, translations (Craft::t), ECS/PHPStan configuration, scaffolding commands, and the verification checklist. Triggers on: writing service classes, models, controllers, elements, element queries, records, queue jobs, migrations, or any PHP class in a Craft CMS context. Also triggers on PHP code review, refactoring, or style questions for Craft plugins and modules. NOT for front-end Twig templates (use craft-twig-guidelines), template architecture (use craft-site), or CP JavaScript/Garnish (use craft-garnish). If you are touching PHP code in a Craft CMS context, you need this skill.

Craft CMS 5 front-end Twig development — atomic design, template architecture, component patterns, Vite buildchain. Covers the full site template surface: atoms, molecules, organisms, props/extends/block pattern, layout chains, view routing, content builders, image presets, Tailwind named-key collections, multi-brand CSS tokens, JavaScript boundaries (Alpine/DataStar/Vue, tabs, accordions, interactive components), Vite asset loading, and front-end auth (login, registration, password reset, user profiles). Triggers on: {% include ... only %}, {% embed %}, _atoms/, _molecules/, _organisms/, _views/, _builders/, _boilerplate/, component--variant.twig, _component--props.twig, image presets, Tailwind class collections, collect({}), utilities prop, multi-brand theming, data-brand, hero sections, card components, content builders, Matrix block rendering, craft.vite.script, vite.php, vite.config.ts, nystudio107, buildchain, asset loading, per-page scripts, Blitz, static caching, page caching, dynamic caching with Sprig, ImageOptimize, Imager-X, responsive images, srcset, image transforms, SEOmatic, meta tags, OpenGraph, JSON-LD, Sprig, htmx, multi-language site, language switcher, hreflang, localization, Formie, form styling, login form, registration form, user authentication front-end, RSS feed, Atom feed, JSON Feed, XML sitemap, feed.xml, sitemap.xml, |rss, |atom, search page, search results, .search(), search index, search form, search configuration, headless, headless CMS, GraphQL queries, preview tokens, Next.js, Nuxt, Astro, consuming GraphQL API, front-end framework integration. Always use when creating, editing, or reviewing any Craft CMS front-end Twig template, component, layout, view, builder, buildchain configuration, or front-end auth flow — including plugin template integration (Blitz, SEOmatic, Sprig, Formie, Imager-X). Do NOT trigger for PHP plugin/module development or content modeling decisions.

Twig coding standards and conventions for Craft CMS 5 templates. ALWAYS load this skill when writing, editing, or reviewing any .twig file in a Craft CMS project — even for small edits. Covers: variable naming (camelCase, no abbreviations), null handling (?? operator, ??? with empty-coalesce plugin), whitespace control ({%- trimming, NOT {%- minify -%}), include isolation (always use 'only'), Craft Twig helpers ({% tag %}, tag(), attr(), |attr filter, |parseAttr, |append, svg()), collect() for props and class collections, .implode(), comment headers with ========= separators on component files, and common pitfalls (snake_case, macros as components, hardcoded colors). Triggers on: Twig template creation, editing, or review; .twig files; {% include %} with 'only'; {% tag %} and polymorphic elements; collect() and props.get(); class string building; attr() and |attr filter; svg() with styling and aria; ?? and ??? null coalescing; whitespace control and blank lines in output; minify alternatives; Twig file headers and comment blocks; variable naming conventions in Twig; currentSite, siteUrl, craft.entries, .eagerly(), .collect in template context. NOT for Twig architecture patterns, atomic design structure, or template routing (use craft-site). NOT for PHP code (use craft-php-guidelines). NOT for content modeling or field configuration (use craft-content-modeling).

Craft CMS 5 plugin and module development — extending Craft with PHP. Covers the full extend surface: elements, element queries, services, models, records, project config, controllers, CP templates, migrations, queue jobs, console commands, field types, native fields, events, behaviors, Twig extensions, utilities, widgets, filesystems, permissions, debugging, testing, GraphQL, and Craft configuration (config/app.php, config/general.php, Redis, SMTP, database replicas). Triggers on: beforePrepare(), afterSave(), defineSources(), defineTableAttributes(), attributeHtml(), MemoizableArray, getConfig(), handleChanged, $allowAnonymous, $enableCsrfValidation, BaseNativeField, EVENT_DEFINE_NATIVE_FIELDS, FieldLayoutBehavior, EVENT_REGISTER, EVENT_DEFINE, EVENT_BEFORE, EVENT_AFTER, CraftVariable, registerTwigExtension, DefineConsoleActionsEvent, PHPStan, Pest, plugin development, module development, custom element type, custom field type, webhook, API endpoint, queue job, batch processing, data sync, migration, CP section, control panel, Craft plugin, Craft module, extending Craft, element action, element exporter, element condition, dashboard widget, utility page, permissions, registerUserPermissions, requirePermission, GraphQL custom types, GraphQL custom mutations, GraphQL schema building, Rector, Craft 4 to 5, upgrade plugin, CI/CD, GitHub Actions, GitLab CI, custom validator, defineRules, EVENT_AUTHORIZE_VIEW, EVENT_AUTHORIZE_SAVE, canView, canSave, canDelete, element authorization, defense-in-depth, query scoping, EVENT_BEFORE_PREPARE, session invalidation, passwordResetRequired, elevated session, Table::SESSIONS, custom field type build, field type development, normalizeValue, serializeValue, inputHtml, BaseCondition, ElementCondition, condition rule, condition builder, system messages, composeFromKey, email sending, Mailer, deployment, zero-downtime deploy, atomic deploy, craft up, project-config/apply, allowAdminChanges, drafts, revisions, provisional draft, canCreateDrafts, applyDraft, getIsDraft, getIsRevision. Always use when writing, editing, or reviewing any Craft CMS plugin or module PHP code — even when the user asks about plugin architecture, Craft internals, or extending Craft without naming specific APIs. Do NOT trigger for front-end Twig templates, content modeling decisions, site-building without PHP, or consuming GraphQL/headless APIs from front-end frameworks (Next.js, Nuxt, Astro) — those belong in craft-site.

Run API integration tests against the running backend, verify endpoints return expected responses and status codes. Use after deploying a preview or starting the dev server.

Build Docker images and launch a local preview environment with docker-compose. Use to test the full stack locally before merging.

You are the **Chair** — John Carmack's philosophy made operational. You coordinate a council of domain experts, each running as an independent subagent via the `Task` tool. Your job is to map the code

You are a **specification engineer**. Your job is to produce the shortest structured document that makes "done" unambiguous — a spec an AI agent can execute against without drift, and a human can revi

Structured Devil's Advocate analysis that surfaces hidden flaws, edge cases, and blind spots.

React and Next.js performance optimization guidelines from Vercel Engineering. Use when writing, reviewing, or refactoring React/Next.js code — components, data fetching, bundle size, or performance.

Use when receiving code review feedback, before implementing suggestions — requires technical rigor and verification, not performative agreement

**Source:** [vercel-labs/agent-skills](https://github.com/vercel-labs/agent-skills) — `skills/web-design-guidelines/SKILL.md` (MIT). Guidelines content is fetched from the URL below; install/update vi

CRO review of a landing page with specific conversion recommendations

>-

Reviews Java 25 and Spring Boot 4 codebases, pull requests, files, and modules for migration risks, architecture boundary violations, JSpecify null-safety issues, security flaws, performance regressions, and Spring Data pitfalls. Use when the task is a concrete Java or Spring code review with code context. Do not use for Kotlin-only code, non-Spring frameworks, or generic review advice without files or diffs.

Validate hunt conclusions against receipts, contradictory evidence, and success criteria

Generate tests for a completed phase based on Evidence Review criteria and implementation

Cross-phase audit of all outstanding Evidence Review and findings validation items

Generate a comprehensive project summary from milestone artifacts for team onboarding and review

Create a clean PR branch by filtering out .planning/ commits — ready for code review

Review and promote backlog items to active milestone

Request cross-AI peer review of phase plans from external AI CLIs

Generate a session report with token usage estimates, work summary, and outcomes