Skills de Claude Code · página 126

Creates and switches to a new, conventionally named branch — derives the name from an inline description, conversation context, or local git diffs. Preserves all local changes. Never commits or pushes. Use when you want a properly named branch for new or in-progress work.

Iterative auto-fix code review — runs `/optimus:code-review` in a fresh subagent context per iteration, applies fixes, runs tests, bisects failures, and continues until convergence or the iteration cap (default 8, hard cap 20). Each iteration runs in an isolated subagent so context does not accumulate. Requires a test command in .claude/CLAUDE.md. Use when single-pass review leaves issues or for thorough cleanup before a release.

Reviews local changes, PRs/MRs, or branch diffs against project coding guidelines using 5 to 7 parallel review agents (bug detection, security/logic, guideline compliance x2, code simplification, test coverage, contract quality). Use before committing, on open PRs/MRs, or to review any branch diff. HIGH SIGNAL only: real bugs, logic errors, security concerns, and guideline violations. For iterative auto-fix in a loop, use `/optimus:code-review-deep`.

Suggests conventional commit messages by analyzing staged, unstaged, and untracked git changes — read-only, never commits. Use when a commit message suggestion is needed without actually committing.

Stages, commits, and optionally pushes local changes with a conventional commit message — analyzes diffs, generates the message, confirms with the user, and commits. On protected branches, offers to create a feature branch automatically. Multi-repo aware. Use when ready to commit work in one step.

>-

>-

Prepares a project for Claude Code — generates CLAUDE.md with progressive disclosure docs, auto-format hooks, and test infrastructure (framework, coverage tooling, testing docs). Detects empty directories and offers new-project scaffolding via official stack tooling before setup. Also audits and syncs existing documentation against source code. Replaces /init. Supports single projects, monorepos, and multi-repo workspaces (separate git repos under a shared parent directory). Use to bootstrap a new or existing project for Claude Code, or re-run to update an outdated setup.

Fetches and optimizes context from a JIRA issue for AI-assisted development. Searches assigned issues or fetches by key. Distills title, description, acceptance criteria, sprint context, and comments into a structured task description. Analyzes the codebase to surface missing criteria, scope, and risks. Optionally enriches the JIRA issue with a structured analysis comment, and for Complex-scope work can spawn implementation tickets in JIRA. Re-running on the same key refreshes the local task with the latest JIRA state instead of overwriting prior enrichment. Use before /optimus:tdd, /optimus:brainstorm, or /optimus:branch to pull task context from JIRA, or to refresh existing context after JIRA edits.

Configures Claude Code permissions for safe agent autonomy. Creates settings.json with allow/deny rules and a path-restriction hook. Use after /optimus:init to enable autonomous agent workflows, or standalone to lock down a project's permission boundaries.

Creates or updates a pull request (GitHub) or merge request (GitLab) for the current branch using the Conventional PR format — intent, summary, changes, rationale, and test plan. Captures the implementation conversation's intent into the PR description when run in the same session. Use when a branch is ready for review, or to update an existing PR/MR description.

>-

Iterative project-wide refactoring — runs `/optimus:refactor` in a fresh subagent context per iteration, applies fixes, runs tests, bisects failures, and continues until convergence or the iteration cap (default 8, hard cap 20). Supports `testability` or `guidelines` focus to prioritize finding categories. Each iteration runs in an isolated subagent so context does not accumulate. Requires a test command in .claude/CLAUDE.md. Use for thorough guideline alignment or testability cleanup before /optimus:unit-test.

Refactors existing code for guideline compliance and testability using 4 parallel analysis agents (guideline compliance, testability barriers, duplication/consistency, code-simplifier). Two goals — align code with project guidelines AND make untestable code testable so /optimus:unit-test can safely increase coverage. Use after /optimus:init to align existing code, before /optimus:unit-test to remove testability barriers, or periodically to prevent tech debt. Supports "testability" focus (after unit-test flags untestable code) or "guidelines" focus (after init establishes rules) to prioritize finding categories, and flexible scoping. For iterative refactor in a loop, use `/optimus:refactor-deep`.

Removes files installed by /optimus:init and /optimus:permissions from the project. Compares each file against plugin templates and classifies as unmodified, likely generated, or user-modified. Always asks before deleting. Git-tracked files are noted as recoverable. Tests are never touched. Monorepo and multi-repo aware. Use for clean reinstall or to stop using optimus.

Use when starting a new project or product and you want a docs-first plan before writing code — scaffolds an empty, product-neutral spec-driven-development cascade (product vision, MVP PRD, target tech-stack) for a human to fill, then hands off to brainstorm. Emits skeletons only; it never authors product content and never overwrites existing docs.

Guides test-driven development — decompose a feature or bug fix into behaviors, then cycle through Red (failing test) → Green (minimal implementation) → Refactor for each one. Requires /optimus:init and working test infrastructure. Use when starting a new feature or bug fix with test-first discipline.

Iterative test-coverage improvement loop — dispatches `/optimus:unit-test` (unit-test phase) and `/optimus:refactor` with testability focus (refactor phase) into fresh subagent contexts per cycle, applies tests, runs the test suite, bisects refactor failures, and continues until coverage plateaus or the cycle cap (default 5, hard cap 10). Use to drive coverage up on a codebase that has untestable barriers — the loop alternates between writing tests and unblocking testability so a single skill cannot stall.

Implements an approved spec by having Claude design and run its own Claude Code dynamic workflow (real parallel subagents) — you hand it the goal and constraints, it chooses the orchestration. Test-first is enforced as a quality bar (tests accompany or precede code and the suite is left green), not as supervised Red-Green-Refactor. A peer of /optimus:tdd for spec implementation; prefer it for large or parallelizable specs where one linear pass is slow. Requires /optimus:init and a spec (auto-detects docs/specs/ or docs/jira/, or pass a path). Uses meaningfully more tokens than a normal session. Use when a spec is ready to build and you want fan-out implementation instead of turn-by-turn TDD cycles.

Creates a git worktree for isolated parallel development — new branch in a separate directory with project setup and test baseline. Enables multiple Claude Code sessions on different tasks simultaneously. Multi-repo aware. Use when you need to work on something else without disturbing current work.

Use when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.

Use when the user wants to create a new CLAUDE.md from scratch for a repository, bootstrap project memory for a new repo, set up a repo for Claude Code for the first time, or completely rewrite an existing CLAUDE.md deemed unsalvageable. Produces a lean, high-signal file under 80 lines (120 hard cap) by scanning the repo for mechanical content (stack, commands, structure) and interviewing the user for judgment content (WHY, gotchas, out-of-scope, approval gates, testing philosophy, external docs like Confluence pages). NOT for auditing or incrementally improving an existing CLAUDE.md — that is the claude-md-improver skill's role.

Set up and maintain Hierarchical Agent Memory (HAM) for Codex using scoped local memory files. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM savings", "HAM stats", "HAM dashboard", "HAM sandwich", "HAM insights", "HAM carbon", or "HAM audit".

>

Fleet infrastructure mechanics - member management, permissions, onboarding, provider awareness, and tool usage patterns

Project Manager — plans, executes, monitors, and resumes multi-step work across fleet members. Delegates to members, tracks progress, drives reviews and deploys. Never writes code directly.

>

>

>

>

>

>

Evaluate, benchmark, compare, and optimize descriptions for existing skills. Use when users want to run evals to test a skill, benchmark skill performance with variance analysis, do blind A/B comparisons between skill versions, or optimize a skill's description for better triggering accuracy. Do NOT use for creating skills from scratch — see write-a-skill for that.

>

>

>

Craft Cloud — Pixel & Tonic's serverless hosting platform for Craft CMS. Covers craft-cloud.yaml configuration, the Build → Migrate → Release deploy pipeline, the craftcms/cloud extension package, edge image transforms via Cloudflare, edge static caching with cache.rules + ESI, Cloud-managed S3 filesystem, MySQL 8 / Postgres 15 databases (no MariaDB, no tablePrefix), Console-based command runner and scheduled cron (once-per-hour minimum), auto-handled queue jobs, custom domains and SSL, preview environments per branch, Cloud limitations (ephemeral filesystem, no SSH, no .htaccess, no built-in mail), plugin development requirements for Cloud compatibility, and self-hosted → Cloud migration. Triggers on: craft-cloud.yaml, craftcms/cloud package, cloud.esi(), php craft cloud/up, php craft cloud/setup, App::isEphemeral(), CRAFT_EPHEMERAL, edge.craft.cloud, preview.craft.cloud, CRAFT_CLOUD_PROJECT_ID, CRAFT_CLOUD_ENVIRONMENT_ID, CRAFT_CLOUD_CDN_BASE_URL, Build → Migrate → Release, Cloud filesystem, Cloud-compatible plugin, Cloudflare Images at edge, AssetsFs, static-caching rules, ESI islands, deploy to Craft Cloud, migrate to Craft Cloud, self-hosted to Cloud, Craft Cloud quotas, Craft Cloud regions. Do NOT trigger for Servd (use the servd skill) or generic Craft deployment on Forge/bare metal (craftcms/deployment.md). Do NOT trigger for general DDEV local dev unrelated to Cloud parity.

Craft CMS 5 content modeling — sections, entry types, fields, Matrix, relations, project config, and content architecture strategy. Covers everything editors and developers need to structure content in Craft: choosing section types, designing entry types and field layouts, selecting field types for specific needs, configuring Matrix and nested entries, setting up relations and eager loading, and planning multi-site propagation. Triggers on: section types (single, channel, structure), entry types, field types, field layout design, field type selection, Matrix configuration, nested entries, relatedTo, eager loading, .with(), .eagerly(), categories, tags, globals, global sets, preloadSingles, propagation, multi-site content, URI format, project config, YAML, content architecture, content strategy, taxonomy, asset volumes, filesystems, image transforms, user groups, content permissions, entries-as-taxonomy, entrify, entrification, CKEditor vs Matrix, CMS editions, site propagation, multi-language, language groups, localization, translation method, field translation, content migration, reserved handles, field instances. Always use when planning content architecture, creating sections/fields, configuring Matrix, setting up relations, choosing field types, designing field layouts, making content modeling decisions, or planning multi-site content propagation. Do NOT trigger for PHP plugin/module development, custom field type code, front-end Twig templates, or buildchain configuration.

Garnish — Craft CMS's built-in JavaScript UI toolkit for the control panel. Covers the 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.DisclosureMenu, Garnish.ESC_KEY/RETURN_KEY, activate/textchange events, UiLayerManager, registerShortcut, trapFocusWithin, garnishjs, GarnishAsset, CpAsset, CP JavaScript, modal dialog, HUD popover, Craft.CP, Craft.Slideout, Craft.ElementEditor, onSortChange, onOptionSelect, onSelectionChange, aria-modal, focus trap, keyboard navigation CP, this.base(), window.Garnish, CP memory leak, event listener cleanup, jQuery .on() in CP. Always use when writing, editing, or reviewing JavaScript that runs in the Craft CP — 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 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-site).

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.

Scaffold Claude Code configuration specifically for Craft CMS projects. Generates CLAUDE.md and .claude/rules/ files tailored to the project type (plugin, site, module, hybrid, or monorepo). Only for Craft CMS projects — not for Next.js, Laravel, or other frameworks. Triggers on: 'set up Claude for this Craft project', 'initialize CLAUDE.md', 'scaffold project config', 'configure Claude Code for Craft', 'create CLAUDE.md', 'missing CLAUDE.md', 'does this project have a CLAUDE.md', 'bootstrap Claude config', 'new Craft project setup', 'onboard a developer to this Craft project', 'generate .claude/rules', 'set up coding standards config', 'upgrade Claude config', 'update CLAUDE.md', 'compare my setup', 'is my config up to date', 'audit my Claude setup', 'redo project setup'. Also triggers when starting work in a new Craft CMS project that lacks a CLAUDE.md file, or when the user wants to check or upgrade an existing configuration. Detects project type from composer.json (craft-plugin, craft-module, project), .ddev/config.yaml, templates/, config/project/, and modules/. NOT for installing Craft CMS itself, creating DDEV environments, writing PHP code, building templates, or content modeling. NOT for non-Craft projects — if the project is React, Next.js, Laravel, or any non-Craft framework, this skill does not apply.

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

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 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. Triggers on: beforePrepare(), afterSave(), defineSources(), defineTableAttributes(), attributeHtml(), MemoizableArray, BaseNativeField, EVENT_REGISTER_*/DEFINE_*/BEFORE_*/AFTER_*, CraftVariable, registerTwigExtension, custom element type, custom field type (normalizeValue, serializeValue, inputHtml), webhook, API endpoint, queue job, batch processing, CP section, control panel, element action, element exporter, element condition, dashboard widget, utility page, registerUserPermissions, requirePermission, GraphQL custom types/mutations, schema building, defineRules, canView/canSave/canDelete authorization, session invalidation, elevated session, BaseCondition, system messages, Mailer, atomic deploy, craft up, project-config/apply, drafts, revisions, GeneralConfig, $allowAnonymous. Always use when writing, editing, or reviewing Craft CMS plugin or module PHP code, even when no specific API names are mentioned. Do NOT trigger for front-end Twig (craft-site), content modeling (craft-content-modeling), or headless GraphQL consumption from Next.js/Nuxt/Astro.

DDEV local development environment for Craft CMS projects. ALWAYS load this skill when running any ddev command, configuring .ddev/config.yaml, or troubleshooting local container issues. Covers: config.yaml settings (project type, PHP/Node versions, database, docroot), shorthand commands (ddev composer, ddev craft, ddev npm), add-ons (ddev add-on get for Redis; built-in Mailpit), custom commands (.ddev/commands/), Vite dev server exposure (web_extra_exposed_ports, web_extra_daemons), database import/export (ddev import-db, ddev export-db, ddev craft db/backup), Xdebug toggling (ddev xdebug on/off), sharing local sites (ddev share, temporary public URLs), and troubleshooting (ddev poweroff, ddev logs, ddev describe, ddev delete, port conflicts, container restart issues). Triggers on: ddev start/stop/restart, ddev craft, ddev composer, ddev npm, ddev ssh, ddev import-db, ddev export-db, ddev xdebug, ddev share, ddev add-on, ddev poweroff, ddev describe, ddev logs, .ddev/config.yaml, web_extra_exposed_ports, web_extra_daemons, PHP version or Node version in local dev, database backup/restore locally, ran npm/composer on host instead of ddev, wrong node_modules architecture, local dev environment for Craft CMS. NOT for production deployment, CI/CD pipelines, GitHub Actions, or server configuration. NOT for Docker/container usage outside of DDEV.

Servd (servd.host) — Craft-specialised managed hosting for Craft CMS. Covers git push-to-deploy with the optional servd.yaml build config, local → staging → production environments with uni-directional Project Config sync, the servd/craft-asset-storage plugin (S3-backed Flysystem volumes on the svdcdn.com CDN, off-server image transforms, Imager-X/ImageOptimize integrations), Servd's static caching (full vs tag-based purge, {% dynamicInclude %}, CSRF injection, cache-busting) and running Blitz alongside it in reverse-proxy mode, MariaDB/MySQL databases over an SSH tunnel, automatic + manual backups, the Dedicated Queue Runner, environment variables and secrets, the ephemeral load-balanced filesystem (Redis + remote volumes for runtime files), plugin/feature constraints, and Servd-vs-Craft-Cloud differences. Triggers on: servd.yaml, servd/craft-asset-storage, servd-asset-storage plugin handle, SERVD_PROJECT_SLUG, SERVD_SECURITY_KEY, SERVD_BUNDLE_HASH, files.svdcdn.com, Servd static caching, {% dynamicInclude %} (Servd), servd-asset-storage/clone, servd-asset-storage/local/pull-database, push-assets, clear-caches/servd-static-cache, clear-caches/servd-edge-caches, Dedicated Queue Runner, Servd Asset Platform, deploy to Servd, host Craft on Servd, Servd vs Craft Cloud. Do NOT trigger for Craft Cloud (use the craft-cloud skill), generic Craft deployment on Forge/bare metal (craftcms/deployment.md), or general DDEV local dev unrelated to Servd parity (ddev).

Audits and optimizes websites for search engine visibility (SEO) and AI search citation (GEO), covering technical health, E-E-A-T content scoring, domain authority, structured data, rich results, and entity signals. Use when running SEO audits, diagnosing traffic drops or ranking losses, generating Schema.org JSON-LD, checking Core Web Vitals, crawlability, robots.txt, sitemaps, hreflang, backlinks, planning content strategy or site migrations, fixing indexing issues, or optimizing for AI Overviews, ChatGPT, and Perplexity. NOT for paid ads (PPC/SEM), social media strategy, email marketing, or general web development unrelated to search.

>

>

Batch download academic paper full-text (PDF/XML) from a list of DOIs. Handles 25 DOI prefixes across 19 publisher families via three layered routes: (1) publisher TDM APIs requiring institutional subscription (Elsevier ScienceDirect, Wiley Online, Springer Nature), (2) Open Access sources (Crossref, Unpaywall, OpenAlex), and (3) a browser-based fallback for paywalled publishers without TDM access (ACS, RSC, IEEE, AIP, IOP, APS, Annual Reviews, T&F, Chinese journals). Browser fallback offers two routes — Route A drives the user's logged-in Chrome via the OpenClaw `browser` tool with `profile="user"` (best for interactive sessions), Route B uses the standalone `auto-paper-harvester` CLI with its built-in Playwright (best for unattended bulk runs). Use when the user wants to harvest, scrape, fetch, or bulk-download papers from a DOI list, savedrecs export, or Excel; or wants to fill missing full-text PDFs for an existing literature collection. Triggers on phrases like "批量下载文献", "下载全文", "harvest papers", "scrape full text", "TDM API", "下载 Elsevier 全文", "Wiley 批量下载", "下载 PDF".

>

>

>

>

Adaptive conversion of LaTeX, PDF, or Markdown sources into a complete Word .docx that follows a user-supplied .docx template. Use when pandoc --reference-doc alone is not enough — for thesis, dissertation, report, or institutional Word formatting that needs cover pages, declarations, TOC, heading numbering, captions, three-line tables, equations, citations, and visual verification.

Analyzes a Delphi / Object Pascal codebase to extract unit-level `uses` dependencies. Use when the user uploads a zip / archive of a Delphi project (or a folder of .pas / .dpr / .dpk files) and asks for a dependency graph, architecture map, cycle detection, fan-in / fan-out coupling analysis, or wants to know how units relate. Produces a Mermaid diagram, a Graphviz DOT file, an SVG when graphviz is available, a JSON dump of the parsed graph, and a markdown report listing cycles, hotspots and orphan units.

Use when refactoring code with poor names, when asked to improve naming, or when a user struggles to name a class/method/variable. Symptoms include -Manager/-Util suffixes, single-letter variables, process/handle/do verbs, primitive obsession, god methods with multiple responsibilities. Two modes — audit (broad scan, list opportunities) and improve (walk one specific identifier through the process).

Complete DataForSEO API integration for SEO data and analysis. Use when the user asks for keyword research, search volume, SERP analysis, backlink audits, competitor analysis, rank tracking, domain authority, technical SEO audits, content monitoring, Google Trends, or any SEO-related data queries. Covers all DataForSEO APIs including SERP, Keywords Data, DataForSEO Labs, Backlinks, OnPage, Domain Analytics, Content Analysis, Business Data, Merchant, App Data, and AI Optimization APIs. Outputs CSV files.

Creates pages/layouts, defines content collections, configures hydration directives, and wires integrations. Use when adding or modifying Astro pages, layouts, components, or content collections. Trigger terms: Astro, content collection, client:load, client:visible, astro:content

Drive real browsers via Chrome DevTools MCP: navigate pages, capture snapshots, run responsive checks, and collect console/perf traces. Use when the user mentions: 'validate UI change in Chrome', 'capture a screenshot', 'run responsive checks', or 'collect console logs'. Trigger terms: browser testing, DevTools, console logs, screenshot, responsive testing

Creates and deploys Cloudflare Workers, configures wrangler.toml bindings, sets up KV/D1/R2 storage and Durable Objects, manages Pages deployments, and implements edge function patterns. Use when building or deploying Cloudflare Workers, setting up Pages, working with KV/D1/R2 storage, configuring wrangler.toml, or deploying edge applications.

Creates Contentful content types, queries entries via GraphQL/REST, runs CLI migrations, and manages assets and locales. Use when building or modifying Contentful content models, writing queries, or migrating content.

Convex reactive database patterns, schema design, real-time queries, mutations, actions, authentication, migrations, performance optimization, and component creation. Use when designing Convex schemas, writing queries/mutations, managing the Convex backend, setting up auth, migrating data, optimizing performance, or building Convex components.

Deploys applications, databases, and services on self-hosted Coolify instances, manages environments and env vars, runs infrastructure diagnostics, and performs batch operations. Use when deploying apps to Coolify, managing Coolify servers, debugging deployment issues, setting up databases, or managing Coolify infrastructure.

Writes Cypress E2E/component tests, configures `cy.intercept()` and `cy.session()`, authors custom commands, and wires CI artifacts. Use when creating E2E specs, component tests, or CI test pipelines. Trigger terms: cypress, e2e, component test, cy.intercept, cy.session

Drizzle ORM schema definition, type-safe queries, relational queries, CRUD operations, transactions, migrations with drizzle-kit, and database setup for PostgreSQL, MySQL, and SQLite. Use when defining database schemas, writing queries or joins, managing migrations, setting up a new Drizzle project, or working with drizzle-kit.

Scaffolds Expo/React Native apps, configures EAS Build profiles, manages native modules via CNG, sets up Expo Router navigation, and uses EAS Update for OTA deployments. Use when creating React Native apps with Expo, configuring EAS builds, setting up Expo Router, managing native modules, or deploying OTA updates.

Figma design-to-code workflows, design token extraction, component inspection, and asset export. Use when translating Figma designs into code, extracting design tokens, or referencing component specs.

Create and update Jira issues, epics, and sprints; manage backlog and sprint transitions. Use when you say: 'create a ticket', 'open a story', 'link an epic', 'start a sprint', or 'search the backlog'.

Creates and names Linear issues, assigns labels and priorities, manages status transitions, and links issues to PRs. Use when decomposing features into tasks or resuming interrupted sessions. Trigger terms: tickets, backlog, task breakdown, project board, sprint planning

Deploy sites, configure serverless and edge functions, and verify builds on Netlify. Use when the user mentions: 'deploy preview', 'configure netlify.toml', or 'debug a failed deploy'. Trigger terms: build error, Netlify Functions, deploy logs, deploy preview

Explains how to configure App Router, implement server/client components, optimize data fetching, and secure routes. Use when the user mentions: 'add an authenticated route', 'migrate to App Router', 'optimize fetch caching', or 'fix RSC hydration'.

Creates Notion pages and databases, applies templates for research docs, ADRs, and specs, and manages team knowledge bases. Use when creating Notion pages, structuring databases, documenting decisions, or capturing research findings.

Run and generate NX targets, configure project.json, and visualize dependency graphs. Use when you say: 'run affected tests', 'nx generate a library', 'configure project.json', or 'show dependency graph'.

Playwright E2E testing patterns, cross-browser configuration, page objects, and CI setup. Use when creating E2E specs, visual regression suites, or configuring Playwright in CI. Trigger terms: playwright, e2e, trace, page object, cross-browser

Prisma ORM schema design, migrations, client generation, and query patterns. Use when designing database schemas, writing migrations, querying data, or managing Prisma Client.

Resend transactional email patterns, React Email templates, domain configuration, and webhook handling. Use when sending emails, building email templates, or configuring email delivery.

Manages Sanity CMS schemas, GROQ queries, dataset exports/imports, and Studio configuration. Use when updating Sanity schemas, running GROQ or Vision queries, exporting datasets, modifying content models, or configuring a headless CMS with Sanity.io.

Sentry error monitoring, SDK initialization, performance tracing, source maps, session replay, and release tracking. Use when adding Sentry to a project, capturing errors with context, setting up distributed tracing, configuring source maps, or debugging production issues.

Slack MCP integration for agent-to-human notifications and bi-directional communication. Use when agents need to post progress updates, request approvals, or read user responses via Slack channels and threads.

Builds Strapi content types, extends controllers and services, implements lifecycle hooks, and configures REST/GraphQL APIs. Use when creating content types, writing custom controllers, developing Strapi plugins, or querying the API.

Stripe payment integration patterns, Checkout Sessions, billing/subscriptions, Connect platforms, and API best practices. Use when building, modifying, or reviewing any Stripe integration — including accepting payments, building marketplaces, setting up subscriptions, or implementing secure key handling.

Generates Supabase database migrations, writes RLS policies with auth.uid(), configures auth integration, and generates TypeScript types. Use when creating tables, writing migrations, configuring RLS, or implementing Supabase auth.

Microsoft Teams MCP integration for agent-to-human notifications and bi-directional communication. Use when agents need to post progress updates, request approvals, or read user responses via Teams channels and chats.

Create and manage Trello cards, checklists, and boards for kanban workflows. Use when the user says: 'create a kanban board', 'add a task card', 'move card to sprint', or 'track project board'.

Configure pipelines, set up local/remote caching, and run scoped tasks in a Turborepo monorepo. Use when you say: 'enable remote caching', 'optimize pipeline inputs/outputs', or 'filter builds to affected packages'.

Vercel deployment workflows, environment management, domain configuration, and build troubleshooting. Use when deploying, checking deployment status, reviewing build logs, or managing environments.

WCAG 2.2 Level AA accessibility patterns for React/HTML/CSS. Use when creating or modifying UI components, forms, navigation, tables, images, or any user-facing elements. Covers keyboard navigation, screen reader semantics, low vision contrast, voice access, inclusive language.

Four lifecycle hooks every agent runs: on-session-start scans LESSONS-LEARNED.md, resumes checkpoints; on-pre-delegate verifies tracker issues, file partitions; on-post-delegate runs fast-review, CI checks; on-session-end executes session guard, writes logs. Use when starting a new session, running pre-flight checks before delegation, coordinating between agents, reviewing a completed handoff, or wrapping up a session. Trigger terms: multi-agent setup, delegate tasks, agent coordination, session management, run pre-flight checks, start a new session, coordinate between agents, wrap up session

Creates, queries agent expertise profiles in AGENT-EXPERTISE.md; increments file-familiarity counters after each task; ranks candidate agents by recency, task-area match. Use when deciding which agent should handle a file, checking who last worked on a module, recording task outcomes, or assigning work based on past performance.

Creates API route handlers, implements Server Actions with Zod schema validation, integrates external REST APIs with error handling. Use when adding endpoints, building request handlers, or wiring external services (endpoint, REST API, request handling, fetch, .ts route files).

Scaffolds production-ready monorepo projects using the backbone CLI: configures workspace packages, wires build tooling, sets up CI pipelines, and initializes framework/backend/CMS integrations. Use when creating, bootstrapping, or initializing a new application, project, starter template, or monorepo from scratch. Trigger terms: scaffold, bootstrap, init, new repo, new app, boilerplate, starter, greenfield.

Guidelines for writing self-explanatory code with minimal comments. Covers when to comment (WHY not WHAT), anti-patterns to avoid, annotation tags, public API documentation. Use when writing or reviewing code comments, docstrings, TODO/FIXME tags, code readability, or inline comments.

Maps file dependencies, flags shared imports, groups files for safe parallel editing before code changes. Use when planning a refactoring, analyzing change impact, or understanding which files a modification will affect.

Transforms, validates, loads data in ETL pipelines. Use when building scrapers, validating NDJSON feeds, or importing data into CMS/DB targets.

Resolves task dependencies, generates machine-actionable delegation specs, structures phased subtask plans for multi-agent work. Use when writing delegation specs, resolving task dependencies, building phased subtask plans for multi-agent work, assigning work to sub-agents, or partitioning a feature into parallelizable phases.

Configures deployment pipelines, manages environment variables, schedules cron jobs, applies security headers, implements caching strategies. Use when working with Docker, Vercel, AWS, Dockerfile, nginx.conf, or platform deployment configs.

Scaffolds issue docs, ADRs, README outlines, changelog entries, roadmap updates, Mermaid architecture diagrams using project templates. Use when drafting ADR, writing changelog, updating roadmap after a feature ships, creating README for a new library, or diagramming a system flow.

Mandatory post-delegation gate: checks output completeness, verifies acceptance criteria compliance, flags regressions, produces PASS/FAIL verdict. Use when checking delegated work against acceptance criteria, running post-delegation gate, validating agent output before acceptance, verifying sub-agent completed its assignment, or running post-delegation QA check.