claude

dx-core

Full-stack development workflow for Azure DevOps projects — requirements, planning, execution, review, bug fixes, and PR management

7 on GitHubby Dragan Filipovicv3.14.1MITupdated 3 days ago
/

Plugin dx-core from marketplace dx-aem-flow in easingthemes/dx-aem-flow. Commands read from the repo's manifest — 3 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (49)

  • dx-adapt

    Auto-detect project type, structure, build commands, and AEM values. Updates .ai/config.yaml with project profile and substitutes real values into installed .claude/rules/. Run after /dx-init and /aem-init. Re-run anytime to refresh detected values.

  • dx-agent-all

    Full pipeline from ADO story to code and PR — requirements, plan, execution, build, review, commit, PR — with optional review checkpoints. Use for 'implement this story', 'do the whole story'.

  • dx-agent-dev

    Dev Agent: implement code from an RE spec — implement, self-check (build/test/lint), fix failures, commit. Use for 'dev agent', 'implement from spec'.

  • dx-agent-re

    RE Agent: analyze an ADO/Jira User Story into a structured requirements spec with task breakdown, and post a summary comment. Use for 're agent', 'requirements agent'.

  • dx-axe

    Accessibility-test a URL with the axe MCP server — find WCAG violations, get remediation, apply fixes, re-verify. Use for 'a11y audit', 'check accessibility'.

  • dx-bug-all

    Full bug workflow in one command for an ADO Bug — triage, reproduce in the browser, fix, PR. Use for 'fix bug <id>'. Not for a single phase (dx-bug-triage, dx-bug-verify, dx-bug-fix).

  • dx-bug-fix

    Plan, implement, test and open a PR for a bug fix from triage.md / verification.md. Use after /dx-bug-triage or /dx-bug-verify. Not before triage exists, not for the whole workflow (dx-bug-all) or reproduction (dx-bug-verify).

  • dx-bug-triage

    Fetch a Bug from ADO/Jira, find the affected component, write raw-bug.md and triage.md with a root-cause hypothesis. Use to start a bug ticket. Not for reproducing (dx-bug-verify), fixing (dx-bug-fix) or the whole flow (dx-bug-all).

  • dx-bug-verify

    Reproduce a bug in the browser (Playwright) — follow repro steps, screenshot, confirm; modes before (default), after (post-fix), qa. Not for fetching the ticket (dx-bug-triage), fixing (dx-bug-fix) or story QA on AEM (aem-qa).

  • dx-council

    Put a question, decision or artifact to a council of 3 AI advisors who analyze it, peer-review each other and give a verdict. Use for 'council this', 'pressure-test this', 'debate this', or a real trade-off. Not for yes/no or factual questions.

  • dx-doc-gen

    Generate wiki docs from completed spec files — decisions, usage, API changes — and post to ADO Wiki or Confluence. Final step after implementation; used by /dx-agent-all Phase 7 and /dx-req-dod. For a done story without spec files, the user runs /dx-doc-retro.

  • dx-doc-retro

    Generate technical documentation retroactively for completed stories — fetches ADO story, finds linked PRs, searches codebase, and produces wiki-ready docs without needing spec files. Posts to ADO Wiki or Confluence depending on provider config. Use when documentation was never generated during deve

  • dx-doctor

    Check health of the dx workflow files — config, rules, scripts, seed data, MCP, settings — for each installed plugin. Use after upgrading plugins or when something seems broken.

  • dx-dor

    Validate a story's Definition of Ready — fetch the wiki checklist, evaluate, post an ADO comment. Use at sprint start ('check DoR', 'is this story ready'), in batch, or via /dx-req.

  • dx-eject

    Eject all plugin assets into the consumer repo — copies skills, agents, rules, templates, shared files, hooks, and MCP config so the project works without plugins installed. Use when a team wants to own all dx files locally instead of depending on plugins.

  • dx-estimate

    Analyze an Azure DevOps/Jira User Story and produce a structured estimation — understanding, implementation plan, recommended hours/SP, AEM pages affected, and open questions. Posts result as an ADO/Jira comment. Use when you want an AI-generated estimation for a story.

  • dx-figma-all

    Full Figma design-to-code flow in one command — extract, prototype, verify. Use when a story has a Figma URL: 'figma all', 'turn this figma into code'.

  • dx-figma-extract

    Extract design context, tokens and screenshots from a Figma URL into figma-extract.md. Use after requirements when the story has a Figma URL. Not for general Figma browsing or without a spec directory.

  • dx-figma-prototype

    Generate a standalone HTML/CSS prototype from figma-extract.md, following project conventions. Use after /dx-figma-extract. Not without figma-extract.md or for non-design tasks.

  • dx-figma-verify

    Compare a generated prototype with the Figma reference screenshot in a browser, fix gaps, write a report. Use after /dx-figma-prototype. Not for components on AEM (aem-fe-verify) or pre-PR checks (dx-step-verify).

  • dx-help

    Answer questions about the project's architecture, components, patterns and dx workflow — 'how does X work?', 'where do I find Z?'. Not for a specific ticket or a component's files.

  • dx-init

    Set up the dx workflow for a new project. Detects your environment, asks a few questions, and generates .ai/config.yaml plus supporting files. Run this first before using any other dx skill.

  • dx-pattern-extract

    Scan completed tickets for recurring patterns and promote to cross-ticket knowledge. Run periodically or after completing several tickets. Creates .ai/graph/nodes/patterns/ entries.

  • dx-plan-resolve

    Resolve risks flagged by /dx-plan-validate — research the codebase and update implement.md steps with concrete fixes. Use for 'resolve plan issues', 'fix plan risks'.

  • dx-plan-validate

    Cross-check implement.md against the requirements — every requirement covered, nothing unrequested, dependencies in order. Use for 'validate plan', 'check the plan', between /dx-plan and /dx-step.

  • dx-plan

    Generate implement.md, a plan with status-tracked steps, from explain.md and research.md. Use after requirements are ready ('plan this story').

  • dx-pr-answer

    Answer open comments on your PRs in the configured SCM (only ado is implemented) — draft and post replies, apply reviewer patches. Not for reviewing a PR (dx-pr-review) or creating/pushing one (dx-pr, dx-pr-commit).

  • dx-pr-commit

    Commit changes (work item ID in the message, rebase onto base) and optionally open a PR in the configured SCM (only ado is implemented). Use for 'commit', 'push', 'open PR', 'create PR'. Not for reviews (dx-pr-review) or replies (dx-pr-answer); the end-of-plan PR is dx-pr.

  • dx-pr-review-all

    Review multiple Azure DevOps pull requests in batch. Use when reviewing several PRs at once or checking active PRs for a repo.

  • dx-pr-review-report

    Write a categorized report of an existing PR review (bug, a11y, regression, …) with patch status, posted to ADO Wiki or Confluence. Not for doing the review (dx-pr-review) or many reviews at once (/dx-pr-reviews-report).

  • dx-pr-review

    Review a pull request by ID or URL in the configured SCM (only scm.provider ado is implemented) — analyze the diff, report findings, optionally post comments. Not for a local diff, creating a PR (dx-pr, dx-pr-commit), answering comments (dx-pr-answer) or a review write-up (dx-pr-review-report).

  • dx-pr-reviews-report

    Generate categorized reports for multiple PR reviews — lists reviewed PRs, generates a report for each, and posts all to ADO Wiki or Confluence. Use when you want to document all recent PR reviews, mentions "report reviews", or wants batch PR review reports.

  • dx-pr

    Create the PR when all plan steps are done — write the description from share-plan.md, push, open it in the configured SCM (only scm.provider ado is implemented). Not for staging or committing (dx-pr-commit), reviews (dx-pr-review) or replies (dx-pr-answer).

  • dx-req-dod

    Check Definition of Done and auto-fix gaps — PR, tasks, docs — then post a summary to ADO. Use for 'check DoD'. Not for fetching requirements (dx-req), child Tasks (dx-req-tasks) or pre-PR checks (dx-step-verify).

  • dx-req-import

    Validate external requirements and create spec structure without ADO. Reads a requirements document, checks completeness, and generates explain.md + optional research.md. Use when you have requirements from a BA, Confluence page, or email instead of an ADO ticket.

  • dx-req-tasks

    Create or close child Tasks under an ADO/Jira User Story — FE/BE/Authoring with hour estimates; 'close' closes them after development. Not for requirements (dx-req) or DoD (dx-req-dod).

  • dx-req

    Start any ticket — fetch the ADO/Jira story, check DoR, distill requirements, research the codebase, write a team summary. Not for requirements from a file (/dx-req-import), child Tasks (dx-req-tasks) or DoD (dx-req-dod).

  • dx-scan

    Deep project scan — discover conventions from actual code, customize rule files with real values, and generate seed data. Interactive. Run after /dx-init + /dx-adapt + /aem-init. Use when setting up a new project or when project structure changes significantly.

  • dx-security

    Security audit — OWASP Top 10, secrets scan, dependency audit, input validation, auth review. Use before a PR or when code handles user input, auth or external integrations.

  • dx-simple

    Apply a small AEM change (a11y label, color, spacing, copy, CSS class, icon, focus trap) via authoring (JCR) or code (PR) paths, read from the ADO story. Use for 'simple change', 'small tweak', '@kai-simple'.

  • dx-simplify

    Simplify working code without changing its behavior — Chesterton's Fence, Rule of 500. Use for 'simplify', 'reduce complexity', 'refactor for clarity'.

  • dx-step-all

    Run every plan step hands-free (implement, test, review, commit), with step-fix on failures; stops after 2 failed fixes on one step. Use for 'execute plan', 'run all steps'.

  • dx-step-build

    Build and deploy to the local dev environment, fixing errors until the build passes. Use after code changes ('build', 'compile', 'build and deploy').

  • dx-step-fix

    Diagnose and fix a blocked step — compile error, test failure, review rejection — directly or by adding corrective steps to implement.md. Use when /dx-step fails.

  • dx-step-verify

    6-phase pre-PR verification with auto-fix — compile, lint, test, secrets, architecture, code review (max 3 cycles). Use after /dx-step-build. Not for checks on a running AEM (aem-verify, aem-fe-verify, aem-qa) or existing PRs (dx-pr-review).

  • dx-step

    Execute the next pending step in implement.md — implement, test, review, commit, update status. Use to go one step at a time ('next step').

  • dx-sync

    Sync plugin updates to consumer repos — runs sync-consumers.sh with selected repos and options. Use when you say "sync plugins", "update consumers", "push to all repos".

  • dx-ticket-analyze

    Research an ADO/Jira ticket and list the source files and assets it involves. Use for 'analyze ticket', 'what files does this touch?', 'find files for this story'.

  • dx-upgrade

    Upgrade a consumer project to the installed plugin versions — run dx-doctor, fix stale and missing files, list manual actions. Use after upgrading plugins.

Subagents (7)

  • dx-code-reviewer

    Senior code reviewer. Reviews code changes against plans, project conventions, and production readiness. Uses confidence-based filtering (>=80) to report only issues that truly matter. Use for full-diff reviews before merging.

  • dx-doc-searcher

    Searches .ai/ index and reference files to look up components, architecture patterns, and feature context. Avoids expensive MCP calls. Used by dx-help, dx-ticket-analyze, and component lookup skills.

  • dx-figma-components

    Analyzes Figma extraction to identify UI building blocks (buttons, images, cards, forms, etc.) and searches the codebase for existing components that can be reused. Used by dx-figma-prototype.

  • dx-figma-markup

    Discovers HTML and accessibility conventions from the consumer project — semantic patterns, component structure, ARIA usage, keyboard handling. Used by dx-figma-prototype.

  • dx-figma-styles

    Discovers CSS/SCSS conventions from the consumer project — variables, breakpoints, typography, spacing, theming, naming patterns. Used by dx-figma-prototype.

  • dx-file-resolver

    Resolves all source files for a component or module across project repos. Returns file paths as clickable ADO URLs. Used by dx-ticket-analyze and component lookup skills.

  • dx-pr-reviewer

    Reviews a single ADO pull request — fetches diff, loads project conventions, analyzes code changes, and returns structured findings with severity and line-level comments. Does NOT post to ADO — returns findings for user approval. Used by review and reviews skills.

MCP servers (2)

  • axe-mcp-server

    runs: npx -y axe-mcp-server

  • figma

    connects to: http://127.0.0.1:3845/mcp

Hooks (10)

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session-start.sh"

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/context-loader.sh"

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/next-step.sh"

  • PreToolUse

    bash -c 'grep -q "git commit" || exit 0; BRANCH=$(git branch --show-current 2>/dev/null); if [ "$BRANCH" = "main" ] || [ "$BRANCH" = "master" ] || [ "$BRANCH" = "development" ] || [ "$BRANCH" = "devel

  • Stop

    [ -f "$CLAUDE_PROJECT_DIR/.claude/hooks/stop-guard.sh" ] && bash "$CLAUDE_PROJECT_DIR/.claude/hooks/stop-guard.sh" || true

  • PostToolUse

    [ -f "$CLAUDE_PROJECT_DIR/.ai/lib/figma-screenshot-hook.sh" ] && bash "$CLAUDE_PROJECT_DIR/.ai/lib/figma-screenshot-hook.sh" || true

  • PostToolUse

    [ -f "$CLAUDE_PROJECT_DIR/.ai/lib/figma-screenshot-hook.sh" ] && bash "$CLAUDE_PROJECT_DIR/.ai/lib/figma-screenshot-hook.sh" || true

  • PostToolUse

    f="$(sed -n 's/.*"file_path" *: *"\([^"]*\)".*/\1/p' | head -1)"; if [ -n "$f" ]; then bash "${CLAUDE_PLUGIN_ROOT}/data/lib/validate-plugin-edit.sh" "$f"; fi

  • PostToolUse

    mkdir -p "$CLAUDE_PROJECT_DIR/.claude" && echo "[$(date '+%H:%M:%S')] Subagent completed" >> "$CLAUDE_PROJECT_DIR/.claude/subagent-log.txt" || true

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/compaction-reminder.sh"

View source on GitHub easingthemes.github.io

More from easingthemes/dx-aem-flow

All 4 plugins →

dx-aem

claude

AEM component verification, dialog inspection, demo capture, QA automation, and multi-platform project knowledge for Adobe Experience Manager projects

12 skills · 6 agents · 2 MCP servers · hooks

7

Eleven autonomous AI agents for ADO workflows — DoR checker, DoD checker, DoD fixer, PR reviewer, PR answerer, BugFix, QA, Dev, Doc, Estimation, and SimpleAgent. Run as ADO pipelines triggered by Azure-native Service Hooks (no AWS required); an AWS Lambda router is optional for central dedupe and rate limiting.

10 skills

7

dx-hub

claude

Multi-repo hub orchestration — run dx skills across sibling repositories from a single hub directory

5 skills

7

Similar plugins

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

headroomlabs-ai/headroom 79,508

Expose the plugin-safe Claude Code subset of Agentic Awesome Skills through a single marketplace entry.

200 skills

sickn33/agentic-awesome-skills 49,620

context-mode

claudecodex

Context window saver for 10 coding agents. Local and free: sandboxed code execution, FTS5 search, session continuity.

3 skills · 1 MCP server

mksglu/context-mode 34,004

Maintain dx-core?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins4 plugins