claude

dev-workflows

Six slash commands for the implementation half of the product lifecycle: `/design` turns a specification into a design, with Opus review and an optional three-take fan-out on a contested interface. `/implement` builds it, gated by Opus plan critique and code review before tests. `/ready` verifies an ARD/spec/design chain's readiness, read-only, no tracker read. `/conformance` traces every requirement against an Epic's branch, or each repository's default branch, and records how each discrepancy is settled. `/upgrade` plans and executes dependency upgrades; `/vuln` researches and fixes a CVE. Fourteen subagents, one hook, nineteen reference files, no bundled skill. Every code-changing command commits before the run ends; push and PR sit behind one consent choice. Depends on the companion `workflows-core` plugin. Neither `product-workflows` nor `docs-workflows` is a dependency.

2 on GitHubby Ivan Gudakv4.63.0MITupdated todaydevelopment
/

Plugin dev-workflows from marketplace shipwright in ihudak/ai-workflows. Commands read from the repo's manifest — today.

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

What it installs

Slash commands (6)

  • /dev-workflows:conformance

    Delivery conformance check. Given an Epic (run by its Dev, before its pull request merges) or a PRD (run by the PE, once every Epic has merged), traces every requirement against the Epic's branch, or each repository's default branch, has a person settle each discrepancy — fix the code, amend the doc

  • /dev-workflows:design

    keyed engineering-design workflow (Dev phase). Takes over a merged specification.md from the specs repo's main branch, grounds strictly in the fully-mounted implementation code, and authors a reviewed engineering design.md through a relentless one-question-at-a-time grill that challenges the spec an

  • /dev-workflows:implement

    End-to-end code implementation workflow. Classifies task risk, creates a branch, plans (Opus for SIGNIFICANT/HIGH-RISK), implements, writes tests, runs Opus code review, and performs post-session maintenance.

  • /dev-workflows:ready

    Artifact-anchored readiness gate. Derives the workflow phase of a PRD/Epic from its artifacts and verifies the ARD/spec/design artifacts justify it and the next transition; returns SUPPORTED / PARTIAL / NOT-SUPPORTED with a coverage roll-up. Never sets a status anywhere; never stops on an unmerged a

  • /dev-workflows:upgrade

    Component upgrade workflow. Upgrades libraries, frameworks, runtimes, or build tools to specified or latest versions. Plans with Opus for complex upgrades, runs code review, and verifies with tests.

  • /dev-workflows:vuln

    Security vulnerability fix workflow. Researches CVEs via NVD, applies dependency and code fixes one at a time, runs Opus code review, and verifies with tests.

Subagents (14)

  • code-review

    Post-implementation code review for SIGNIFICANT / HIGH-RISK tasks, and for /implement's MODERATE ones. Checks correctness, security, architecture, edge cases, migration, dependencies, tests, rollback. Returns PASS / PASS WITH RECOMMENDATIONS / BLOCK and gates the test run. Uses Claude Opus.

  • code-writer

    Writes the code for one group of an approved plan's steps — or one fix attempt from a failing test, lint or build — for /implement, in the branched repository only. Runs no test, lint, build or type-check in the repository, writes no git state, dispatches nothing and never asks the user; returns don

  • conformance-tracer

    Traces a list of requirements against one code repository at one ref, read-only there, for /conformance. Writes to the output file its caller names one verdict per requirement — satisfied, partial, missing, contradicts or not-checkable — each with exact file:line@commit evidence, or a tight range, a

  • design-reviewer

    Reviews an engineering design.md authored by /design against the design-format authority and traceability to its specification.md — architecture/interface/seam/test-strategy soundness, coverage of every in-scope requirement, decision-completeness, and every claim the design makes about the existing

  • interface-designer

    Produces ONE interface proposal for ONE contested interface under ONE named design constraint, for `/design`'s Phase 5 fan-out. Dispatched three times in parallel with different constraints so the takes diverge; the caller compares them on depth, locality, and seam placement. Read-only — proposes an

  • readiness-reviewer

    Cross-artifact readiness verifier for /ready. Takes the phase the caller derived from the artifacts and checks the ARD/spec/design artifacts justify that phase and the next transition. Returns SUPPORTED / PARTIAL / NOT-SUPPORTED. Uses Claude Opus. The only reviewer that synthesises a verdict across

  • review-fixer

    Applies targeted code fixes for BLOCKER and MAJOR findings from a code-review agent report, and MINOR ones where the caller asks for them, as /implement does. Returns a structured fix report; the caller re-runs the review, save after a User-applied pass that follows its last review, which no review

  • risk-planner

    Risk-weighted planner for SIGNIFICANT / HIGH-RISK tasks. Returns a structured plan with an explicit risks section. Uses Claude Opus. Do NOT use for SIMPLE / MODERATE tasks.

  • test-baseliner

    Run every test suite step 1's detection table covers — all of them where a repository has several, and the test command the repository declares for itself where the table covers none — and return structured results for regression comparison. Operates in two modes — "capture" (run tests, record basel

  • test-writer

    Writes tests for new or changed behavior based on a diff. Does NOT run tests. Takes the framework from the required test-baseliner baseline rather than re-detecting it — one framework, or several where the repository has several suites; where that baseline names none at all, returns "not detected" i

  • upgrade-executor

    Agent for the upgrade workflow. Handles Phase 2 (execution) for a single component: apply the upgrade plan produced by upgrade-planner, run the build, verify tests via test-baseliner, and auto-fix any test code breakage caused by the new version's API changes. Invoked sequentially by the /upgrade co

  • upgrade-planner

    Agent for the upgrade workflow. Handles Phase 1 (compatibility planning) for a single component: detect the component in the repo, resolve the requested target version (exact, minor, latest, lts, or bare), and verify compatibility with all other components in the repo. Invoked in parallel by the upg

  • vuln-fixer

    Agent for the vuln workflow. Handles the fix phase of CVE remediation: read the baseline the orchestrator captured, create the fix branch before touching a file, apply the minimal version change produced by vuln-research, rebuild, and verify tests via test-baseliner — leaving the change on that bran

  • vuln-research

    Agent for the vuln workflow. Handles the read-only research phase of CVE remediation: NVD API lookup, library detection in the repository, current version discovery, and minimum safe version resolution. Invoked explicitly by the /vuln command orchestrator — NOT triggered by direct user prompts. Acce

Hooks (1)

  • UserPromptSubmit

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

View source on GitHub

More from ihudak/ai-workflows

All 8 plugins →

Seventeen slash commands for defining a product — its requirements, architecture and specification: a six-command BRD-to-PRD route (/brd-intake → /brd-split → /prd-ground → /brd-split → /brd-interview → /brd-package → /brd-reconcile) that grounds a customer's requirements document, settles it with them and seeds the PRD, ARD and specification; the idea→PRD→ARD→specification ladder (/idea → /create-prd → /update-prd → /create-ard → /specify), /update-spec revising a merged specification, and /prd-ground optionally grounding the PRD; /epics, deriving Epics; /harvest-decisions and /promote-decisions, keeping merged ARD decisions as team records and promoting them to organisation ADRs; and /prd-proposal and /brd-proposal, pricing graded requirements in human hours, never money. Fourteen agents carry the grounding, review and Epic writing; twelve reference files define the shared formats.

17 commands · 14 agents · hooks

2

Shared foundation for the workflow plugin family: the addressing grammar and specs-repo git entry points, phase handoff, model routing, escalation and finding-triage rules, documentation and architecture grounding, cost/feedback/follow-up emission, and the reference loader skill that lets a dependent plugin read them. Also carries the family-meta utility commands — /feedback, /prompt, /prompt-brainstorm, /prompt-grill-me, /statusline — /frames for indexing design frame sets, and /diagnose-session for reading a session's transcripts to report, with evidence, why a run went wrong.

3 skills · 7 commands · 11 agents · hooks

2

Commands for a product's documentation and release notes. /docs-init scaffolds a documentation repository from nothing: a Material for MkDocs skeleton, public and internal builds over one content root, Vale, CI and a docs-profile.yml. /docs-brand extracts a logo and colour pair from the product's code and applies them, WCAG contrast-checked. /docs-serve runs the site's dev server. /docs-audit turns the product's own code and specs tree into a coverage grid and a prioritised backlog of the pages it is missing, behind an Opus review gate. /document edits prose directly, or keyed to a PRD folder writes product docs from its implementation diffs behind an Opus review gate. /docs-profile refreshes a docs repository's machine-readable profile; /release-notes drafts a destination-shaped entry from the same folder. Depends on workflows-core and prose-style.

1 skill · 7 commands · 11 agents · hooks

2

Pluggable prose style checker and writing aid for documentation, planning documents, and release notes. Ships a vendor-neutral baseline — terminology, word list, voice and tone, grammar, formatting, UI interactions, inclusive language, and prose accessibility — distilled from the Microsoft, Google, and Apple style guides, Chicago, the Conscious Style Guide, and WCAG. Point it at your own organization's style guide and the overlay augments or overrides that baseline; every resolution miss falls back silently. Provides /prose-review-pr, /prose-review-docs (with --fix), /prose-style-refresh, a prose-style-checker agent, a prose-fixer agent, and a prose-style-rules skill.

1 skill · 3 commands · 2 agents

2

Reviews an OpenAPI specification against bundled REST API and IAM permission-naming guidance, and reviews application code or UI against bundled public design-system and accessibility standards. Ships the guidance it reviews against — Google AIP, Zalando, Microsoft REST, OpenAPI 3.1 and ~20 RFCs for APIs; Apple HIG, Material Design 3, Microsoft Fluent 2, W3C WCAG 2.2, ARIA APG and NN/g for interfaces — plus a Spectral ruleset that runs against a spec directly. Standalone: it consumes no workflow artefact and produces none.

2 commands · 2 agents

2

acli

claude

Atlassian CLI (acli) reference skill for Jira and Confluence: JQL search, work items, comments, links, attachments, watchers, projects, sprints, boards, filters, and Confluence spaces, pages and blog posts. Adds container-friendly authentication (token on stdin; --web OAuth cannot complete without a browser) and a write policy in which --yes carries the user's approval, given in the conversation first, and a blast-radius count precedes any --jql/--filter mutation. Requires the acli binary on PATH.

1 skill

2

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

diagram-design

claudecodex

Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.

1 skill · 7 commands

cathrynlavery/diagram-design 66,757

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain dev-workflows?

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 plugins8 plugins