claude

workflows-core

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.

2 on GitHubby Ivan Gudakv1.85.0MITupdated todaydevelopment
/

Plugin workflows-core 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

Skills (3)

  • model-routing

    Loads the plugin family's task-complexity classification rules and model fallback chain (workflows-core:model-routing/classification). Invoked at the classification step by every pipeline command across the family, so each loads one copy of the rules from one named entry point rather than citing the

  • reference

    Read a shared workflows-core reference by name, or one part of a reference that loads by part, and optionally execute one of its entry points.

  • specs-git

    Runs a command's specs-repository start and end (specs-preflight, commit-artifacts) through specs-git.py, and says which of its lines to print and where.

Slash commands (7)

  • /workflows-core:diagnose-session

    Read a session's transcripts on disk and report what happened in a run of this plugin family that went wrong — repeated work, an ignored plan, stumbles, a step that did not fire, too slow or too expensive — with a `path:line` citation behind every finding. Agrees the problem with you first, triages

  • /workflows-core:feedback

    Log a manual note about this plugin family itself — friction you hit or an improvement you want — to the per-PRD feedback file in the specs repo, for the plugin maintainer to aggregate. Tied to no command; run any time.

  • /workflows-core:frames

    (Re)builds the frame-set index of one BRD, PRD or Epic folder: for each design/<frame-set>/ it lists the images, reads the index already there, describes the frames no row accounts for and writes the index grounding-format §6 requires. Use after dropping in a frame set exported by hand, which design

  • /workflows-core:prompt-brainstorm

    Log a corrective interaction as plugin feedback, then hand off to superpowers:brainstorming, where installed, to redesign the correction together — or, without it, point to /prompt-grill-me. Captures the friction, your verbatim prompt (secrets, email addresses, non-public hosts, IP addresses and hom

  • /workflows-core:prompt-grill-me

    Log a corrective interaction as plugin feedback, then grill the fix inline — a bounded one-question-at-a-time interrogation (≤5 questions) of the correction following the embedded grilling technique. Self-contained; no plugin dependency.

  • /workflows-core:prompt

    Log a corrective interaction — a command produced something wrong and you're fixing it — as plugin feedback, then act on your correction directly. Captures the friction, your verbatim prompt (secrets, email addresses, non-public hosts, IP addresses and home paths redacted), and the resolution to the

  • /workflows-core:statusline

    Install the plugin family's multi-line status line (session identity, git, context bar, cost, tokens, rate limits) into your Claude Code settings. Vendors the script to a stable per-user path, backs up anything it would overwrite, and — given jq — writes the cost snapshot behind session cost reporti

Subagents (11)

  • adr-drafter

    Writes the body of one scaffolded organisation ADR for /product-workflows:promote-decisions — Context opening with the Origin line that names the team records, Decision, Consequences and Glossary terms — from the team records it promotes or, for a superseding proposal, from the accepted ADR it would

  • architecture-grounder

    Read-only architecture grounding for /create-ard, /specify and /design. From an architecture repository (radar, standards, principles, patterns, accepted ADRs) and/or the team's harvested decisions, returns a bounded digest: arch_references (what settles or constrains the work, quoted and linked) an

  • code-scanner

    Scans one code repository for existing capabilities and gaps against a set of themes — from a PRD or Epic, an implementation spec, an item being specified, an idea, the documentation surface kinds, an engineering design or architect-driven discovery — broad-then-narrow where its caller asks (model-r

  • defect-reporter

    Bugs-only post-session reporter used under --skip-feedback in place of impl-maintenance. Reads the compact session handoff and returns only real defects fixable in this plugin family or in the ai-containers environment — each with its location, the session evidence and a minimal repro — or none. Exc

  • doc-fixer

    Applies targeted fixes for BLOCKER and MAJOR findings from a doc-reviewer or epic-reviewer report, or for violations from docs-style-checker / prose-style-checker. Mirrors review-fixer for the docs domain. Returns a structured fix report; caller re-runs the reviewer. Shared between `/document` and `

  • docs-grounder

    Read-only documentation grounding for authoring commands. Given $DOCS_PATH, a feature summary and an optional key or themes, returns a bounded digest: docs_references (same-feature facts, precedents to model after) and docs_challenges (already documented, a terminology mismatch, a contradiction, a d

  • frame-describer

    Reads the frames of one exported design frame set and returns one plain-language description per frame — what screen, report, or state it depicts and what it shows on it. Read-only, bounded by a caller-supplied frame list. Produces no finding, cites no requirement, and reconciles nothing. Model tier

  • impl-maintenance

    Post-session maintenance agent. Reads what happened during an implementation, fix, or upgrade session and produces a structured Lessons Learned report with actionable suggestions for improving project tooling — CLAUDE.md rules, reference docs, hooks, command workflows, new skill patterns, and fixes

  • overlap-reader

    Read-only overlap read for /dev-workflows:design, /product-workflows:specify and /product-workflows:update-spec before a play-back gate, and over the edits and decisions answering the last review. From the draft, the run's decisions, a design's specification and the inherited [AD#N] Rules, lists gri

  • promotion-scout

    Read-only comparison for /product-workflows:promote-decisions. Given the candidate records of the team's architecture knowledge base, their deterministic signals and an architecture repository, returns for each record whether an accepted ADR or active standard already covers it, contradicts it, or n

  • session-analyst

    Reads one session's transcripts on disk for ONE dimension of `/diagnose-session`'s triage — timeline, plan adherence, repeated work, stumbles, claims and evidence, conflicting instructions, or cost and time — and returns findings, each citing the `path:line` it rests on. Dispatched seven times in pa

Hooks (2)

  • Stop

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/notify-done.sh"

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/test-notify.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

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.

6 commands · 14 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

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

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain workflows-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 plugins8 plugins