claude

shipyard

Turn your idea into working code — Shipyard runs Claude Code through a spec-driven agile sprint lifecycle: discuss features, plan sprints, build with TDD, review, and ship.

0 on GitHubby Acendasv3.26.0MITupdated 23 days agodevelopment
/

Plugin shipyard from marketplace acendas in Acendas/acendas-marketplace. Commands read from the repo's manifest — 23 days ago.

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 (32)

  • acquiring-skill-lock

    Acquire a per-project lock for the current skill.

  • anti-stub-scan

    Scan a diff for stub patterns and TODO markers.

  • authoring-acceptance-probe

    Author a runnable acceptance probe from criteria.

  • discovering-edge-cases

    Discover edge cases and adversarial inputs.

  • dispatching-code-review

    Dispatch a fresh-context code review subagent.

  • dispatching-gap-analysis

    Dispatch a review gap-analysis subagent.

  • dispatching-operational-task

    Dispatch a Shipyard operational task subagent.

  • dispatching-research-task

    Dispatch a Shipyard research task subagent.

  • dispatching-spec-review

    Dispatch a fresh-context spec review subagent.

  • dispatching-task-loop

    Dispatch a fresh-context feature task subagent.

  • dispatching-track-coordinator

    Dispatch a track coordinator for one feature track.

  • escalating-to-thinker

    Dispatch a think-tier consult when the pipeline is stuck.

  • evaluating-sprint-complete

    Evaluate the eight-invariant sprint-complete predicate.

  • extracting-acceptance-criteria

    Extract atomic acceptance criteria from a feature.

  • running-acceptance-probe

    Run a task's acceptance probe and capture output.

  • ship-backlog

    View and groom the Shipyard backlog.

  • ship-bug

    File a bug or hotfix with minimal ceremony.

  • ship-debug

    Systematic debugging with persistent cross-session state.

  • ship-discuss

    Discover features from idea to full spec.

  • ship-execute

    Execute the current sprint in test-first waves.

  • ship-help

    Ask Shipyard questions or run workflow actions.

  • ship-quick

    Land a single self-contained change with quality bar.

  • ship-review

    Run multi-agent review, retrospective, and release.

  • ship-spec

    View, search, and manage the product spec.

  • ship-sprint

    Plan a new sprint or cancel an active one.

  • ship-status

    Show the Shipyard project dashboard and next steps.

  • splitting-stories

    Split a story or task into smaller pieces.

  • tdd-cycle

    Enforce the Red-Green-Refactor TDD cycle.

  • using-worktrees

    Give a task its own filesystem checkout.

  • validating-e2e-coverage

    Validate E2E acceptance criteria coverage.

  • verifying-completion

    Verify completion claims with evidence before commit.

  • verifying-wave-completion

    Verify wave completion across six invariants.

Subagents (7)

  • shipyard-code-reviewer

    Read-only code-quality reviewer for a Shipyard task/wave/feature/sprint diff. Scans a git diff against a set of concern domains (security, bugs, silent-failures, patterns, tests, observability, data) and returns structured findings with confidence scores. Dispatched by the `dispatching-code-review`

  • shipyard-disciplined-builder

    TDD-disciplined implementer for one Shipyard feature task in an isolated worktree. Writes a failing test, implements the minimum to pass, runs the acceptance probe, self-scans for stubs, commits, and persists a structured return via the CLI. Dispatched by the `dispatching-task-loop` capability skill

  • shipyard-gap-analyst

    Read-only gap analyst for Shipyard review. Compares specs, delivered behavior, test evidence, spec-review findings, and goal-verification artifacts; returns structured gaps plus the Stage 4.5 self-review checklist. Dispatched by the `dispatching-gap-analysis` capability skill — never invoked standal

  • shipyard-operational-task

    Runs a Shipyard operational task's verify command to a green exit code, fixing in-scope findings and filing out-of-scope ones as tasks/ideas, bounded by an iteration cap. Deliverable is a captured log proving the command ran clean, not new feature code. Dispatched by the `dispatching-operational-tas

  • shipyard-researcher

    Investigates a Shipyard research task and produces one markdown findings doc with a concrete, evidence-backed recommendation. Write scope is contractually limited to a single output file. Dispatched by the `dispatching-research-task` capability skill with a brief containing task/feature paths, the f

  • shipyard-spec-reviewer

    Read-only spec-compliance reviewer for a Shipyard task/wave/feature/sprint scope. Maps acceptance criteria to code and tests, classifies each MET/PARTIAL/MISSING/OVER-BUILT, and returns a structured verdict. Dispatched by the `dispatching-spec-review` capability skill with a brief containing scope,

  • shipyard-track-coordinator

    Coordinates nested per-task builders for one Shipyard feature track within a single wave — dispatches `shipyard-disciplined-builder` sequentially per task, maintains a running TRACK NOTES block prepended to each successive builder's brief, broadcasts interface changes to sibling track coordinators,

Hooks (4)

  • SessionStart

    node "${CLAUDE_PLUGIN_ROOT}/bin/hook-runner.mjs" plugin-data-breadcrumb

  • SessionEnd

    node "${CLAUDE_PLUGIN_ROOT}/bin/hook-runner.mjs" lock-reap

  • PreToolUse

    node "${CLAUDE_PLUGIN_ROOT}/bin/hook-runner.mjs" auto-approve-data

  • WorktreeCreate

    node "${CLAUDE_PLUGIN_ROOT}/bin/hook-runner.mjs" worktree-branch

View source on GitHub

More from Acendas/acendas-marketplace

All 3 plugins →

Unified Jira Cloud + Confluence Cloud + Bitbucket Cloud + QMetry Test Management integration for Claude Code. Jira (issues, backlog ordering/rank, sprints, versions, search, attachments, remote links), Confluence (pages, comments, attachments, backlinks, page properties), Bitbucket (PRs, tasks, source browse + blame, pipelines incl. watching a run to its outcome, deployments, branch restrictions), QMetry (projects, full test-case/cycle/step CRUD, test plans, execution results, execution update with status/comment/assignee + execution-level attachment, requirement traceability), plus a 12-scanner PR review pipeline with adversarial critic and deep-dive investigator. Safe docs->Confluence publishing (confluence_publish_preflight / publish_page / markdown_to_storage / render_mermaid / sync_attachments): renders ```mermaid fences to SVG and attaches them in place via a detected local mermaid CLI or a self-hosted Kroki endpoint (never a third-party service by default, and no bundled Chromium); renders Markdown straight to storage XML rather than through ADF, carries <ac:inline-comment-marker> anchors across a page rewrite, refuses to publish when a reviewer's comment or a diagram would be orphaned, and verifies against Confluence's own dangling-comment list afterwards with a restore-version rollback. Credentials stored in ~/.acendas-atlassian/config.json with atomic-write + rolling backup.

45 skills · 21 agents · 1 MCP server

0

Android debugging for Claude Code: breakpoints, stepping, heap and trace inspection, HotSwap, static graphs, debug plans, and event-driven UI driving on live devices.

15 skills · 1 agent · 1 MCP server

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

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

Maintain shipyard?

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 plugins3 plugins