shipyard-delivery

Plugin shipyard-delivery from marketplace shipyard in lokeshrana9999/shipyard. Commands read from the repo's manifest — 9 days ago.

Skills (14)

• build-workflow

  Runs a plan, the remaining delivery stages, or another multi-step job as one multi-agent run, after deciding whether one agent is enough, with capped fix loops and a separate verifier; or writes one agent or sub-session brief from its template. Takes a goal or plan file, the stages to run, `go` to s

• db-migration

  Plans and makes database migrations through the project's migration tool (shipped for Prisma). Use when asked to "plan a migration", "add a field to the Prisma schema", "rename this column", or "check this migration", when changing a database schema, migrating a model, field, enum, or relation, or c

• design-tests

  Designs the tests for a feature from its spec and its real code, as a test-design document an implementer turns into tests. Use when asked "design tests for this", "write a test plan", or "what should we test?", to decide what to verify, or before tests are written for a change. It designs only; it

• eval-loop

  Improves prompt, skill, or instruction text in scored rounds against locked eval cases, with a frozen grader hash, replicates, holdout cases, and a human read of raw transcripts before pass. Use when asked to "run the evals and fix the prompt", "make the bot pass its cases", "is the new prompt bette

• flow-diagram

  Draws flowcharts, sequence and state diagrams for any written artifact (plan, PR, issue, doc), in Mermaid where it renders and ASCII elsewhere, reusing the plan's diagram for the same flow. Use when asked to "draw a diagram of this flow" or "add a sequence diagram", when about to draw any diagram, o

• grill-plan

  Turns a build ask into a confirmed plan file through numbered question rounds, each with a recommended answer, settling caps and defaults before code. Use when asked to "plan this", "grill me on this", or "let's plan before we build", when a multi-part ask, a new tool, or a public or irreversible ch

• land

  Lands a verified, reviewed branch on its base. Takes the repo lock, syncs the base, runs the project gate, merges as the project settings allow, records the merge with a read-back, waits a bounded time for the deploy, closes linked issues, and writes a report with a named verdict. Takes the branch t

• live-verify

  Verifies a change in the running app or browser extension, or checks a list of claims against it, and writes a report bound to the verified commit. Use when asked to "check it actually works", "does it actually work", "verify this live", "check it live", "smoke-test it in the browser", or "verify th

• pr-description

  Drafts the pull request title and body from the branch's diff and history, shows it for approval, then creates or updates the pull request on the project's code host. Run only when the user asks to write, draft, or publish the PR description.

• pr-review

  Reviews the current branch or a pull request in two agent stages and reports only validated findings, with an advisory ship verdict. Unlike a general code review, it checks the project's own recurring concerns and prints how much of its catalog it covered. Takes a base branch or pull request; `mine`

• runner-creation

  Creates or hardens an unattended runner, the wrapper, pre-flight gate, permission profile, ledger, watchdog, and caps around a headless agent run. Use when asked to "schedule this", "run it every N hours", "make a headless sweep", or "why does the runner waste tokens", or when a runner double-launch

• ship

  Places the current branch in the delivery pipeline from the evidence on disk and names the next stage, or hands the rest to a multi-agent run. Use when asked "ship this", "what's next in the pipeline", "where am I in the pipeline", "what's left before I open a PR", or "take this to PR". Not for "wha

• skill-auditor

  Audits SKILL.md files and writes a scored report with concrete fixes. Use when asked to "audit this skill", "review my skills", or "score this SKILL.md", to critique, grade, or lint a skill or a folder of skills, or before publishing or porting one into a plugin. Not for creating or rewriting a skil

• walkthrough

  Explains things and writes reader-facing documents answer-first, ending with one next action. Use when asked "explain how this works", "walk me through this", "why did this break", or "write up a handoff", when giving a multi-step plan, or when writing a plan, spec, or report for someone to act on.

Subagents (4)

• concern-reviewer

  Maps a review catalog onto one slice of a diff and reviews every concern it maps. Reads the whole catalog and its slice's added lines, writes out each concern with its exact sites, then reads the real code (callers, callees, tests) and returns a finding with a concrete failure scenario or clears the

• live-verifier

  Verifies a change in the running app, unattended. It boots the app, gets its own test session, drives the changed flow over HTTP or in a browser, confirms the stored effect, and returns a structured pass, fail, or blocked result with evidence. Use after implementation and tests pass, when a change n

• review-verifier

  Skeptically validates review findings, or claims that findings were fixed, against the code before anyone acts on them. Given every finding from a review (each quoting an added line) and the diff, it checks the quoted line, reads the real code, callers, and tests, and tags each finding confirmed, fa

• test-designer

  Designs the tests for a feature or slice of one, unattended, from its spec and its real implementation, and returns a test-design document with open questions listed instead of asked. Read-only. Use when a multi-agent run needs test designs for one or more slices in parallel, or when test design sho

Similar plugins