toycrane-skills

Plugin toycrane-skills from marketplace toycrane in toy-crane/skills. Commands read from the repo's manifest — today.

Skills (28)

• writing-great-skills

  Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

• expo-dev-loop

  Verify Expo and React Native changes in a running app with agent-device. Use after editing screens, navigation, interactions, app configuration, config plugins, native dependencies, permissions, startup behavior, or performance, or whenever the user asks to confirm an Expo change on an iOS or Androi

• expo-smoke-test

  Verify an Expo or React Native change together with the app's core loop on both iOS and Android using agent-device. Use before delivering a change, when the user asks to confirm behavior on both platforms, or when the core loop should be exercised again as a regression. Establish runtime readiness a

• babysit-pr

  Watch one open GitHub pull request through CI and review bots until it is ready to merge or needs a person, fixing confirmed findings and failing checks, answering and resolving review threads, and rerunning infrastructure flakes. Use when a pull request has just been opened or updated and its check

• clean-branches

  Clean up the local leftovers of finished work in one pass, removing worktrees and local branches whose pull request merged or closed, detached worktrees already contained in the base, and left-over worktree folders that lost their Git registration, while leaving open, uncommitted, session-attached,

• commit

  Create Git commits for the current request's in-scope changes as logical Conventional Commits. Always use this skill for an actual Git commit operation, including requests to commit or amend changes, save work in repository history, stage and record selected files, or group staged or unstaged change

• merge

  Carry the current repository change through a verified GitHub pull request merge into the requested base, or the repository's remote default branch when none is named, then hand the merged branch to clean-branches so its worktree and local branch are cleaned up with the project's declared cleanup co

• pr

  Create or reuse a ready-for-review GitHub PR for the current repository change against the requested base, or the repository's remote default branch when none is named. Always use this skill for an actual PR publication, including requests to create, open, raise, publish, or reuse a pull request, pu

• pull

  Rebase the current Git checkout onto the requested remote base branch, or the repository's remote default branch when none is named, without losing local work. Always use this skill for an actual base-branch synchronization operation, including requests to pull or sync main, master, trunk, or the de

• push

  Publish local Git commits on a named branch without losing local or remote work. Always use this skill for an actual Git branch publication, including requests to push, publish, upload, or put the current or detached checkout on origin or another Git remote. Use it for detached-HEAD publication and

• add-stack-context

  Audit and establish current agent context for the technologies that define a project's stack. Use when setting up a project for agent work, after selecting or adding a framework, library, developer tool, or hosted service, or when entering an existing project whose agent context has not been audited

• audit-evals

  Audit a project's LLM eval regression suite from its committed cell history, report cells whose most recent 10 trials all passed, checks with identical recent histories, cells that flip after graduating, and cells that always fail, then propose demoting the recently always-passing cells to the lower

• babysit-specs

  Revise active `docs/specs/SLUG/` specs so they match what has shipped since they were written. Use when earlier work has landed and queued specs may now rest on stale assumptions, acceptance criteria, constraints, terms, or prototypes, or when implementation reports a spec as stale before changing s

• build-prototype

  Build a complete dummy-data HTML prototype or a temporary comparison of up to three alternatives for a specific user situation. Use to settle a screen-based product before implementation or resolve a visual or interaction decision during shaping or prototype review. Do not use for production impleme

• define-product

  Interview the user to define or revise the app's overall product direction, then preserve the confirmed meaning in root PRODUCT.md. Always use for a new app direction or any app-wide change to users, usage situations, problem, promised change, core loop, durable boundaries, experience principles, su

• explain-visually

  Render an explanation as a diagram, comparison, trace with real values, or annotated code. Use when the user asks to have a concept, decision, flow, or code explained, or says they do not follow.

• implement

  Implement or resume settled work from one selected spec folder as one handoff bundle. Use when the user provides a `docs/specs/SLUG/` folder and wants its settled spec completed in the current checkout with verification, one completed and triaged automated code review, a ready-for-review pull reques

• llm-evals

  Prove LLM behavior with evals. Use when an acceptance criterion or request concerns the quality of LLM or agent output that varies run to run and no deterministic assertion can decide, such as a prompt, classifier, extractor, summarizer, tool-using agent, or a skill's instructions, whether `implemen

• maintain-project-context

  Clean, compact, and reconcile durable project context and any configured issue-tracker mirror without changing established meaning. Always use this skill whenever a request cleans, audits, or checks consistency across two or more durable context sources, even when they are called product docs, gloss

• project-knowledge

  Maintain a project's canonical terms and settled decisions that future work should reuse, and record follow-ups a session discovers but does not resolve. Use when project-specific terms are being clarified, when a choice that may constrain future work is being considered or settles, including during

• resolve-follow-ups

  Resolve evidence-backed `docs/follow-ups/*.md` through a bounded manual, Codex Scheduled task, or Claude Routine sweep. Use when project follow-ups should be reproduced before editing, handled by one isolated worker and branch per item, and published as independent ready-for-review pull requests wit

• review-sessions

  Review this machine's recent Claude Code and Codex session logs for work agents redo by chance every session, and report candidates to hand to a deterministic owner (a hook or permission rule, a lint or protected path, a bundled script, a script interface, a project config or doctor, or one skill se

• self-ship

  Carry one settled `docs/specs/SLUG/` folder from implementation through a verified merge and cleanup with no person present, asking everything a person must answer at the start and later only through the question tool. Runs only when the user invokes it by name with one spec folder; it never runs a

• setup-issue-tracker

  Record once per repository which issue tracker coordinates spec folders and, when requested, scheduled triage of human-written issues. Run by hand before parallel implementation or issue triage; rerun to change trackers or upgrade an older convention.

• shape-idea

  Turn a chosen problem and broad direction into shared decisions and an implementation-ready spec. Use when the user wants to clarify behavior or scope, stress-test an idea, align before implementation, or produce a spec.

• tdd

  Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions TDD or "red-green-refactor", asks for tests that prove a behavior, wants a bug reproduced as a failing test, or wants integration tests. Not for only running an existing test suite.

• triage-issues

  Triage general issues from a configured issue tracker once, when each comes due, in a scheduled or manual run, or one named issue. Investigate, ask only decisions that need a person, raise one implementation or spec pull request when ready, run due post-release checks, and return one report of what

• update-project-skills

  Update every skill installed in the current Git project to its latest published version through skills.sh, from toy-crane/skills and every other source, then reconcile the Toycrane set by installing newly published skills that fit the project's stack, retiring unpublished ones, materializing their c

Similar plugins