toy-crane

@toy-crane source repo

28 skills
0 followers
23 hours ago last updated

▌
Writing Great Skills · toy-crane bundle
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

0
installs
▌
Setup Supabase · toy-crane bundle
Set up or resume a minimal Supabase Cloud integration for an application, with optional email/password or Google authentication, the official profiles pattern, owner-only authorization, and a protected settings page. Use when a project needs Supabase connected or a learner-friendly Supabase Auth setup without broader backend features or production hardening.

0
installs
▌
Save · toy-crane bundle
Save any content (YouTube, web page, X post, document, text, or conversation) to Obsidian

0
installs
▌
Batch Save · toy-crane
Save multiple URLs in parallel to Obsidian. Fire-and-forget, no session switching needed. Use when user provides multiple URLs to save at once, says "batch save", "save these URLs", "여러 개 저장", "이것들 저장해줘", or pastes a list of links.

0
installs
▌
Excalidraw Diagram · toy-crane bundle
Create and edit Excalidraw diagram JSON files that make visual arguments with free-form spatial layouts. Use when the user wants to create, edit, fix, or review .excalidraw diagrams — including alignment, spacing, positioning, or visual quality issues. Prefer this over Mermaid when the diagram needs spatial freedom, custom positioning, evidence artifacts, or hand-crafted visual storytelling. Trigger whenever the user mentions "excalidraw", references a .excalidraw file, says "diagram", "draw", "visualize", or asks to explain something visually, even if they don't explicitly say "excalidraw".

0
installs
▌
Pr · toy-crane bundle
Publish the current repository change as a ready-for-review GitHub pull request 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, put work up for review, or make and share a GitHub review link. Complete the needed commit, base synchronization, and branch publication, but stop before merge.

0
installs
▌
Pull · toy-crane bundle
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 default branch; update a branch from its base; rebase onto a remote base; bring incoming base commits into the current checkout; or update a detached worktree from that base.

0
installs
▌
Push · toy-crane bundle
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 post-rebase lease-protected updates; it pushes existing commits only and does not commit dirty changes, create a PR, or merge.

0
installs
▌
Merge · toy-crane bundle
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 clean up only the merged worktree and its owned development processes. Always use this skill for an actual PR merge or its post-merge cleanup, including requests to inspect, finish, land, or merge an existing PR; create a PR and merge it; preserve meaningful commits; or clean up an already-merged worktree. Report an existing merge instead of duplicating it.

0
installs
▌
Commit · toy-crane bundle
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 changes into commits. Use it even when the request describes recording changes without saying "commit"; it performs the commit rather than only suggesting a message, and it does not push.

0
installs
▌
Tdd · toy-crane bundle
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

0
installs
▌
Expo Dev Loop · toy-crane bundle
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 Android simulator, emulator, or physical device. Establish target readiness and the scenario's required state, classify whether the change can use the Metro fast path or requires a native rebuild, then finish only with observable runtime evidence.

0
installs
▌
Implement · toy-crane bundle
Implement or resume settled work from a selected spec folder as one handoff bundle. Use when the user provides a `docs/specs/SLUG/` folder and wants its settled spec or approved tasks completed in the current checkout with verification, one completed and triaged automated code review, and a runnable product handoff when the repository exposes one through a local server.

0
installs
▌
Shape Idea · toy-crane bundle
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.

0
installs
▌
Draft Piece · toy-crane bundle
Draft or resume a piece from a selected docs/briefs/SLUG/ folder, or apply user corrections to an existing article. Verify reader understanding, embedded code, and confirmed writing criteria; preserve reusable feedback and preview locally when supported. Do not use to change the brief, define a publication, or commit or publish the piece.

0
installs
▌
Expo Smoke Test · toy-crane bundle
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 and an explicit state profile, coordinate shared prerequisites, then spawn exactly two isolated platform subagents—prefer the installed expo-smoke-runner profile—wait for both, and finish only with separate runtime evidence for each platform. For verifying one change on a single target during ordinary editing, use expo-dev-loop instead.

0
installs
▌
Define Piece · toy-crane bundle
Turn one topic and a rough direction into a confirmed brief for a single piece of writing, such as a blog post, newsletter issue, or page of copy, at docs/briefs/<slug>/brief.md. Use when the user wants to settle a piece's thesis, reader, scope, outline, or reader questions before any prose is written, or asks for a brief. Do not use to write the body, to define the publication itself, or to shape a code work unit, which belongs to shape-idea.

0
installs
▌
Human Review · toy-crane bundle
Help a human understand and inspect completed AI-authored repository work through actual results, before-and-after explanations, and supporting evidence. Use when the user asks to understand the work before accepting it, examine assumptions beyond an AI summary, or resume a human review after switching tasks. Also use for explicit requests to judge unresolved product behavior. Ordinary change summaries, automated defect hunting, and non-repository content do not need this skill.

0
installs
▌
Define Product · toy-crane bundle
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, success signals, assumptions, or unknowns, even when PRODUCT.md is not named. Start from an existing definition or a rough app direction. Do not use for blank-page idea discovery, architecture, or shaping or specifying one feature or work unit.

0
installs
▌
Build Prototype · toy-crane bundle
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 implementation or CLI, terminal, or voice interfaces.

0
installs
▌
Explain Visually · toy-crane bundle
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.

0
installs
▌
Split Into Tasks · toy-crane bundle
Split an implementation-ready spec into the fewest independently deliverable vertical tasks and select only risk-justified intermediate review checkpoints. Use when a spec has multiple outcomes needing separate delivery or dependency tracking; keep one coherent outcome as the spec itself.

0
installs
▌
Add Stack Context · toy-crane bundle
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.

0
installs
▌
Project Knowledge · toy-crane bundle
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 planning, or when a session applies a temporary workaround whose root cause stays open or observes an out-of-scope defect with evidence. Do not use for simple definitions, routine implementation details, or carrying out an already-settled decision.

0
installs
▌
Define Publication · toy-crane bundle
Interview the user to define or revise the standing premise of one writing medium, such as a product blog, newsletter, or brand site, then preserve it in docs/publications/<slug>.md. Always use for a new publication or any change to its readers, promised change, voice, coverage, medium conventions, or how a finished piece is evidenced, even when the file is not named. Start from a rough medium direction. Do not use to brief or draft one piece, and do not use for the app's product meaning, which belongs to define-product.

0
installs
▌
Resolve Follow Ups · toy-crane bundle
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 without automatic merge. Do not use to invent intended behavior or merely record a newly discovered follow-up.

0
installs
▌
Update Project Skills · toy-crane bundle
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, and materializing their companion custom agents for Claude Code and Codex. Use when the user asks to update, upgrade, refresh, or sync the skills or custom agents installed in a project. Third-party skills are refreshed in place only; project-local skills and agents stay untouched.

0
installs
▌
Maintain Project Context · toy-crane bundle
Clean, compact, and reconcile durable project context 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, glossary, decisions, specs, or agent instructions instead of PRODUCT.md, GLOSSARY.md, docs/decisions, docs/specs, AGENTS.md, or CLAUDE.md. Also use for confirmed shipped-spec retirement. Do not use to define new product intent, record one newly settled term or decision, look up context, shape a feature, or implement work.

0
installs

28 published skills