ystack
ystack contains 12 collected skills from yulonghe97, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
Create a pull request after verification and docs are updated. Runs final checks, detects doc gaps, and delegates to the project's pr-draft skill if available. Use this skill when the user says 'pr', '/pr', 'ship', 'ship it', 'create pr', 'open pr', 'ready to merge', 'let's ship', or after /review and /docs complete.
Take a bug, ticket, or feature from investigation all the way to a draft PR in one autonomous run — `/goal` planning plus the full ystack chain (/build → /go → /qa → /review → /docs → /pr), orchestrated end-to-end without stopping between phases. Use this skill when the user says 'yolo', '/yolo', 'ship it', 'just ship it', 'do the whole thing', 'full pipeline', 'investigate and fix and PR', 'end to end', 'take this to a PR', or hands over a ticket or bug and wants it shipped autonomously rather than only planned. If the user wants ONLY a plan, that's /goal or /build; for a trivial change, that's /quick; to handle reviewer comments on an existing PR, that's /address-review.
Fetch PR review comments, triage them by priority, and address them. Use this skill when the user says 'address review', '/address-review', 'address comments', 'fix review comments', 'address feedback', 'handle PR comments', 'review feedback', 'what do reviewers say', 'check PR comments', or when a PR has review comments that need to be addressed. Works with comments from human reviewers, AI reviewers, and CI checks.
Browser automation for QA testing via Playwright MCP. Navigate pages, click elements, fill forms, take screenshots, check console errors, and verify page state. Used by /qa for visual testing. Use this skill when the user says 'browse', '/browse', 'open browser', 'check the page', 'screenshot', or when /qa needs to test affected pages. Requires Playwright MCP to be registered (see Setup).
Plan a feature by reading documentation and code, surfacing assumptions, capturing decisions, and creating an execution plan with goal-backward success criteria. Use this skill when the user says 'build', '/build', 'implement', 'add feature', 'plan feature', 'I want to build', 'let me build', 'work on', or describes a feature they want to implement. This is the entry point for the ystack workflow — it produces a PLAN.md that /go executes, plus a local plan.html preview for user approval.
Update documentation for completed work. Only updates docs for features that are implemented and verified — never for planned or in-progress work. Use this skill when the user says 'docs', '/docs', 'update docs', 'update documentation', 'sync docs', or after /review passes and before /pr.
Execute a plan created by /build. Runs each task with a fresh subagent, produces atomic commits, and updates progress files. Use this skill when the user says 'go', '/go', 'execute', 'run the plan', 'execute the plan', 'start building', 'let's do it', or confirms a plan and wants to proceed with implementation. Requires a PLAN.md from a prior /build run.
Analyze an existing codebase and generate a ystack module registry, progress files, and a documentation gap report. Use this skill when the user says 'import', '/import', 'adopt this project', 'onboard this repo', 'scan the codebase', 'set up ystack here', or when adding ystack to a project that already has code and possibly docs. Supports incremental adoption with --module flag.
Plan-driven QA testing with agentic self-testing as first-class, automated tests next, browser testing last (and optional). Develops a QA plan covering project standards compliance + feature completeness, spawns parallel sub-agents to execute it, reports issues to QA-REPORT.md, and optionally runs a bug-fixing loop when requested. Use this skill when the user says 'qa', '/qa', 'test it', 'run qa', 'check if it works', 'does it build', 'run the checks', or after /go completes. Runs between /go and /review. Use '--fix' to allow automatic fixes. Optionally accepts a URL for frontend features: '/qa http://localhost:3000'.
Fast path for bug fixes, chores, and small changes that don't need full planning. Skips /build planning, progress tracking, and /docs. Use this skill when the user says 'quick', '/quick', 'quick fix', 'just fix', 'small fix', 'hotfix', 'chore', 'bump', 'typo', 'quick change', or describes a change that's clearly a bug fix, dependency update, config tweak, or other small change that doesn't represent a new feature or architectural change.
Code review with multi-agent parallel analysis and confidence-based scoring. Use this skill when the user says 'review', '/review', 'check my work', 'verify', 'did it work', 'is it done', 'review the changes', or after /go completes and the user wants to verify the implementation before shipping. Also supports reviewing external PRs by URL (e.g., '/review owner/repo#123').
Scaffold documentation structure from a plan. Two modes: (1) full-project — takes a markdown plan describing all modules and their relationships, produces doc stubs, module registry, Mermaid architecture diagrams, and progress files. (2) single-module — adds one new module to an existing project. Use this skill when the user says 'scaffold', '/scaffold', 'scaffold docs', 'scaffold project', 'set up the docs', 'add a module', 'new module', 'scaffold module', 'turn this plan into docs', 'bootstrap project', or provides a high-level plan they want to turn into structured documentation.