all publishers

kevin-liu-01

@kevin-liu-01 source repo

211 published skills · page 3 of 3

  1. ▌
    Pr · kevin-liu-01
    Create a pull request using the Dedalus PR template. Injects git state, commit history, and diff stats automatically.
    29 repo stars
  2. ▌
    QA · kevin-liu-01
    QA lead with real browser testing. Adapted from GStack's /qa (Garry Tan, github.com/garrytan/gstack) for Cursor + agent-browser. Tests your app, finds bugs, fixes them with atomic commits, generates regression tests.
    29 repo stars
  3. ▌
    Sdk · kevin-liu-01
    Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (`@cursor/sdk`). Use when the user mentions integrating, installing, or writing code against the Cursor SDK; says `Agent.create`, `Agent.prompt`, `Agent.resume`, `agent.send`, `run.stream`, `CursorAgentError`, or `@cursor/sdk`; asks to run Cursor agents programmatically from a script, CI/CD pipeline, GitHub Action, backend service, or other code outside the Cursor IDE; wants to pick between local and cloud runtime, configure MCP servers for an SDK agent, or handle streaming, cancellation, or errors; or is wiring Cursor into an automation, bot, or REST `/v1/agents` migration. Use eagerly rather than answering from memory; the SDK surface evolves and this skill is the source of truth for the external package.
    29 repo stars
  4. ▌
    Bugs · kevin-liu-01
    CTF-style security and correctness audit. Dispatches parallel Opus subagents to hunt for day-0 bugs in security-critical files. Each agent must find a real bug or honestly admit failure. Use when you want a thorough adversarial review of a codebase area.
    29 repo stars
  5. ▌
    Lerp · kevin-liu-01
    Audit prose (comments, docs, READMEs, commit messages, PR descriptions) for jargon, unexplained acronyms, and assumed context. Rewrites for the least experienced reader. Use after writing docs, READMEs, or any prose that will be read by someone who did not write the code.
    29 repo stars
  6. ▌
    Perf · kevin-liu-01
    Discipline for performance investigations. Ramp up from cheap experiments to expensive ones. Profile before patching. Isolate hypotheses with standalone probes before touching production code. Numbers gate every decision. Use when the user says `/perf`, asks to speed up code, or asks why something is slow.
    29 repo stars
  7. ▌
    Rtfm · kevin-liu-01
    Verify claims against primary sources before writing code or docs. Read the actual API, run the actual command, check the actual docs. Do not guess. Do not assume. Do not ship until verified.
    29 repo stars
  8. ▌
    Issue · kevin-liu-01
    Create a GitHub issue using the Dedalus issue templates (bug, feature, question). Injects branch and commit context automatically, prompts for Linear link. Use when creating a GitHub issue using Dedalus templates, or the user says "file an issue", "create issue", "open a bug", or "report a feature request".
    29 repo stars
  9. ▌
    Voice · kevin-liu-01
    Write third-person, credential-forward bio copy in someone's own voice. Modeled on the "Why?" blurbs Sequoia / curated job platforms generate for founders + engineers. Use whenever the agent needs to describe a real person to a reader (recruiter "Why this candidate" blurbs, LinkedIn headlines + About sections, conference bios, intro requests, cold outreach openers, "tell me about yourself" answers, X/site bios, panel descriptions, app submission profiles, founder intros). Triggers on "write a bio", "intro me", "one-liner", "pitch me", "About section", "candidate blurb", "outreach opener", "describe me", or whenever copy is being authored that represents a person in their own voice.
    29 repo stars
  10. ▌
    Canvas · kevin-liu-01
    A Cursor Canvas is a live React app that the user can open beside the chat. You MUST use a canvas when the agent produces a standalone analytical artifact — quantitative analyses, billing investigations, security audits, architecture reviews, data-heavy content, timelines, charts, tables, interactive explorations, repeatable tools, or any response that benefits from visual layout. Especially prefer a canvas when presenting results from MCP tools (Datadog, Databricks, Linear, Sentry, Slack, etc.) where the data is the deliverable — render it in a rich canvas rather than dumping it into a markdown table or code block. If you catch yourself about to write a markdown table, stop and use a canvas instead. You MUST also read this skill whenever you create, edit, or debug any .canvas.tsx file.
    29 repo stars
  11. ▌
    Commit · kevin-liu-01
    Create a git commit with conventional commit format. Injects current git state automatically.
    29 repo stars