quick
Use when the user types /vibekit:quick: writes the change immediately under lazy's ladder, no spec, no plan, no subagents.
Skill by rizukirr
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/rizukirr-quick
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/quick
What's inside
- Skill name
quick- Description
- Use when the user types /vibekit:quick: writes the change immediately under lazy's ladder, no spec, no plan, no subagents. Reports what it skipped.
- License
- MIT
- Instructions
- 41 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# quick The fast path. One intent in, the change written now. ## The waiver `brainstorm`, `plan`, `exec` and `verify` do not apply here. No spec doc, no plan doc, no subagent dispatch, no verification report. That is the whole point of typing this instead of `/vibekit:vibe`. Invoke `lazy` and write under its ladder. Do not restate its rungs: one copy of the ladder exists, and it lives in `lazy`. ## Bail out first Check before writing. Each of these is a fact about the change, not a judgement about its size: - It needs a dependency that is not already installed. - It touches a schema, a migration, or the shape of stored data. - It touches auth, payments, permissions, or any other trust boundary. - It spans more files than you can hold in one reading. - The intent reads two ways. Any one of them: stop, name the criterion that tripped, and say the request wants `brainstorm`. Do not start a spec yourself, and do not negotiate: the user asked for speed, and the honest answer is that this is not the path for it. None of them: write the change now. ## The floor still holds Nothing runs behind you, so `lazy`'s never-simplify-away list is not optional here: validation at trust boundaries, error handling that prevents data loss, security, accessibility, and anything the user explicitly asked for. Non-trivial logic leaves one runnable check, and **you run it**. `verify` is not coming. A change you did not execute is a change you are guessing about, and "evidence or it did not happen" is not waived by speed. ## debug is not waived A failed check routes to `debug` exactly as it always does. `quick` skips the gates before implementation. It does not skip the one after a failure. ## Say what you skipped Close with one line naming the skipped stages and the check you ran, so a fast path never reads like a verified one: > Skipped: brainstorm, plan, exec, verify. Ran: <the check, and its result>.
From rizukirr/vibekit, MIT.
More from rizukirr/vibekit
- 0.644score
plan
rizukirr
Use when a spec is approved and implementation has not started: turns it into a task-by-task plan with exact paths and checkable verification.
SkillAFreshness: A★ 20Claude Code +9 - 0.644score
exec
rizukirr
Use when a plan is approved and implementation has not started: dispatches one fresh subagent per task, runs each task's verify clause, and routes failures…
SkillAFreshness: A★ 20Claude Code +9 - 0.644score
using-vibekit
rizukirr
Use when starting any conversation: establishes the auto-trigger discipline so guardrail skills fire instead of being silently skipped.
SkillAFreshness: A★ 20Claude Code +9 - 0.644score
debug
rizukirr
Use when a check fails: a red test, a broken build, a failed clause, or a bug you can point at.
SkillAFreshness: A★ 20Claude Code +9 - 0.644score
plain
rizukirr
Use before writing any text, in chat or into a file.
SkillAFreshness: A★ 20Claude Code +9 - 0.641score
brainstorm
rizukirr
Use before any creative or implementation work: features, components, behavior changes.
SkillAFreshness: A★ 20Claude Code +9 - 0.641score
lazy
rizukirr
Use at the start of any coding work: writing, adding, refactoring, fixing, designing.
SkillAFreshness: A★ 20Claude Code +9 - 0.641score
terse
rizukirr
Use at the start of every session.
SkillAFreshness: A★ 20Claude Code +9 - 0.641score
verify
rizukirr
Use before claiming a change is done, fixed or passing: checks the whole change against its spec, runs the checks no single task could, hunts for the bugs the…
SkillAFreshness: A★ 20Claude Code +9 - 0.633score
vibe
rizukirr
Run a short intent through the pipeline.
SkillAFreshness: A★ 20Claude Code +9
Signals
- Stars
- 20
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Aug 25, 2026 (2 months ago)
- Last release
- Oct 10, 2026 (19 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/rizukirr/vibekit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from rizukirr
- 0.644score
plan
rizukirr
Use when a spec is approved and implementation has not started: turns it into a task-by-task plan with exact paths and checkable verification.
SkillAFreshness: A★ 20Claude Code +9 - 0.644score
exec
rizukirr
Use when a plan is approved and implementation has not started: dispatches one fresh subagent per task, runs each task's verify clause, and routes failures…
SkillAFreshness: A★ 20Claude Code +9 - 0.644score
using-vibekit
rizukirr
Use when starting any conversation: establishes the auto-trigger discipline so guardrail skills fire instead of being silently skipped.
SkillAFreshness: A★ 20Claude Code +9 - 0.644score
debug
rizukirr
Use when a check fails: a red test, a broken build, a failed clause, or a bug you can point at.
SkillAFreshness: A★ 20Claude Code +9 - 0.644score
plain
rizukirr
Use before writing any text, in chat or into a file.
SkillAFreshness: A★ 20Claude Code +9 - 0.641score
brainstorm
rizukirr
Use before any creative or implementation work: features, components, behavior changes.
SkillAFreshness: A★ 20Claude Code +9
Cite this page
quick skill. Agent Mart. https://agentmart.dev/skills/rizukirr-quick (last updated 2026-10-24)