quirk

Plugin quirk from marketplace quirk-dev in zpyoung/quirk. Commands read from the repo's manifest — 7 days ago.

Skills (31)

• adhd

  Divergent-ideation subroutine for surfacing N non-obvious viable options when facing decision points. Explicitly invoked via /adhd or delegated from brainstorming's gray-area resolution. Uses parallel agent dispatch (Diverge + Deepen) + inline Score/Cluster to generate structured option lists with c

• adversarial-review

  Use when a work product needs adversarial review - attacking a diff, spec, plan, or written claim to find what is wrong with it. Triggers on "adversarial review", "critique this", "red team it", "attack this", "find flaws", "tear this apart", "poke holes in", or when another skill composes a review

• brainstorming

  You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

• building-mini-apps

  Use when the user asks to "build me a mini app", "a little app to track…", "a local tool with saved data", or to "analyze <app> as a mini app" - a small React app they will keep and run on their own machine, built from proven interaction patterns (list-peek, action-palette, view-switcher and others)

• dispatching-parallel-agents

  Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

• executing-plans

  Use to implement a multi-step task sequentially in one session when subagents aren't available — plans in context, then executes

• exploring-ideas

  Use when the user wants to deeply research a topic OR brainstorm/explore ideas WITHOUT building anything yet — produces a cited briefing or idea-landscape (an exploration doc), never a spec, plan, or implementation. Triggers on "do deep research on X", "research X", "let's brainstorm ideas around X"

• filing-requests

  Use when the user wants to file, report, or write up a bug, a feature request, or a code-change request — triggers on "file a bug", "report an issue", "write up a bug report", "open an issue", "file a feature request", "raise a ticket". Runs a guided evidence-gathering session, resolves what it can

• finishing-a-development-branch

  Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

• full-code-review

  Use when asked for a full, multi-lens code review of a GitHub pull request, a GitLab merge request, a branch, or local changes ("full review", "full code review", "review this PR", "review this MR"). Runs up to 14 specialist lenses in parallel (correctness, safety, risk, claim verification, scope, d

• interface-design

  Use when the user wants product UI built, reviewed or refined in their own codebase so it looks decided rather than defaulted - dashboards, admin panels, tools, settings pages, data views, docs and other reading surfaces, and native iOS or Android screens. Covers the verbs build, review, audit, crit

• making-videos

  Use when the user asks for a video, explainer, motion graphics, an animated announcement or demo, a narrated or voiceover piece, or a rendered MP4, usually about software and up to 3 minutes. Builds it locally from a brief with HyperFrames, optional Kokoro narration and optional headless Blender, ch

• pi-dev

  Use when dispatching the pi coding agent for a sub-task — code review, analysis, edits, or multi-agent orchestration. Triggers on "use pi", "run pi", or "pi <model>" (codex, terra, opus, sonnet, gemini, haiku, grok).

• receiving-code-review

  Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

• releasing-quirk

  Use when releasing the quirk plugin - commits any pending changes, stamps a calendar-based (CalVer) version from today's date, writes the changelog, and pushes to origin autonomously. Triggers on "release quirk", "ship quirk", "bump and push quirk", or "cut a quirk release".

• requesting-code-review

  Use when completing tasks, implementing major features, or before merging to verify work meets requirements

• simplifying-safely

  Use when asked to simplify, clean up, or refactor code; when asked to review a diff, PR, or draft for over-engineered additions; or when authoring or editing a spec, a CLAUDE.md, a skill file, or other agent-facing document. Notices when an agent is over-producing. Where a correctness check exists —

• stacking-prs

  Use when splitting a large branch into a stack of smaller PRs/MRs, when managing or updating an existing stack (review feedback on a lower PR, trunk moved, a broken chain), or when landing or merging a stack and syncing the rest after the bottom merges. Also use when a reviewer asks to "make this PR

• subagent-driven-development

  Use when executing implementation plans with independent tasks in the current session

• systematic-debugging

  Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

• test-driven-development

  Use when implementing any feature or bugfix, before writing implementation code

• typed-artifacts

  Use when about to write hedging language like "pre-existing", "out of scope", "future work", "skipped for brevity", or "architectural concern" — instead, route the observation to a typed artifact (BUGS.md, DEFERRED.md, TEST_BACKLOG.md, proposals.md) or an ADR. Also use when the user invokes /quirk:a

• using-apps-like-a-user

  Use when asked to dogfood an app, use it like a user, or "try it in the app" - operating a web app, an Electron app, or a native macOS app through its UI by looking at the screen, acting only on what is visible, and proving each action changed something. Triggers on "dogfood", "like a user", "try it

• using-git-worktrees

  Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

• using-quirk

  Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

• verification-before-completion

  Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

• writing-html-artifacts

  Use when the user asks for HTML, a web page, an interactive tool, a dashboard or report as a page, or an offline single-file artifact, or when an answer would read better as a page and you want to offer one. Builds a styled self-contained page from a template, checks it, and hands it over with a del

• writing-plans

  The planning rubric the execution skills run in-context at the start of a run — turns the tech spec (tech.md) when present, else the logic spec / requirements, into a task breakdown (contracts, acceptance, parallelism) before code

• writing-scannable-prose

  Use when writing or revising a human-facing technical document — README, guide, ADR, PR description, changelog — or when asked to tighten, shorten, or declutter one ("tighten this", "too long", "hard to scan", "make this scannable"). Separates what the reader's decision depends on from detail they d

• writing-skills

  Use when creating, editing, or testing a Claude Code skill — writing SKILL.md and its frontmatter/description, choosing skill vs command vs subagent vs CLAUDE.md, fixing a skill that won't trigger, or deciding how strictly to test one. Covers activation (getting a skill to fire) and execution (getti

• writing-specs

  The two-document spec rubric — what a good logic spec (logic.md) and tech spec (tech.md) contain, and which stage owns which. Brainstorming runs the logic-spec half after design approval; the execution skills run the tech-spec half in-context when the complexity gate fires, before planning.

Slash commands (9)

• /quirk:adversarial-review

  Adversarially review a diff, spec, plan, or written claim. Runs a deterministic pre-pass, a promote/refute two-stage with a cross-family reviewer, and an evidence gate, then reports a verdict with findings.

• /quirk:artifacts:adr

  Create a new Architecture Decision Record (ADR) in docs/adr/. Use to record a significant architectural decision.

• /quirk:artifacts:bug

  Append a BUG-N entry to BUGS.md. Use when you've noticed a bug you cannot fix in the current scope.

• /quirk:artifacts:defer

  Append a DEFER-N entry to DEFERRED.md for tasks that are out of scope for the current session.

• /quirk:artifacts:init

  Scaffold typed-artifact files (BUGS, DEFERRED, TEST_BACKLOG, proposals, docs/adr/) into this project.

• /quirk:artifacts:review-artifacts

  Read-only summary of all typed-artifact entries (bugs, deferred work, test backlog, proposals, ADRs).

• /quirk:artifacts:test-skip

  Append a TEST-N entry to TEST_BACKLOG.md for skipped or abbreviated tests.

• /quirk:artifacts:triage

  Classify an observation into bug / defer / test-skip / proposal and append a structured entry. Use when the routing destination isn't obvious.

• /quirk:explore

  Deep research or brainstorm a topic WITHOUT producing a spec — yields a cited briefing / idea-landscape. Optional intensity via --wild 0.1–1.0 and involvement via --involve low|medium|high.

Hooks (4)

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/hooks/load_artifact_tail.sh

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/lint_tics.sh

• Stop

  ${CLAUDE_PLUGIN_ROOT}/hooks/wrap_session.sh

Similar plugins