zpyoung

@zpyoung source repo

27 skills
0 followers
6 hours ago last updated

▌
Release · zpyoung
Use when cutting a release of the zpyoung/orca fork, or when asked to update CHANGELOG.md with fork-owned changes. Records commits this fork owns (not upstream's), computes a fork version anchored to the upstream point main is built on, and dispatches release-cut.yml. Triggers on "cut a release", "release the fork", "update the changelog", "ship a build".

0
installs
▌
Sync Upstream · zpyoung bundle
Use when syncing the zpyoung/orca fork to upstream's latest stable release, or when a sync has failed and needs diagnosing — merges an upstream stable tag on a run branch, resolves file ownership from the manifest, verifies, opens a PR, drives it green, merges it, and hands off to the release skill. Triggers on "sync upstream", "sync the fork", "merge the stable tag", "sync failed", "typecheck fails after the merge".

0
installs
▌
Agent Isles Render · zpyoung
Render or watch Agent Isles Markdown from Claude Code and verify the generated HTML artifact.

0
installs
▌
Agent Isles Install Update · zpyoung
Install or update Agent Isles in the current Claude Code project with deterministic package-manager detection and a render smoke check.

0
installs
▌
Agent Isles Component Authoring · zpyoung
Author Agent Isles Markdown with supported <agent-*> islands, readable source, and explicit security boundaries.

0
installs
▌
Agent Isles Component Pack Authoring · zpyoung
Create trusted local Agent Isles Component Packs V1 with manifests, custom-element assets, diagnostics, and render smoke verification.

0
installs
▌
Adhd · zpyoung bundle
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 critiques.

0
installs
▌
Pi Dev · zpyoung bundle
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).

0
installs
▌
Using Quirk · zpyoung bundle
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

0
installs
▌
Split Branch · zpyoung bundle
Use when a feature branch exceeds ~400 lines of diff, when a reviewer asks to "make this PR smaller", when planning a large feature so it ships in reviewable chunks, or when the user invokes /split-branch

0
installs
▌
Brainstorming · zpyoung bundle
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.

0
installs
▌
Writing Plans · zpyoung bundle
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

0
installs
▌
Writing Specs · zpyoung bundle
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.

0
installs
▌
Writing Skills · zpyoung bundle
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 (getting it right once loaded).

0
installs
▌
Executing Plans · zpyoung
Use to implement a multi-step task sequentially in one session when subagents aren't available — plans in context, then executes

0
installs
▌
Exploring Ideas · zpyoung bundle
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", "explore X", "what are some ideas for X". NOT for "build/implement/add/fix X" — that is the brainstorming skill. Set wildness with `--wild 0.1–1.0`.

0
installs
▌
Filing Requests · zpyoung bundle
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 by reading the repo, and emits a terse provenance-marked markdown artifact plus, on explicit confirmation, a GitHub issue. NOT for "build/implement/add X" — that is brainstorming.

0
installs
▌
Releasing Quirk · zpyoung
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".

0
installs
▌
Typed Artifacts · zpyoung
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:artifacts:* commands or asks how to log a bug, defer a task, or record a decision.

0
installs
▌
Adversarial Review · zpyoung bundle
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 step. Runs a deterministic pre-pass, a two-stage promote/refute protocol with a cross-family reviewer, and an evidence gate that drops findings whose evidence cannot be re-resolved.

0
installs
▌
Using Git Worktrees · zpyoung
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

0
installs
▌
Systematic Debugging · zpyoung bundle
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

0
installs
▌
Requesting Code Review · zpyoung bundle
Use when completing tasks, implementing major features, or before merging to verify work meets requirements

0
installs
▌
Writing Scannable Prose · zpyoung bundle
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 do not want, cutting whole sections that earn no keep; then treats every remaining cut as a dependency problem, so compression removes real bulk without orphaning the claims it leaves behind.

0
installs
▌
Dispatching Parallel Agents · zpyoung
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

0
installs
▌
Subagent Driven Development · zpyoung bundle
Use when executing implementation plans with independent tasks in the current session

0
installs
▌
Finishing A Development Branch · zpyoung
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

0
installs

27 published skills