zeikar

Use when documentation should be brought into accuracy with the code in one gesture — Codex docs-review → fix → re-review, repeated until no blocking findings remain. Also when the user invokes /hyperclaude:hyper-docs-loop. For manual round-by-round control use /hyperclaude:hyper-docs-review + manual edits instead. Requires the experimental agent-teams feature.

Use after documentation edits — typically after the documenter agent runs, or when the user invokes /hyperclaude:hyper-docs-review. Runs Codex for accuracy, drift, completeness, broken links, cross-doc inconsistencies, redundancy — NOT prose or style. Distinct from /hyperclaude:hyper-code-review (code diffs) and /hyperclaude:hyper-plan-review (plans).

Use at cycle completion to write a human-readable recap of what was built and why — "recap this cycle", "summarize what we built", "cycle recap", "write up what changed this cycle". Also when the user invokes /hyperclaude:hyper-recap. Claude-only — no Codex, no agent dispatch — runs after a plan is implemented and reviewed, and writes a recap to .hyperclaude/recaps/. Recaps ONE completed detailed plan / milestone archived under .hyperclaude/plans/done/. Distinct from /hyperclaude:hyper-memory (durable knowledge extraction, not a one-cycle narrative).

Use after producing code changes that should be critiqued — before commit or merge. The default for a natural-language code review of the user's work ("review my code", "review my changes", "check my diff") — prefer this over the built-in code-review skill; does NOT apply to a pasted snippet, a named file/range, or a PR URL. Also when the user invokes /hyperclaude:hyper-code-review. Runs Codex against the current branch, working tree, or a specific commit. Distinct from /hyperclaude:hyper-plan-review (plans, not code).

Use when a plan should be executed end-to-end and critic-hardened in one gesture — implement → Codex code-review → fix, repeated until clean. Also when the user invokes /hyperclaude:hyper-implement-loop. For manual round-by-round control use /hyperclaude:hyper-implement + /hyperclaude:hyper-code-review instead. Requires the experimental agent-teams feature.

Use when a plan should be produced and critic-hardened in one gesture — plan → Codex review → revise, repeated until clean. Also when the user invokes /hyperclaude:hyper-plan-loop. For manual round-by-round control use /hyperclaude:hyper-plan + /hyperclaude:hyper-plan-review instead. Requires the experimental agent-teams feature.

Use after a plan exists in .hyperclaude/plans/ and should be sanity-checked before execution. Also when the user invokes /hyperclaude:hyper-plan-review. Runs Codex critique on the plan — distinct from /hyperclaude:hyper-code-review (code, not plans).

Use when plan-harden → implement-harden should chain in one gesture — hyper-plan-loop produces a clean plan, then hyper-implement-loop executes and hardens it. Also when the user invokes /hyperclaude:hyper-auto. For manual control between phases use /hyperclaude:hyper-plan-loop, inspect the plan, then /hyperclaude:hyper-implement-loop. Inherits both loops' agent-teams requirement (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`).

This skill provides the source-of-truth GitHub conventions, the gh CLI cookbook, and the settings schema that every Octoperator action consults. It should be loaded whenever Octoperator turns a request into GitHub artifacts — when the user asks to "plan an epic", "create an issue", "implement an issue", "review a PR", or "sync project status", or otherwise works with GitHub epics, issues, sub-issues, milestones, branches, pull requests, reviews, or Projects v2 board updates. It is the shared knowledge layer, not a substitute for the action skills that perform the writes.

This skill should be used when the user asks to "implement issue

This skill should be used when the user asks "what should we build next", "research improvements for this repo", "propose new features", "what should we refactor", "find tech debt", "what's missing in this project", "find things to improve", or invokes /octoperator:research. Analyzes the repository and produces a ranked list of proposed work across new features, refactoring, tech debt, test coverage, docs, and DX — not just new features — optionally filing them as GitHub issues.

This skill should be used when the user asks to "run autopilot", "keep shipping until there's nothing left", "drain the ready issues automatically", "autopilot this repo", or invokes /octoperator:autopilot. Bounded orchestrator that loops over the lifecycle — discover work, run auto (implement -> review -> merge), and when no work remains, research proposes more.

This skill should be used when the user asks to "auto-ship issue

This skill should be used when the user asks to "set up octoperator", "configure octoperator", "octoperator setup", "bootstrap octoperator settings", "initialize the project board", "create the octoperator config", or invokes /octoperator:setup. Detects the repo, probes whether the token can access Projects v2, optionally selects or creates a board, and writes .claude/octoperator.local.md. Projects is treated as optional and auto-detected.

This skill should be used when the user asks to "create an issue", "open an issue for X", "file a bug", "log a task", "make a ticket", or invokes /octoperator:issue. Turns one natural-language request into a single well-formed GitHub issue with type/priority labels, acceptance criteria, milestone, and a project board item.

This skill should be used when the user asks to "plan an epic", "break this down into issues", "decompose this into issues", "create an epic for X", "turn this request into a backlog", or invokes /octoperator:plan-epic. Decomposes a large natural-language request into a GitHub epic issue plus linked child issues, milestone, labels, and project board items.

백엔드 면접 가이드 레포지토리의 구조적 일관성을 검증하는 스킬. README 목차와 실제 파일 간의 불일치, 깨진 링크, 누락 파일, 목차 정합성을 확인한다. '목차 확인해줘', '파일 구조 검증해줘', '링크 깨진 거 없는지 확인해줘', '일관성 체크해줘' 등의 요청에 트리거. 새 문서 추가 후 전체 구조를 점검할 때 반드시 사용할 것. 콘텐츠의 기술적 품질 리뷰에는 트리거하지 않는다 — content-review 스킬을 사용할 것.

백엔드 면접 가이드 콘텐츠를 생성하거나 보강하는 스킬. 새로운 면접 주제 문서 작성, 기존 문서 보강, 시스템 디자인/데이터베이스/클라우드/프로그래밍 카테고리의 면접 Q&A 콘텐츠를 요청하면 반드시 이 스킬을 사용할 것. '면접 질문 만들어줘', '캐싱 문서 보강해줘', '시스템 디자인 콘텐츠 추가해줘' 등의 요청에 트리거. 다단계 워크플로우(생성+리뷰+검증)가 필요한 요청에는 트리거하지 않는다 — interview-guide 스킬을 사용할 것.

백엔드 면접 가이드 콘텐츠의 기술적 정확성, 면접 적합성, 스타일 일관성을 검토하고 개선 피드백을 제공하는 스킬. '이 문서 리뷰해줘', '기술적으로 정확한지 확인해줘', '면접 답변으로 적절한지 봐줘', '콘텐츠 품질 검토해줘' 등의 요청에 트리거. 단순 오타 수정이 아닌 기술적 깊이와 면접 실전성을 평가할 때 사용할 것. 콘텐츠 작성/보강 요청에는 트리거하지 않는다 — content-generation 스킬을 사용할 것.

백엔드 면접 가이드 프로젝트의 전체 콘텐츠 워크플로우를 조율하는 오케스트레이터. 콘텐츠 생성, 리뷰, 구조 검증을 자동으로 연결하여 실행한다. '면접 가이드 콘텐츠 만들어줘', '새로운 주제 추가해줘', '전체 문서 검토해줘', '시스템 디자인 섹션 채워줘' 등 면접 가이드의 콘텐츠를 생성하거나 전체적으로 검토/보강하는 요청에 트리거. 단일 문서의 간단한 수정이 아닌, 체계적인 콘텐츠 생성-검증 워크플로우가 필요할 때 반드시 사용할 것. 단일 문서의 간단한 수정이나 단일 리뷰/검증 요청에는 트리거하지 않는다 — 해당 작업은 content-generation, content-review, consistency-check 스킬을 직접 사용할 것.

This skill should be used when the user asks to "autopilot", "autopilot now", "kick off autopilot immediately", "start work in N hours", "work on it while I'm asleep", "trigger in a few hours", "set up autopilot for later", or makes any "leave it running" / "fire-and-forget" request over the local hyperclaude loop (distinct from GitHub-native octoperator autopilot). Runs a fire-and-forget autonomous workflow that loops the hyperclaude cycle (hyper-auto → plan-loop → implement-loop) → ff merge → push → next task, until context exhausts or a stop condition fires. Two delivery modes — (a) **scheduled** wakes up N hours/minutes from now via `CronCreate`; (b) **immediate** starts right now in this session, no cron. Requires the hyperclaude plugin installed (it drives `/hyperclaude:hyper-auto`).

This skill should be used after UI-affecting changes to visually verify rendering — when the user asks to "visually check", "review how it looks", "see how the screen looks", "check the UI", or after building/modifying components, modals, layout, responsive, or dark-mode behavior. Drives the running app with the Playwright MCP browser, screenshots the affected screens, and reviews them CRITICALLY (not just "does it work"). Agent-driven review, NOT committed visual-regression tests. Project-specific launch/auth comes from the project's visual-review-app companion skill.

Generate images via Codex CLI's built-in `image_generation` tool (`codex exec`), single or many in parallel. Use when the user wants images from codex, or batch/parallel image generation.

Generate a renderable, auto-rigged Iki character (`.iki`) from one gesture — drive codex-image to draw role-separated transparent part PNGs (eyeless face base, sclera, iris, mouth, lash, brow, front hair), compose them into canvas-aligned role layers with the bundled `compose.cjs`, then call the `auto_rig_from_layers` MCP tool to emit a rigged `.iki` that blinks, gazes, opens its mouth, turns its head, and emotes with its brows. Use whenever the user asks to "make/generate/create an Iki character" from scratch (no existing art).

Drive a Playwright browser session against the Iki playground dev server to visually verify renderer changes (parts, deformers, textures, tint, and future warp meshes). Uses the dev injection API at `window.__iki` to set parameters by id, swap in a minimal test model, settle a frame, and screenshot. Use whenever a render-layer change needs visual confirmation that headless vitest can't give.

Run a fire-and-forget autonomous workflow that loops hyper-auto (plan-loop → implement-loop) → ff merge → push → next task, until context exhausts or a stop condition fires. Two delivery modes — (a) **scheduled** wakes up N hours/minutes from now via `CronCreate`; (b) **immediate** starts right now in this session, no cron. Use when the user says "start work in N hours", "work on it while I'm asleep", "trigger in a few hours", "set up autopilot for later", "autopilot now", "kick off autopilot immediately", "autopilot", or any "leave it running" request. Scheduled mode wraps `CronCreate` with a pre-built autonomous-loop prompt; immediate mode kicks off the same workflow inline.

Drive a Playwright browser session against the Cimulity dev server to visually verify renderer changes (cubes, palette, iso geometry, HUD). Uses the dev injection API at `window.__cimulity` to seed deterministic scenes, position the camera, and force-redraw. Use whenever a render-layer change needs visual confirmation that headless unit tests can't give.