uzysjung

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

deep-research

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.

eval-harness

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

strategic-compact

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

verification-loop

A comprehensive verification system for Claude Code sessions. Every run ends with a fixed verdict — PASS / PASS_WITH_NITS / FAIL — plus severity-labeled findings (CRITICAL/HIGH/MEDIUM/LOW).

Testing & QA Listed

e2e-testing

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

investor-materials

Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.

investor-outreach

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

python-patterns

Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.

Testing & QA Listed

python-testing

Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.

market-research

Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.

Web & Frontend Listed

nextjs-turbopack

Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.

asis-tobe-decision

Present a decision or confirmation request in the user's four-part format: 전후맥락 (context) → 추천 + 이유 (recommendation) → UI/UX 형태 (a scannable table/option-list) → ASIS→TOBE contrast, led by the recommendation so the user can say yes fast. Fire at genuine A-or-B / approval / explicit-ASIS-TOBE moments. Triggers on the user's verbatim phrases "ASIS TOBE로 설명", "ASIS-TOBE로 알려줘", "화면으로 ASIS TOBE로 설명", "의사결정 / 컨펌 요청", "이거 진행할까요?", and the softer "다음 진행할 것들 알려줘"; English equivalents: "present this as ASIS/TOBE", "give me the as-is to-be", "should I do A or B", "ask for my approval", "lay out the options". Do NOT fire for pure information with no decision, or trivial reversible actions you would just do.

compaction-handoff

Create a compact, reconstructible checkpoint immediately before context compaction. Persist only durable facts and decisions, overwrite one current resume anchor, verify Git and open-PR state, and emit one concrete next action plus a short /compact line. Use for "컴팩션 준비해줘", "컴팩션하고 이어서 진행할 수 있게 준비해줘", "핸드오프 준비해줘", or "prepare for compaction", or equivalent. Repeated execution must be idempotent and must not grow state files without bound.

gap-analysis-e2e

Two-mode chained gap analysis. DETECT scans the current service end-to-end through three lenses — north-star alignment, correctness (bugs), and user-perspective (UX) — and enumerates concrete, severity-ranked gaps. Then BENCHMARK researches how reference/benchmark services actually solved each high-ranked gap and PROPOSES a closing approach. Use when the user says any of: "북극성 기준으로 부족한 점", "사용자 관점에서 부족한 점", "다른 벤치마크 서비스는 이 부분을 어떻게 해결했는지", "갭분석", "레퍼런스 서비스랑 비교해서 부족한 점 찾아줘" — or the English equivalents: "gap analysis", "what are we missing vs the ideal/north-star", "benchmark against reference services". Fires for both Korean and English phrasing. NOT for a whole-codebase multi-dimension audit (use ultracode-service-audit) or single-artifact prose review (use multi-persona-review) — this is the narrower gap-vs-benchmark loop.

harness-health-audit

Audit the health of an AI-coding harness — the CLAUDE.md / AGENTS.md files, rules, skills, agents, hooks, and commands that steer an agent in a repository — across four questions a linter cannot answer: is it TRUE (does it match the real code?), is it USED (do skills actually trigger and does the loop actually verify?), is it AFFORDABLE (is it inside the budget where instructions are still followed?), and is it SAFE (is a live, accurate instruction still a good idea — permission bypasses, unpinned remote scripts, untrusted content flowing in as instructions? — safety findings are flagged for the user's decision, never auto-removed). Then surgically correct or remove only what is proven wrong or dead. Use whenever the steering layer may have rotted or may not be working: "하네스 점검해줘", "하네스 드리프트 감사", "CLAUDE.md가 실제랑 맞는지 봐줘", "룰/스킬이 최신인지 확인해줘", "스킬이 제대로 활용되는지 봐줘", "루프 엔지니어링 잘 되고 있는지 검토해줘", "죽은 훅/커맨드 정리해줘", "하네스 안전한지 점검해줘", "audit my harness", "check the rules still match the real stack", "are my skills actually be

model-orchestration

Apply the fixed model-role and thinking-effort policy whenever work is delegated to subagents or a model/effort choice is made: the orchestrator (top-tier model) DIRECTLY sets service direction, reviews plan/spec documents (with multi-persona-review), improves shipped features, and hunts performance/security problems; plan/spec/planning documents are AUTHORED by Opus, which also owns core implementation and V&V, at xhigh or above; repetitive implementation and E2E tests go to Sonnet at high or above — never delegate below those effort floors. Use whenever you are about to spawn an Agent/Task/Workflow worker, pick a model for a subtask, set a thinking/effort level, assign verification, or hand off orchestration because the current model's quota is exhausted. Trigger on "위임해", "에이전트로 돌려", "오케스트레이션", "모델 역할분담", "어떤 모델로", "effort 얼마로", "thinking level", "서브에이전트", or in English "delegate this", "spawn an agent for", "which model should", "route this task", "verify with", "orchestrate". Fire even when the user does

multi-persona-review

A panel-review skill that critiques ONE artifact (launch post, README, doc, markdown, plan, design) via 3-5 disjoint user-perspective personas running in parallel, then synthesizes deduped, severity-ranked improvement points (P0/P1/P2). Use when the user says "작성글을 사용자 관점의 페르소나를 여러명 만들어서 (손넷 모델정도로) 피드백 받아바", "다면 리뷰 해볼까", "페르소나로 리뷰", "여러 관점으로 피드백", or in English "multi-persona review", "review this from different user perspectives", "get persona feedback on this post/README/doc", "panel review this artifact". Lighter than a full service audit — point it at ONE artifact, not a whole codebase. NOT for a whole-codebase multi-dimension audit (use ultracode-service-audit) or a single-axis gap-vs-benchmark loop (use gap-analysis-e2e).

north-star

Defines and enforces a project's long-term direction (North Star Statement, metric-as-proxy NSM, strategic Pillars with a module↔pillar map, Will/Won't, 4-gate + priority-order decision heuristics). Use when starting a new project, when scope creep is suspected, or when a non-obvious feature request needs prioritization. Sits one layer above SPEC/PRD — answers 'why and where to', not 'what and how'.

northstar-roadmap

Read the project's NORTH_STAR / vision doc, measure current state against the goal, then propose a forward direction plus prioritized feature proposals — persisted as a durable roadmap in docs/plans + memory so the plan survives /compact and new sessions. Use when the user asks where the project should go next or wants a backlog grounded in the vision. Fires on the user's real phrasings: "앞으로 어떤 방향으로 개선·발전시킬지 고민해봐", "NORTH.md / NORTH_STAR 보고 나아갈 방향 + 기능 제안", "나아갈 방향 + 기능제안 (수용 → 계획 수립하고 메모리에 기록)", "북극성 정렬 로드맵", as well as the English equivalents: "what direction should we take next", "propose a roadmap / feature backlog from the north star", "plan the next milestones and save it to memory". Not for detecting bugs or auditing current quality (see gap-analysis-e2e / ultracode-service-audit) — this skill DIRECTS forward planning.

recurrence-prevention

When the same defect, mistake, or incident happens AGAIN — a recurrence, not a one-off — verify it against prior evidence (memory, rule case tables, git/CHANGELOG history), classify it as a simple slip vs a complex harness problem, then escalate the countermeasure one level up the ladder: record (1st) → forced rule with a case table (2nd) → structural gate — test, hook, or derive — once prose has failed (3rd+). Complex problems get countermeasure candidates designed by a multi-persona panel instead of a quick patch. Use for "재발했어", "같은 실수 또 했네", "이거 저번에도 그랬잖아", "재발방지 대책 등록해줘", "재발방지 룰 만들어", "this happened again", "same bug as last time", "add a recurrence countermeasure", "postmortem this failure". NOT for a first-time defect (fix it, record it, stop) and NOT a general steering-layer audit (that's harness-health-audit).

ultracode-service-audit

Run a multi-agent, adversarially-verified full-service audit across 7 dimensions (code / UX / scalability / planning+north-star / security / promotion / extensible), separating findings into confirmed / unverified / rejected and producing a priority-ranked, M-numbered milestone roadmap (as many milestones as the findings warrant). Use when the user says "ultracode 전체 서비스 점검", "전체 서비스를 점검하자", "코드·UX·확장성·기획·북극성지표·보안·홍보 문제점을 파악하고 우선순위에 따라 개선", "다차원 서비스 감사", or in English "audit the whole service / full multi-dimensional service audit / find code, UX, scalability, planning, security, and marketing problems and prioritize fixes". The heavyweight superset audit — orchestrate it as a Workflow with fan-out finders and an adversarial verify pass. NOT for a single-artifact prose/README review (use multi-persona-review) or a single-axis gap-vs-benchmark loop (use gap-analysis-e2e) — those are the lighter siblings.

codex-consult

Consult OpenAI Codex (via the local `codex` CLI, non-interactive `codex exec`) for the two things it is comparatively strong at: (1) CONCISE, well-STRUCTURED writing — tightening verbose prose, restructuring a doc into a clean outline / tables / sections, executive summaries, README skeletons, changelog entries — and (2) IMAGE GENERATION — hero/placeholder art, logos, simple illustrative art, produced as real PNG files on disk (labeled flowcharts / architecture / sequence diagrams are NOT this — render those natively as Mermaid). Use whenever a document needs to get SHORTER and better ORGANIZED (not prettier-sounding), or whenever the user wants a generated image. Triggers: "codex한테 물어봐 / codex로 정리해 / 간결하게 정리해줘 / 구조화해줘 / 문서 구조 잡아줘 / 이미지 만들어줘 / 그림 생성해줘", or in English "ask codex", "tighten this up", "make this concise", "restructure this doc", "generate an image". Korean NUANCE/copy polish belongs to the sibling skill gemini-consult — this skill owns structure, concision, and images. Returns candidates/files f

explain-plainly

Explain a technical finding to someone who has not read the code: fix the referent first (one name often points at two things), lead with who is affected and what changes, then show evidence. Run it whenever you explain a bug, a cause, or what your change did — especially the moment the reader says they don't follow ("뭔 소리야", "쉽게 설명해줘", "이해가 안 돼", "I don't follow", "in plain terms"), or when your draft opens with a file path or symbol name.

gemini-consult

Consult Google Gemini (via the local Antigravity `agy` CLI, Pro tier) for three things: (1) natural, native-sounding KOREAN phrasing — copy, UI microcopy, marketing/brochure text, toasts, user-facing messages, translations, rewrites — (2) a MULTI-PERSONA / second-opinion review of a design, plan, spec, PR, or piece of writing, and (3) IMAGE GENERATION via Gemini's image tool (real PNG/JPG files, collected from agy's artifact store). Use this whenever Korean text needs to read naturally (not translated/stiff), whenever the user says the Korean "sounds awkward / 어색해 / 자연스럽게 다듬어줘", whenever you are about to hand-write polished Korean copy yourself, whenever you want an independent NON-Claude model's critique, or when the user asks for a Gemini/Nano-Banana-style generated image. Claude's Korean often reads machine-translated — delegating Korean polish here is this skill's premise (the installing user's standing preference, not a benchmark). Returns candidates/files for the user to choose from. Also triggers on "g

gh-issue-workflow

Treats GitHub Issues as the async backlog + decision channel between user and AI agent. Use when a non-blocking todo / bug / decision needs to persist beyond the chat session. Enforces 5-section body template (Background / Given / Decision / AC / Next) so issues become reusable agent context, not just sticky notes.

ui-visual-review

Captures screenshots of key UI flows after E2E tests pass, runs an agent-side first-pass diff (regressions, console errors, layout shifts), then surfaces a checklist for the user's final approval. Also owns the browser-launch procedure the `playwright-launch` rule delegates here: use it whenever a browser must be opened for a human to drive or for automated capture — manual E2E checks, UX/fidelity comparison against a reference product, or a one-time OAuth login. Use after E2E tests pass on a UI track (csr-*, ssr-*, full).

spec-scaling

Detects when SPEC.md or PRD.md exceeds 300 lines and proposes feature-based splitting with a master route document. Use when SPEC.md grows too large to be effectively used as a single document.