Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add CaesiumY/claude-interview-agents --skill portfolio-strategygit clone --depth 1 https://github.com/CaesiumY/claude-interview-agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/caesiumy/claude-interview-agents/portfolio-strategy)<a href="https://agentmods.dev/skills/caesiumy/claude-interview-agents/portfolio-strategy"><img src="https://agentmods.dev/badge/skills/caesiumy/claude-interview-agents/portfolio-strategy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/caesiumy/claude-interview-agents/portfolio-strategy"><img src="https://agentmods.dev/badge/skills/caesiumy/claude-interview-agents/portfolio-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.01322 |
| Opus 5 | $0.00029 | $0.00661 |
| Sonnet 5 | $0.00012 | $0.00264 |
| Haiku 4.5 | $0.00006 | $0.00132 |
Grade A, and why
portfolio-strategy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
포트폴리오 전략 스킬 (4-Phase 하니스)
핵심 관점
포트폴리오는 면접관에게 질문을 유도하는 트리거다.
- 블로그 글은 정보 전달이 목적이지만, 포트폴리오는 압축된 형식으로 면접관의 질문을 미리 유도한다
- "면접까지 간다면 이거 한 번 물어봐 주세요"라는 신호를 설계하는 작업이다
- 이력서 한 줄은 진짜 경험을 압축한 결과물이지, 그 자체가 경험은 아니다
- AI의 역할: 말투와 표현의 일관성 / 인간의 역할: 진정한 경험 디테일과 의사결정권
전체 파이프라인
┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ Curation │ → │ Interview │ → │ Drafting │ → │ Review │
│ AI 주도 │ │ 인간 주도 │ │ AI 주도 │ │ AI + 인간 │
└─────────────┘ └─────────────┘ └─────────────┘ └─────────────┘
후보 선별 디테일 채우기 마크다운 작성 다차원 평가
✋ GATE 1 ✋ GATE 2 ✋ GATE 3·4
| Phase | 주도 | 참조 파일 | 산출물 |
|---|---|---|---|
| 1. Curation | AI | jd-parsing.md |
portfolio/_curation/curation-[YYYY-MM-DD].md |
| 2. Interview | 인간 | interview-protocol.md |
portfolio/<slug>/interview-notes.md |
| 3. Drafting | AI (strategist) | templates.md |
portfolio/<slug>/draft-v{n}.md |
| 4. Review | AI (reviewer) + 인간 | review-rubric.md |
portfolio/<slug>/review-v{n}.md, final.md |
3대 설계 원칙
1. 작성자 ≠ 평가자
- Phase 3(portfolio-strategist)과 Phase 4(portfolio-reviewer)는 반드시 다른 서브에이전트로 실행
- 이유: 작성 단계의 컨텍스트가 평가를 좁히는 오염 방지 + AI도 자기 결과물에 관대해지는 경향 제거
- 참조 파일도 분리: strategist는
templates.md만, reviewer는review-rubric.md만 읽는다
2. 인터뷰 답변은 파일로 저장
- 답변은 메모리에만 두지 않고 즉시
interview-notes.md에 기록 - 이유: 사용자가 검토·편집할 승인 지점 확보 + 같은 프로젝트로 다른 JD에 재사용 가능한 영구 자산
- "한 번 답한 것은 다시 답할 필요가 없어야 한다" — 기존 노트가 있으면 부족분만 질문
3. AI 산출물은 사용자가 볼 수 있는 자리에 남긴다
- 인터뷰 노트 → 파일로 노출
- 평가 결과 → 파일 저장 + 사용자 게이트 화면에 노출
- 초안 → 검토 전 파일로 노출
사용자 게이트 (자동 진행 금지 지점)
| 게이트 | 시점 | 사용자 결정 |
|---|---|---|
| GATE 1 | Phase 1 완료 후 | 작성할 항목 N개 최종 선택 |
| GATE 2 | Phase 2 완료 후 | 인터뷰 노트 검토·편집 후 진행 승인 |
| GATE 3·4 | Phase 4 평가 후 | 평가 결과 확인 및 최종 저장(final.md) 승인 |
Phase 3 → Phase 4는 게이트 없이 자동 진행하며, 임계 미통과 시 최대 3회 자동 재작성 루프를 돕니다.
재사용 시나리오 (다른 회사 JD 적용)
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 78 lines · 58 tokens per session scan A 7f6395856315
portfolio-strategy is a skill published in the GitHub repository CaesiumY/claude-interview-agents (3 stars, last pushed 26d ago), licensed MIT. It adds 58 tokens to every session and 1,322 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
haiku
When writing a haiku for this bot, follow these conventions.
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.