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 kimsanguine/hplan --skill interview-synthesisgit clone --depth 1 https://github.com/kimsanguine/hplanWrote 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/kimsanguine/hplan/interview-synthesis)<a href="https://agentmods.dev/skills/kimsanguine/hplan/interview-synthesis"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/interview-synthesis.svg" alt="Measured on agentmods" 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 | $0.00093 | $0.01667 |
| Opus 5 | $0.00046 | $0.00834 |
| Sonnet 5 | $0.00019 | $0.00333 |
| Haiku 4.5 | $0.00009 | $0.00167 |
Grade A, and why
interview-synthesis 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 8d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Synthesis — AI Extracts, Human Tags
Running for: $ARGUMENTS
Core Goal
- 2026 현실 반영 — 78% PM 팀이 AI 합성 사용. 차단하지 말고 받아들이되, evidence strength 태깅은 인간에게 강제.
- AI는 quote 추출 + 테마 클러스터링; 인간은 strong/medium/weak + Push/Pull/Habit/Anxiety 축 부여.
- "5 interviews 중 3명이 같은 강한 Push를 말하면 Product Gate로" 규칙을 코드로 강제 (
PROCEED_TO_PRODUCT_GATEverdict).
Trigger Gate
Use This Skill When
- BuildBetter / Perspective / similar synthesis tools export JSON이 손에 있을 때
- 인터뷰 5건 이상 — 수동 정리는 비용 비효율적
evidence-rubric점수에서interview_notes보강이 필요할 때- 신규 PM이 인터뷰 evidence를 어떻게 태깅해야 하는지 학습할 때
Route to Other Skills When
- 5/3 패턴 통과 → Product Gate (
ostskill) - 5명 미만 → 추가 인터뷰 (skill 외 실세계 행동)
- 태그된 quote 강도가 너무 낮음 →
pivot또는hold결정 →decision-log
Boundary Checks
- ❌ AI 합성이 evidence를 대체할 수 없다. 태그 안 된 quote는 evidence가 아니다.
- ❌ AI sentiment ≠ evidence strength. 인간이 직접 판단.
Inputs
Expected AI export JSON shape:
{
"source": "buildbetter",
"interviews": [
{
"person": "ICP candidate 1",
"role": "HR 담당자 (선택 입력)",
"company_size": "50-200명 (선택 입력)",
"date": "2026-05-09",
"quotes": [
{"text": "지난주에 30분 또 날렸어요", "theme": "manual workaround"},
{"text": "이거 안 되면 영업 못 따요", "theme": "economic pain"}
]
}
]
}
role필드 처리 정책:role이 AI export JSON에 있으면 PERSONA_SPECS.json에 그대로 기입 (결정론). 없으면null로 저장 — 이 경우 LLM이 ICP 컨텍스트 기반으로 추론하지 않으며, 수동으로 채워야 합니다.role은 PERSONA_SPECS 생성 규칙의 "LLM 추론 금지" 원칙의 예외가 아닌, 입력 데이터 부재 시 명시적null처리로 대응합니다.
Steps
실행은 python3 hplan/scripts/interview_synthesis.py <subcommand> 형태로 호출합니다.
python3 hplan/scripts/interview_synthesis.py import <ai_export.json>— quotes를harness/evidence/snapshots.jsonl에 ingest (status: awaiting_human_tag).python3 hplan/scripts/interview_synthesis.py list --untagged— 미태깅 quote 확인.- quote마다
python3 hplan/scripts/interview_synthesis.py tag <quote_id> --strength strong --axes push,anxiety— 인간 입력. python3 hplan/scripts/interview_synthesis.py audit— 5/3 규칙 통과 여부 + 다음 액션 가이드.audit결과가PROCEED_TO_PRODUCT_GATE이면 PERSONA_SPECS.json 저장 — 태깅된 인터뷰이를 QA 라운드용 페르소나로 구조화해harness/PERSONA_SPECS.json에 기록.
What ships with it
4 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.
- 8d ago First seen · 115 lines · 93 tokens per session scan A 4a23cb9c80e3
interview-synthesis is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 22d ago), licensed MIT. It adds 93 tokens to every session and 1,667 once invoked, about $0.0005 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
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…
recap-doc
Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…
runbook
Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.