policy-report-review

policy-report-review is a skill for Claude Code from parkjui92/policy-research-kit. It costs 161 tokens per session (1,771 once invoked), scanned A, original, MIT.

A Korean-language review process for policy research designs and report drafts, with separate checks before writing and after drafting.

In plain words
What is it for?
It helps review a research plan for scope and evidence, or inspect a draft for logical consistency, source support, policy feasibility, quantitative detail, and language quality.
Why use it?
It finds gaps in research questions, structure, evidence, reasoning, feasibility, and Korean writing before they undermine the report.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the policy-research-kit plugin — 6 skills, 5 agents shipped together

Good fit It helps review a research plan for scope and evidence, or inspect a draft for logical consistency, source support, policy feasibility, quantitative detail, and language quality.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/parkjui92/policy-research-kit/policy-report-review
Install

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.

Any agent
npx skills add parkjui92/policy-research-kit --skill policy-report-review
Clone the repo
git clone --depth 1 https://github.com/parkjui92/policy-research-kit

Made for: Claude Code.

Or install policy-research-kit, the plugin that ships this one along with the rest of its 6 skills, 5 agents.

Wrote 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.

agentmods badge for policy-report-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/parkjui92/policy-research-kit/policy-report-review/github.svg)](https://agentmods.dev/skills/parkjui92/policy-research-kit/policy-report-review)
Your own site
<a href="https://agentmods.dev/skills/parkjui92/policy-research-kit/policy-report-review"><img src="https://agentmods.dev/badge/skills/parkjui92/policy-research-kit/policy-report-review/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.

agentmods 80×15 button for policy-report-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/parkjui92/policy-research-kit/policy-report-review"><img src="https://agentmods.dev/badge/skills/parkjui92/policy-research-kit/policy-report-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 161 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,771 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00161 $0.01771
Opus 5 $0.00081 $0.00886
Sonnet 5 $0.00032 $0.00354
Haiku 4.5 $0.00016 $0.00177

Measured 11d ago against content hash caeb607055cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

policy-report-review 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 11d 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.

skills/policy-report-review/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

정책연구 검수 (2모드)

정책연구의 품질을 두 관문에서 지킨다. 막연한 평이 아니라 위치·문제·해결을 갖춘 실행 가능한 지적만 낸다. 가장 값싼 교정은 가장 이른 교정이므로, 설계 게이트(모드1)에 특히 철저하다.


모드 1 — 설계 검토 게이트 (집필 전)

입력: _workspace/01_research_design.md. 단 하나의 질문에 답한다: "이 설계대로 가면 RQ에 막힘없이 답하는 보고서가 나오는가?"

점검 체크리스트

  • RQ 적정성 — 연구 목적과 일치하는가? 답할 수 있는 구체적 질문인가(주제 나열이 아니라)?
  • 분석틀 적합성 — 선택한 틀이 RQ에 답하기에 맞는가? 근거가 있는가?
  • 목차 정합성 — 표준구조(현황→쟁점→대안→제언)를 충족하는가? 장 간 논리가 이어지는가? 빈틈·중복은 없는가?
  • 근거 확보 가능성 — 각 목차 항목에 붙은 [방법][필요근거]가 현실적으로 확보 가능한가? (확보 불가한 데이터에 의존하는 장은 위험)
  • 범위 적정성 — 과설계(답 못 할 질문·못 채울 장)나 누락(핵심 빠짐)이 없는가?
  • 숨은 가정 — 결론을 미리 정해둔 편향 설계는 아닌가?

출력 (_workspace/02_design_review.md)

  • 판정: 승인 / 조건부 승인(필수 수정 후 진행) / 반려(재설계 필요)
  • 항목별 지적: 위치(장·절) + 문제 + 권고 + 우선순위 [필수]/[권고]
  • 반려 시 재설계 방향을 구체적으로 제시

모드 2 — 초안 검수 (집필 후)

입력: _workspace/04_report_draft.md01(설계)·03(근거)과 교차 검증한다. 네 축으로 점검한다.

축 1 — 논리 정합성

  • 현황→쟁점→대안→제언이 논리적으로 이어지는가
  • 제언이 앞의 분석에서 도출되는가, 아니면 갑자기 튀어나오는가
  • 비약·모순·순환논증은 없는가
  • 설계(01)의 RQ에 실제로 답했는가

축 2 — 근거 충실성

  • 모든 사실 주장에 출처가 있는가
  • 출처가 주장을 실제로 뒷받침하는가(출처와 본문 진술 일치)
  • 03_evidence.md에 없는 수치를 지어내지 않았는가
  • [보강 필요]로 남아야 할 곳이 근거 없이 단정되지 않았는가
  • 과장·일반화("모두", "항상")가 근거를 넘어서지 않는가

축 3 — 정책 타당성

  • 정책대안이 실현 가능한가(법·예산·행정·시간)
  • 대안 비교가 객관적 기준으로 이뤄졌는가, 권고안에 근거가 있는가
  • 제언이 실행 수준인가(수단·주체·재원·일정), 당위 구호에 그치지 않는가
  • 예상 부작용·수용성·전제조건을 다뤘는가

축 4 — 정량성·표현

  • 수치가 맥락(기준연도·정의·비교군)과 함께 제시됐는가
  • "많다/심각하다"식 정성 표현을 정량으로 바꿀 여지
  • 한국어 문장·맞춤법·용어 일관성, 두괄식 여부
  • 표·그림이 효과적인 곳에 쓰였는가

축 5 — 참고문헌·출처 검증 + 분량

정책연구보고서의 신뢰는 출처에서 나온다. 말미 참고문헌과 본문 인용을 대조한다.

  • 본문 ↔ 참고문헌 1:1 대응 — 본문에 인용됐는데 목록에 없거나(누락), 목록에 있는데 본문에 안 쓰인(유령) 출처가 없는가.
  • 출처 실재·접근성 — 각 출처가 실재하고 접근 가능한가. 기관·문서명·연도가 구체적인가(모호·날조 의심 출처 플래그).
  • 인용-출처 일치 — 본문 수치·주장이 해당 출처의 실제 내용과 맞는가(03_evidence.md와 교차). 출처가 주장을 과대하게 떠받치지 않는가.
  • 서지 형식 일관성 — 형식이 통일됐는가, 신뢰도 낮은 출처가 1차 출처로 둔갑하지 않았는가.
  • 분량 — 본문이 목표 분량(기본 50p)을 충족하는가. 미달이면 어느 장을 어떻게 보강할지 권고.
  • 검증 불가·불일치 출처는 [필수] 또는 [권고]로 플래그하고, 1차 출처 교체나 [보강 필요] 처리를 권한다.

출력 (_workspace/05_draft_review.md)

각 지적은 다음을 갖춘다:

[필수] 5장 2절 — 권고안 도출 근거 부재
  문제: 대안 B를 권고하나, 비교표의 '비용' 기준에서 B가 가장 비싼데 이유 설명 없음.
  권고: 비용 외 기준(수용성·실현성)에서 B의 우위를 명시하거나, 비용 가중치 판단 근거를 추가.
  • 우선순위 [필수]/[권고]/[선택]로 구분 — 작성가가 한정된 수정 횟수를 잘 쓰게.
  • 종합 의견 + 승인 여부.

Read the full file on GitHub · 88 lines

Changes

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.

  1. 11d ago First seen · 88 lines · 161 tokens per session scan A caeb607055cb

Subscribe to this mod's changes

policy-report-review is a skill published in the GitHub repository parkjui92/policy-research-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 161 tokens to every session and 1,771 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

socsci-paper-orchestrator

An orchestrator for writing Korean social-science research papers with a team of six specialized agents. Social science studies people, organizations, and society; a research paper presents a question, evidence, methods, and conclusions.

parkjui92/socsci-paper-kit · 384 tokens

paper-design

A research-planning guide for starting a social-science paper or thesis. It turns a broad topic into research questions, hypotheses, theory, methods, and an outline.

parkjui92/socsci-paper-kit · 164 tokens

paper-research

An evidence-gathering guide for social-science research. It finds prior studies, academic theories, official statistics, and relevant cases, while recording sources for claims.

parkjui92/socsci-paper-kit · 139 tokens

scientometric-paper-review

A review skill for quantitative social-science papers, especially studies that count publications or estimate effects from panel or policy data. Bibliometrics measures patterns in published research, and a quasi-experiment estimates an effect without a fully controlled experiment.

parkjui92/socsci-paper-kit · 234 tokens

paper-writing

A writing workflow for producing a social-science research paper from an approved research design, cited prior studies, and analysis results.

parkjui92/socsci-paper-kit · 165 tokens

paper-analysis

A data-analysis skill for social-science research using numerical data, interview or text data, or both. It checks data quality before testing hypotheses and reports results with tables, figures, and limitations.

parkjui92/socsci-paper-kit · 154 tokens