policy-brief
Writes a concise, evidence-based policy brief - problem, options compared on consistent criteria, and a recommendation - that a decision-maker can act on in minutes. Use when someone asks "write a policy brief", "summarize the evidence and options for this decision", "brief the minister/board/council on X", or needs a one-to-four-page document that turns research into a recommended action. Do NOT use for persuasive opinion pieces - use op-ed-writer instead; for long-form marketing documents, use whitepapers; for condensing an existing long document, use executive-summary.
- License 许可
- MIT
- 最近更新
- 2026-10-05
- Stars
- ★ 3
- Forks
- 0
01 前言 Front Matter
- name
- policy-brief
- metadata
- { "title": "Policy Brief" }
- description
- Writes a concise, evidence-based policy brief - problem, options compared on consistent criteria, and a recommendation - that a decision-maker can act on in minutes. Use when someone asks "write a policy brief", "summarize the evidence and options for this decision", "brief the minister/board/council on X", or needs a one-to-four-page document that turns research into a recommended action. Do NOT use for persuasive opinion pieces - use op-ed-writer instead; for long-form marketing documents, use whitepapers; for condensing an existing long document, use executive-summary.
03 SKILL.md 正文
Policy Brief
A brief exists to inform one specific choice by one specific decision-maker - not to survey a literature. The costly failure is the brief that is read only as far as its summary and gives the reader nothing actionable there, or that strawmans the rejected options and loses credibility the moment a stakeholder notices. Write so that a busy reader who stops after the first half-page still knows the problem, the recommendation, and why.
Inputs to collect
- Who decides, and what decision they face - the single question the brief must answer. If the user cannot name the decision, help them narrow it before writing; "inform them about X" is not a decision.
- The decision deadline and any political, budget, or legal constraints that rule options in or out.
- The evidence available: studies, data, prior evaluations. Note what is missing; gaps shape how strongly the brief can recommend.
- The audience's technical depth. Default: intelligent non-specialist - define every acronym on first use.
- Length target. Default: one to four pages. Longer than four pages is a report, not a brief.
Label anything assumed rather than supplied.
Operating procedure
Order matters: options cannot be compared until criteria are fixed, and the executive summary is written last even though it appears first.
- Fix the decision and criteria. State the choice in one sentence. Choose 3-5 comparison criteria - effectiveness, cost, equity, feasibility, time-to-impact are the standard set - and hold them constant across every option.
- Draft the problem statement. What is wrong, who is affected, why now, and the cost of inaction. Quantify wherever possible; a problem without a number invites indefinite delay.
- Compress the background. Only what is needed to understand the problem - typically one to two paragraphs.
- Assemble the evidence. Cite credible primary sources; note the strength and limitation of each. Distinguish strong causal evidence (randomized or well-identified quasi-experimental) from correlation and from expert opinion, and say which is which. Present evidence on all sides, including findings inconvenient to the eventual recommendation.
- Build 2-4 realistic options, always including the status quo. For each: how it works, expected impact, cost, feasibility, key trade-offs - scored against the fixed criteria in a comparison table. Do not strawman the options you reject; state each option's best case fairly.
- Recommend and condition. Name the preferred option, the reasoning against the criteria, the assumptions it rests on, and the conditions under which the recommendation would change.
- Sketch implementation. Concrete first steps, owners, and timeline - a recommendation without a first step is a suggestion.
- Write the executive summary last. Problem plus recommendation in 3-4 sentences that stand alone. Many readers read nothing else.
Options table template
Criteria (weight) | Option A: [FILL] | Option B: [FILL] | Status quo
Effectiveness | [FILL] | [FILL] | [FILL]
Cost (annual) | $[FILL] | $[FILL] | $[FILL]
Equity impact | [FILL] | [FILL] | [FILL]
Feasibility | High/Med/Low | High/Med/Low | High/Med/Low
Time to impact | [FILL] months | [FILL] months | n/a
Key trade-off | [FILL] | [FILL] | cost of inaction: [FILL]
Bad summary: "This brief examines several approaches to school absenteeism and discusses their relative merits." Good summary: "Chronic absenteeism has doubled to 28% of students since the baseline year. Of three options assessed, targeted mentoring is recommended: evaluations show a 4-6 percentage-point reduction at roughly $1,500 per student, versus weak evidence for automated messaging alone. Begin with a two-school pilot next term."
Deliverable
Produce a one-to-four-page brief containing: title and standalone executive summary; quantified problem statement; minimal background; evidence section with sources graded by strength; 2-4 options scored in a consistent comparison table; a conditioned recommendation; and implementation first steps with owners and timeline.
Do NOT
- Do not bury the recommendation at the end. Lead with the bottom line (BLUF); the structure of a brief is conclusion-first, evidence-after.
- Do not present only supporting evidence. Omitting the strongest counter-evidence is the fastest way to lose a skeptical reader - and decision-makers employ skeptical staff.
- Do not mix evidence with values silently. Separate what is (evidence) from what should be (normative choices) and label the normative ones.
- Do not compare options on shifting criteria - praising one option's cost and another's speed hides the real trade-off.
- Do not exceed four pages or leave jargon and acronyms unexplained.
Quality bar
Before shipping: the executive summary stands alone and states the recommendation; every factual claim has a findable citation; evidence strength is graded, not asserted; all options - including status quo - are scored on identical criteria; assumptions and change-conditions are explicit; a reader can identify the first implementation step and its owner.
Escalation
A brief informs a decision; it is not legal advice, and options touching statute, regulation, or liability need counsel review before adoption. For verifying a load-bearing statistic before it anchors the problem statement, use fact-checker. For deep sourcing on an unfamiliar topic before drafting, run deep-research first.
04 同仓库更多 Skills
systematic-review
Runs a PRISMA-compliant systematic review from PICO question and pre-registered protocol through search strings, two-stage screening, risk-of-bias appraisal, and GRADE-rated synthesis. Use when someone asks "run a systematic review", "build my search strategy and inclusion criteria", "screen these studies against a protocol", or "meta-analyze the evidence on X". Do NOT use for a thematic narrative review of a field without a registered protocol and exhaustive search - use literature-review instead. Do NOT use for synthesizing mixed non-study sources into decision themes - use research-synthesis instead.
literature-review
Produces a thematic literature review that organizes a field into an argument - consensus, disputes, evidence quality, and the open gap the reader should care about. Use when someone asks "write my related-work section", "review the literature on X", "what does the research say about X", or "organize these papers into themes". Do NOT use for an exhaustive, protocol-registered review with formal inclusion criteria and risk-of-bias appraisal - use systematic-review instead. Do NOT use for synthesizing interviews or mixed non-academic sources into decision themes - use research-synthesis instead.
fact-checker
Verifies discrete factual claims against multiple independent sources and returns a calibrated verdict - Verified, Likely true, Likely false, Unverifiable, or False - with confidence and citations. Use when someone asks "is this true", "fact-check this claim", "did X really happen", "verify this statistic before we publish", or pastes a quote, number, or viral post to check. Do NOT use for tracing a citation chain back to its primary origin and appraising study methodology - use claims-verifier instead; for a broad open-ended question that needs a full research brief, use deep-research.
citation-tracker
Verifies that every citation is real, unretracted, and complete, rates source quality by evidence tier, and formats reference lists precisely in APA, MLA, Chicago, or IEEE. Use when someone asks "check my references", "format this bibliography in APA", "are these citations real", or "convert my reference list to IEEE". Do NOT use for checking whether the claims in the text are true - use fact-checker or claims-verifier instead. Do NOT use for writing the review itself - use literature-review or systematic-review instead.
academic-essay
Structures and drafts argumentative academic essays - a contestable thesis, claim-evidence-analysis body paragraphs, a fairly-engaged counterargument, and a synthesizing conclusion - marking every spot that needs a real citation instead of inventing sources. Use when a student or writer asks "help me outline my essay", "is my thesis strong enough", "structure my argument for this paper", or needs a draft refined for logic and formal register. Do NOT use for opinion pieces aimed at a general audience - use op-ed-writer instead; for surveying scholarly sources, use literature-review.