skills/58-charlescoverdale-econstack/briefing-note/SKILL.md
Structured policy briefing note (1-2 pages). Issue, background, analysis, options, recommendation. UK GES, Australian Treasury, consulting formats. Auto-populates from econstack data skills.
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research briefing-noteInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Only stop to ask the user when: the policy issue is unclear, the audience is ambiguous, or multiple conflicting options exist and the user needs to choose a framing. Never stop to ask about: format (use the detected template), section ordering, data sources (use the best available), or citation style.
<!-- preamble: update check -->Before starting, run this silently. If it outputs UPDATE_AVAILABLE, tell the user:
"A new version of econstack is available. Run cd ~/.claude/skills/econstack && git pull to update."
Then continue with the skill normally.
~/.claude/skills/econstack/bin/econstack-update-check 2>/dev/null || true
<!-- preamble: project learnings -->
After the update check, run this silently to load prior learnings for this project:
eval "$(~/.claude/skills/econstack/bin/econstack-slug)"
~/.claude/skills/econstack/bin/econstack-learnings-read --limit 3 2>/dev/null || true
If learnings are found, apply them. When a prior learning influences a decision, note: "Prior learning applied: [key]".
Capturing new learnings: After completing this skill, log new insights via:
~/.claude/skills/econstack/bin/econstack-learnings-log '{"skill":"...","type":"...","key":"...","insight":"...","confidence":N,"source":"observed|user-stated|inferred"}'
Types: framework (preferred appraisal framework), parameter (custom overrides), data-source (preferred data), output (past report references), operational (tool/env quirks), preference (formatting/style). Confidence: 9-10 observed/stated, 6-8 strong inference, 4-5 weak. User-stated never decays; observed/inferred lose 1 point per 30 days. All data stored locally. Nothing transmitted.
Safety rules for this skill:
Parameter database is read-only. Never write to, modify, or delete files in ~/econstack-data/parameters/. These are shared, versioned parameters maintained separately. If a parameter needs updating, tell the user to update the econstack-data repo.
Confirm before overwriting. Before writing an output file, check if a file with the same name already exists. If it does, ask the user: "A file named [filename] already exists. Overwrite it, or save with a new name?" Do not silently overwrite.
At the end of every skill run, report one of these statuses:
Format: STATUS: [status] | [one-line reason]
Generate a structured 1-2 page policy briefing note. The most common output of government and consulting economists: a short, decision-focused document that presents an issue, analyses it, sets out options, and makes a recommendation.
This skill is interactive. It confirms the topic, audience, and framing, then generates the note.
/briefing-note [topic] [options]
Examples:
/briefing-note "Impact of the new minimum wage increase on hospitality sector employment"
/briefing-note "Options for reforming business rates" --audience minister
/briefing-note "Economic case for extending childcare subsidies" --format au-ris
/briefing-note "Trade implications of US tariff changes for UK manufacturing" --format word
Options:
--audience <type> : Target reader. minister (default), board, cabinet, sr (spending review), public. Adjusts tone and detail level.--format <template> : Briefing template. uk-ges (default), au-treasury, consulting, think-tank. See templates below.--stance <position> : neutral (default, present options equally), recommend (lead with a recommendation), advocate (make the case for a specific position, with caveats).--length <pages> : 1 or 2 (default). Page 1 is always the core brief; page 2 adds deeper analysis.--data : Auto-populate with live data from econstack R packages (ons, boe, fred, etc.) where relevant.--with-cba <file> : Import a CBA output to summarise in the options section.--with-io <file> : Import an IO report to summarise in the analysis section.--client "Name" : Add "Prepared for" metadata.--format-output <type> : Output format: markdown, word, pptx, pdf, or all. Default: markdown.--exec : Generate a 3-slide executive summary deck.uk-ges, default)The standard Government Economic Service briefing structure:
RESTRICTED / OFFICIAL-SENSITIVE [classification]
TO: [Minister / Director / Board]
FROM: [Team / Division]
DATE: [Date]
SUBJECT: [One-line topic]
1. ISSUE
[1-2 sentences. What decision is needed and why now?]
2. BACKGROUND
[3-5 sentences. Context the reader needs. What has happened,
what is the current position, why does it matter?]
3. ANALYSIS
[The core economic analysis. 1-3 key findings with numbers.
Each finding should be a bolded topic sentence followed by
1-2 sentences of evidence. Cite sources.]
4. OPTIONS
[2-4 options, each with:
- What it involves (1 sentence)
- Estimated cost/benefit (1 line)
- Pros (1-2 bullets)
- Cons (1-2 bullets)]
5. RECOMMENDATION
[1-2 sentences. Which option and why. If --stance neutral,
present the trade-off and leave the decision to the reader.]
6. NEXT STEPS
[2-3 bullet points. What happens if the recommendation
is accepted. Timeline.]
ANNEX: [Optional. Key data table or chart. 1 page max.]
au-treasury)BRIEF FOR [Minister / Secretary / Board]
TOPIC: [One-line subject]
TIMING: [Why now? Decision deadline if applicable]
ACTION: [What is the reader being asked to do?]
KEY POINTS
- [Bullet 1: the single most important thing]
- [Bullet 2: supporting point]
- [Bullet 3: risk or caveat]
BACKGROUND
[3-5 sentences of context]
ANALYSIS
[Core analysis with numbers. Include comparison to
other jurisdictions where relevant (UK, NZ, Canada).]
OPTIONS
[Structured as above. Australian briefs tend to include
fiscal impact explicitly for each option.]
RECOMMENDATION
[Direct. Australian briefs are typically more explicit
in their recommendation than UK ones.]
Cleared by: [Division Head]
Contact: [Officer name, phone]
consulting)[CLIENT LOGO PLACEHOLDER]
ECONOMIC BRIEFING: [TOPIC]
[Date] | Prepared for [Client]
EXECUTIVE SUMMARY
[3-4 sentences covering the issue, key finding, and recommendation.
Bolded key numbers. Action-oriented language.]
CONTEXT
[Why this matters to the client specifically.
Link to their strategy / KPIs / current programme.]
KEY FINDINGS
[3-5 findings, each as a bolded headline sentence + 2-3 lines
of supporting evidence. Use bullet points for data.]
IMPLICATIONS AND OPTIONS
[2-3 options with estimated impact. Frame in terms of
the client's objectives, not abstract policy goals.]
RECOMMENDED APPROACH
[Clear recommendation with implementation steps.]
APPENDIX: METHODOLOGY AND SOURCES
[Brief note on data sources and analytical approach.
1-2 sentences, not a full methodology section.]
think-tank)[TITLE: Provocative, insight-led headline]
[Subtitle: one sentence framing]
[Author name / Team] | [Date]
[Opening paragraph: the hook. Start with the most surprising
or important finding, not the background. Think Resolution
Foundation / IFS / Grattan Institute style.]
[2-3 sections of analysis with charts/tables. Each section
has a bolded finding as a heading.]
[Policy implications: what should government do?]
[Methodology note: 2-3 sentences at the end.]
Extract:
If the topic is not provided, ask:
AskUserQuestion: "What is the policy issue or question for this briefing note?"
(Free text)
Before writing, confirm the framing with the user:
AskUserQuestion: "I'll write a [length]-page [template] briefing note on '[topic]' for [audience]. The stance will be [stance]. Is this right?"
Options:
- "Yes, go ahead" (Recommended)
- "Change the audience"
- "Change the template"
- "Change the stance"
If the topic relates to macroeconomic indicators, fiscal data, trade data, or local authority data, pull relevant data using econstack R packages:
# Check which packages are available
macro_available <- requireNamespace("ons", quietly = TRUE) ||
requireNamespace("fred", quietly = TRUE)
trade_available <- requireNamespace("comtrade", quietly = TRUE)
Use the data to populate the Analysis section with specific numbers. Always cite the source and date of the data.
If the topic requires data that is not available via R packages, use WebSearch to find the latest figures from official sources.
Follow the selected template exactly. Key principles:
Tone by audience:
minister: Short sentences. No jargon. Lead with "so what." Every paragraph earns its place.board: Slightly more technical. Can use economic terms without defining them. Focus on financial implications.cabinet: Political awareness. Flag distributional impacts and regional effects. Note any media/public sensitivity.sr: Fiscal focus. Everything framed in terms of spending, savings, and value for money. Reference Spending Review guidance.public: Plain English. No acronyms. Explain why this matters to people's lives.Tone by stance:
neutral: Present options equally. "On the one hand... on the other." End with "Ministers may wish to consider..."recommend: Lead with the recommendation. Present options but signal preference. "We recommend Option B because..."advocate: Make the strongest case for the preferred position, while honestly noting risks and counterarguments.Data presentation:
Length control:
<!-- KEY NUMBERS
type: briefing-note
topic: [topic]
template: [template]
audience: [audience]
stance: [stance]
date: [date]
key_finding: [one sentence]
-->
Save as briefing-{slugified-topic}-{date}.md if and only if markdown is in the requested output set (the default).
The user requests format(s) via --format. Default: md. Comma-separated lists are allowed (e.g. --format md,pdf); all expands to every supported format.
For each format explicitly requested, produce that file and only that file:
md: write the markdown inline (only when md is in the requested set).docx: invoke the docx skill with the rendered content.pdf: render via the econstack Quarto template (or invoke the pdf skill if no template exists for this skill).xlsx: invoke the xlsx skill with the structured tables.pptx: invoke the pptx skill with the briefing as a deck.Do NOT produce formats that were not requested. This is the v0.4 fix for the multi-format leak that previously caused --format pdf to also write .md and .docx files alongside the PDF. Any intermediate files needed during rendering must go to a temp directory and be cleaned up before the skill returns.
When you finish, the file listing in your "Saved:" message must contain exactly the files the user asked for, no extras.
(Note: in this skill --format selects the briefing template, not the output format. Output format is controlled by --format-output. The dispatcher above applies to whatever the user passes via --format-output.)
If --exec specified, generate a 3-slide deck:
Every numerical claim in the output must be followed by an inline citation in the form [SOURCE_CODE, vintage]. SOURCE_CODE is a short tag (e.g. ONS_PSF, OBR_EFO, BoE_MPR, Fed_FOMC, ECB_EB, RBA_SoMP, IMF_WEO, OECD_EO, Eurostat, BLS, BEA, FRED, ABS, Comtrade) matching an entry in the References footer. vintage is the publication date of the source data (e.g. Mar 2026, Q4 2025, Jan 2026).
Examples:
CPI was 3.4% YoY in March 2026 [ONS_CPI, Mar 2026].
The OBR forecasts borrowing falling to 1.6% of GDP by 2028-29 [OBR_EFO, Mar 2026].
Industry concentration is moderate: HHI is 1,820 across the top 8 firms [Companies_House, Q4 2025].
Numbers that cannot be sourced to a primary publication must NOT appear in the output. No exceptions: do not estimate, infer from training data, interpolate, or recall from memory. If a needed number isn't in fetched data, state it explicitly:
[Source] has not yet published this measure for [period].
Self-check before output: scan the draft for every number. If any number lacks an inline citation, either add the citation or remove the number. Citation density should be roughly even across sections; a section with no citations is a red flag that the section was generated rather than sourced.
Briefing notes are decision tools and so factual errors are particularly damaging. Before asserting any quantitative or technical claim, verify it against a primary source. If a needed fact is not available in the fetched data or supplied context, say so explicitly rather than recall from memory:
The latest [indicator] for [period] has not yet been published.
Common gotchas in policy briefing: definitions drift between governments (e.g. "free school meals", "hate crime", "rough sleeping" all have specific operational definitions that have changed); thresholds and rates change frequently; "the government has committed to X" requires a citation to a specific document.
A briefing note is constrained by --stance. Do not exceed it:
--stance neutral, do NOT smuggle a recommendation into analysis sections. Keep analysis and recommendation strictly separate.--stance advocate, do NOT hide counterarguments; the reader's trust depends on acknowledging downsides.tools
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDF→Markdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it. Curated catalog of 70+ vetted projects. 支持中英文(用于「文献综述工具选型」与「一键安装/运行」)。
development
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
documentation
Use when the project collects primary data or runs a field, lab, or survey experiment, before the intervention begins — write the pre-analysis plan, size the sample from a power calculation, and register with the AEA RCT Registry. Apply after the design is chosen in aer-identification and before any outcome data are seen.
tools
Guide economists to authoritative data sources with explicit, confirmed data specifications before retrieval; interfaces with Playwright MCP to navigate portals and extract real data, not articles about data.