Convert a Researcher Evidence Brief (one slug under literature-reviews/) into one of four learning products: MA-facing 2-page brief, workshop / CoP pack, regional learning brief, or donor / management talking-points memo. Reuses the brief's verified sources only; never fabricates citations; applies

Learning Product One Researcher Evidence Brief → one of four learning product output types. The skill carries the brief's evidence into the format the audience can use, without weakening the rigour and without adding sources the brief did not verify. When to use Trigger on any of: "learning product", "learning brief", "MA brief from this Evidence Brief", "MA facing brief" "workshop pack", "CoP pack", "facilitator pack", "build me a workshop from this brief" "regional learning brief", "federation brief", "regional synthesis" "donor memo from this brief", "management memo", "talking points memo", "decision memo for donor" explicit naming of an output type ( v1 , v2 , v3 , v4 , ma brief , workshop cop pack , regional learning brief , donor management memo ) Do not trigger for: producing the underlying Evidence Brief — that is the researcher skill general decision memos not derived from a Researcher Evidence Brief — that is the decision memo skill evaluation design or indicator design — those are separate skills ToC building — toc builder Required inputs Ask in one batch. First two are required. 1. Evidence Brief slug (required): the directory name under literature reviews/ , e.g. 2026 05 10 cse anti gender opposition eca . The skill reads literature reviews/<slug /evidence brief.md . 2. Output type (required): one of ma brief (v1), workshop cop pack (v2), regional learning brief (v3), donor management memo (v4). 3. Recipient (required for v4 only): one of donor programme officer , donor senior , ippf en management , ippf central management , mp or policy . Used to calibrate voice register and the decision asked framing. 4. Audience focus (optional): MA cluster, sub region, country list. Defaults derive from the Evidence Brief's geography metadata. 5. Length override (optional): word count or page count beyond default. Defaults defined per output type below. 6. Workshop format (optional, v2 only): single 90min (default), two session split , half day , full day . Affects slide count and segment timing. 7. Workshop modality (optional, v2 only): in person (default), hybrid , virtual . Affects facilitator notes and microstructure adaptations. 8. Country snapshot count (optional, v3 only): default 4; allowed range 3–5. 9. Country naming convention (optional, v3 only): sub region label (default — Western Balkans MA, Caucasus MA, Baltic MA, Visegrád MA) or country name (triggers redaction candidate flagging). 10. Decision asked (optional, v4 only): the specific decision the recipient must make. If absent, the skill drafts a placeholder and flags it for replacement before publication. Session start 1. Read this SKILL.md fully. 2. Read the Evidence Brief at literature reviews/<slug /evidence brief.md . 3. Read the matching exemplar at agent improvements/learning product exemplar v[1 2 3 4].md for the requested output type. The exemplar is the structural target. 4. Read ~/.claude/CLAUDE.md audience tier register section once per session if not already in context. Workflow Step 1 — parse inputs and route Identify output type. If missing or ambiguous, ask Ane in one round: "Which output type? ma brief (2 page MA brief), workshop cop pack (workshop + CoP pack), regional learning brief (5–8 page federation brief), or donor management memo (1 page memo)?" If donor management memo is selected without a recipient parameter, ask for it in the same round. Step 2 — load source material Read in order: 1. literature reviews/<slug /evidence brief.md — the source content 2. literature reviews/<slug /sources.md if present — verified hyperlink list 3. literature reviews/<slug /literature review.md if present — fuller synthesis for v3 depth 4. agent improvements/learning product exemplar v[N].md — structural target The Evidence Brief frontmatter carries the region , period , and confidence metadata the output's title block uses. Step 3 — apply the output type sub prompt Route to one of the four sub prompts below. Each sub prompt instantiates the corresponding exemplar's structure against the Evidence Brief's content. Step 4 — apply quality gates (all output types) Before returning the draft: BLUF discipline. Sentence 1 = the verdict. Sentence 2 = the load bearing reason. v1 headline ≤ 3 lines bold; v3 executive summary 5 bullets exact; v4 bottom line 1 paragraph bolding the decision ask. Voice register. Tier 1 working brief by default. v4 unlocks directive register only at the decision asked section. v2 facilitator notes use directive verbs for procedural steps. Citation placement. Tier 1 working brief: framework names off the running text; Evidence base: line at end of section. v2 source slide uses "For further details you can consult:" lead phrase per feedback source slide framing.md . Citation rigour. Author surname + year + venue + section where applicable. Lifted verbatim from the Evidence Brief. Never invent. Hyperlink policy. Reuse only URLs that appear in the Evidence Brief or its sources.md . Never fabricate. Any URL not present in the source carries ⚠️ URL unverified — confirm before publication . Session time URL audit step. Before returning the draft, verify each cited URL against the IPPF/UNFPA hyperlink standard: Aggregator wrappers ( consensus.app , ResearchGate, academia.edu, Wikipedia) MUST be replaced with the canonical publisher URL or DOI before publication. Aggregators are tolerated only as supplementary alongside canonical, never as sole source. DOI links that resolve to a paywall MUST be supplemented with an open access alternative (PMC, institutional repository, publisher hosted open PDF, author manuscript) where one exists. Publisher migrated URLs (Rowman to Bloomsbury, journal venue changes, etc.) MUST be updated to the current canonical URL. URLs returning 404 MUST be replaced with the canonical permanent link (typically UNESDOC, DOI, or institutional repository). When the canonical source has no open access alternative and the audience is non academic, the citation MUST flag "paywalled, no open access alternative found" so MA staff and partner readers know in advance. The audit applies WebFetch and WebSearch at session time. Lift the audit cost across the four output types (v1/v2/v3/v4) by running once per Evidence Brief, caching the URL substitutions, and reusing them across all output types generated from the same source brief. Sentence length. Under 25 words. Active voice. No em dashes in body prose. No nominalisations where a verb works. Narrative prose model + fidelity gate (per agent improvements/model selection policy.md ). The illustrative narrative elements — v1 vignettes and v2 CoP workshop scenarios — MAY be drafted via a Fable per call override (sanctioned: Fable was the more faithful drafter on narrative source constrained prose, 2026 06 10). When any narrative element is Fable drafted, the prose fidelity gate (Gate 2 in the policy) is MANDATORY: run it on Sonnet against the source Evidence Brief and clear every flag before inclusion. The v4 donor / management talking points memo and any persuasive or management decision content stay on this skill's own model (Opus/Sonnet) — Fable is NOT used there, because the persuasive genre pulls both models toward overstatement; run the prose fidelity gate with attention to overstatement and attribution inflation regardless. Plain English. Anglo Saxon over Latinate. Acronyms spelled on first use. Translatability test for ECA / SSA / MENA readers. Disaggregation default. When the Evidence Brief carries WG SS, age, gender identity, geography breakdown, the output preserves the disaggregation rather than collapsing. Cross MA naming. Default sub region labels (Western Balkans MA, Caucasus MA, Baltic MA, Visegrád MA) unless the Evidence Brief or Ane explicitly names a country. Country level naming triggers a redaction candidate flag. IPPF Visual Identity 2025. Word, PPTX, and PDF outputs go through ane package.reporting brand template entry points. No hard coded colours, fonts, or formats. Step 5 — provenance footer Every output ends with a How this <product was made block: One paragraph naming the source Evidence Brief (slug + date), the voice register applied, and the brand template path. A Cross MA references named: line listing every MA cluster or country named in the body. A Redaction candidates: list of any specific MA, country, or named individual a federation reader may want to remove before external use. If the body uses sub region labels only, the list reads "none at sub region level". A Companion artefacts in the four exemplar series: line for v2/v3/v4 cross referencing the other three outputs as agent improvements/learning product exemplar v[N].md . Step 6 — return Return the draft as text in the assistant turn. If the output is workshop pack (v2), additionally generate the artefact files via ane package.reporting : Slide deck → pptx export.write pptx deck Handout one pager → word export.write word report → exported to PDF via pdf export.write pdf report Worksheet → simple Word file via word export.write word report For v1, v3, v4: return as markdown body in the assistant turn. Ane converts to Word/PDF/PPT via the existing reporting modules at her discretion. v3 is long enough to also produce a Word document via word export.write word report if Ane asks. Sub prompt — v1 — MA facing 2 page brief Default length. 1,200 words (≈ 2 pages). Hard cap: 1,500. Below 1,000 fails the brief's substantive density test. Required structure (mirror learning product exemplar v1.md ): 1. Title block — title, audience, length, date, voice, evidence (Tier 1/2 mix from the brief). 2. Headline — 3 line BLUF, bold the verdict in line 2. 3. Why this brief — frames the issue. 3–5 sentences. Names the geography from the Evidence Brief. 4. What we know — 3–5 numbered findings. Each finding is one paragraph. Findings come from the Evidence Brief's RQ1 / Findings section verbatim or compressed. 5. Evidence base line — at end of "What we know". Hyperlinked. Pulls from the brief's source list. 6. Four levers your MA can use — 3–4 levers. Each lever has: action (1 sentence), Why it works (1 paragraph), One MA example (1 short paragraph; sub region labels by default), Resource estimate (1 line). Skip a sub field only if the Evidence Brief does not provide content. 7. What to do next quarter — single concrete action. Force one lever commitment. 8. Adaptation prompts for your context — 4 questions. Questions invite MA judgement, not Secretariat directive. 9. Questions to bring to your next regional peer exchange — 4 questions seeding the CoP convening. 10. How this brief was made — provenance + redaction candidates list per Step 5. Voice. Tier 1 working brief, collaborative. "We propose," "your MA can," "evidence suggests," "MAs may adapt to context." Reserve directive voice for compliance subject content only — none in v1. Quality bars specific to v1: Adaptation prompts MUST be questions, not statements. Each lever MUST carry a Why it works paragraph; missing this drops the brief below USAID Learning Brief implementer audience standard. The "What to do next quarter" section MUST force one lever commitment, not multi lever menu. When the source Evidence Brief carries finding level confidence markers (HIGH / MODERATE / LOW / MIXED), preserve them inline next to each finding in the "What we know" section. Federation readers need the differential confidence to interpret the lever choices; collapsing to a single rating obscures it. Sub prompt — v2 — workshop / CoP pack Default settings. Single 90 minute session; 8–15 participants; in person modality; full pack (slides + facilitator notes + handout + worksheet + pre read

learning-product