Update to Pendar

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,21 +1,23 @@
 ---
 name: trace-citation-impact
-description: Trace who has built on a specific paper — whether its citations are accelerating or fading, which research fields picked it up, whether universities or industry or hospitals are citing it, and which authors cite it most. Use when the user asks how influential a paper is, whether it is still relevant, where a method spread, which labs are working on it, or what it was built on.
+description: Measure a paper's scholarly impact — whether its citations are accelerating or fading, which research fields adopted it, and what kinds of institutions cite it. Use when the user asks how influential a paper is, whether it is still relevant, where a method spread, or what it was built on.
 metadata:
-  short-description: Follow who has built on a paper, and where it spread
+  short-description: Measure a paper's impact and where it spread
 ---
 
 # Trace citation impact
 
-Take one paper and report how the literature has used it: the exact per-year
-citation history, the fields the citing work comes from, the kinds of institution
-doing the citing, and the authors citing it most. `graph_hopper` resolves the
-paper, walks one hop forward to its citers and one hop back to its references,
-and returns counts over the citing set.
-
-The value is in *who* cited it, not how many did. A citation total is available
-anywhere; the composition of the citing set is what says whether a method
-travelled beyond its home field and who is carrying it.
+Take one paper and report how the literature has used it: the per-year citation
+history, the research fields of the citing papers, the kinds of institution the
+citing papers come from, and how that mix is shifting. `graph_hopper` resolves
+the paper, looks one step forward to the papers citing it and one step back to
+its references, and returns exact counts over the whole citing set.
+
+The value is in the composition of the citing literature, not the total. A
+citation count is available anywhere; the mix of fields and institution types is
+what shows whether a method travelled beyond its home field. Describe the result
+as how one paper connects to the field around it: which areas picked it up, and
+which it was built on.
 
 ## Quick start
 
@@ -23,12 +25,9 @@
    A `paper_id` from an earlier Pendar result also works and resolves exactly.
 2. Leave `direction` as `both` unless the user asked only about influence
    (`forward`) or only about foundations (`backward`).
-3. Leave `analyze_citers` at 50, or raise it toward 100 for a heavily cited
-   paper. It widens the breakdowns at almost no cost, since they come back as
-   counts.
-4. Keep `papers_per_direction` small — 10 is usually enough. The breakdowns
-   already summarise the rest.
-5. Set `include_graph: true` **only** when the user wants a diagram of the
+3. Keep `papers_per_direction` small — 10 is usually enough. The breakdowns
+   already cover every citing paper.
+4. Set `include_graph: true` **only** when the user wants a diagram of the
    neighbourhood. It is large and adds nothing the breakdowns do not cover.
 
 If `found` is false, present `candidates` and ask which paper was meant. Do not
@@ -38,49 +37,63 @@
 
 - `momentum.trend` is one of `accelerating`, `steady`, `declining`, `too_new`,
   `unreliable`, or `unknown`.
-  - **`unreliable` means report no trend at all.** The paper's own per-year
-    history contradicts itself, which happens when duplicate records for one
-    paper are merged or split and most of its citations follow the other copy.
-    Say the citation record for this paper appears damaged and that a trend
-    cannot be read from it. Do not describe such a paper as declining — that is
-    the artefact talking, and it will be wrong about famous papers in particular.
+  - **`unreliable` means report no trend at all.** The paper's per-year history
+    contradicts itself, which happens when duplicate records of one paper are
+    merged or split. Say the citation record appears damaged and a trend cannot
+    be read from it. Do not describe such a paper as declining.
   - `too_new` means too little history, not lack of impact.
-  - Use `momentum.interpretation` as written; it is derived from the exact
-    histogram. `recent_3y_citations` against `prior_3y_citations` is the evidence
-    behind it.
-- `field_mix` — the research areas the citing papers belong to, from a standard
-  discipline taxonomy. Name both `subfield` and `field`. Subfields far from the paper's
-  own are the interesting part: they are where the work crossed over. Do not
-  reduce this to a single "interdisciplinarity" figure; field boundaries are
-  administrative and such a number would mislead.
-- `institution_mix` — universities, industry, hospitals, government labs. An
-  industry or hospital share is the signal that research became practice.
-  `representative_institutions` are examples from that bucket, not the full list,
-  so do not present them as the only ones.
-- `top_citing_authors` — the corresponding authors citing the work most, ranked
-  by their own citation totals. These are the people building on it: useful for
-  finding collaborators, reviewers, or labs to approach. They are **not**
-  co-authors of the seed paper, and citing a paper does not imply endorsing it.
+  - Use `momentum.interpretation` as written. `recent_3y_citations` against
+    `prior_3y_citations` is the evidence behind it.
+- `breakdowns_exact` — when true, `field_mix`, `institution_mix`,
+  `top_citing_venues`, `citing_work_types`, and `citing_funders` are counted over
+  all `citing_papers_total` citing papers, not a sample. When false, they cover
+  `citer_sample_size` papers; say so whenever you quote a percentage.
+- `field_mix` — the research areas of the citing papers, from a standard
+  discipline taxonomy. Name both `subfield` and `field`. Subfields far from the
+  paper's own are where the work crossed over. Do not reduce this to a single
+  "interdisciplinarity" figure; field boundaries are administrative.
+- `field_drift` — each subfield's share of the citing papers in the last three
+  complete years against the three before (`drift_window` names the years),
+  with a `share_trend` of `gaining`, `steady`, `losing`, or `new`. This is where
+  the paper is being picked up now, as opposed to where it was picked up first.
+  All `steady` is a finding too: the audience has not shifted.
+- `institution_mix` — the share of citing papers with at least one author at a
+  university, company, hospital, government lab, and so on. Shares overlap,
+  because one paper can have authors in several sectors. A company or hospital
+  share is the signal that research moved into practice.
+- `citing_work_types` — articles, preprints, reviews, and so on. A large preprint
+  share means the uptake is recent and not yet peer reviewed.
+- `citing_funders` — funders acknowledged by the citing papers. Only papers that
+  report funding are counted, so this is a lower bound.
+- `top_citing_authors` — authors of the citing papers, from the public
+  publication record, ranked by how many citing papers they appear on
+  (`paper_count`). `total_citations` covers only the most-cited sample; do not
+  quote it as a citation total. Report these authors as part of the citing
+  literature, not as endorsements of the paper.
 - `cited_by` and `references` — the most-cited individual papers in each
   direction. Abstracts are omitted; call `verify_paper` on one if the user wants
   its full record.
-- `notes` — carries the sample size behind the breakdowns ("breakdowns cover N
-  citing papers") and flags an absent citer or reference list. Quote the sample
-  size whenever you quote a percentage.
+- `notes` — caveats about coverage. Repeat the ones that bear on what you claim.
 
 ## Never
 
 - Equate citation count with quality or correctness. It measures attention.
   Retracted papers accumulate citations too, so check `seed.is_retracted`.
 - Report a decline when `trend` is `unreliable`.
-- Say a paper is uncited when `notes` reports that no citers were indexed — a
-  recent paper and an unindexed one look identical from here, and the note
-  distinguishes them.
-- Infer a lab's research agenda, a company's product plans, or an author's
-  opinion from a single citation.
+- Say a paper is uncited when `notes` reports that no citing papers are indexed —
+  a recent paper and an unindexed one look identical from here.
+- Draw conclusions about any person or organisation beyond what the publication
+  record shows.
 - Compare two papers' raw citation totals across different years or fields
   without saying that both vary by publication age and field size.
 
+## Drawing
+
+Offer charts when the user would benefit from them: the citation momentum as a
+line of citing papers per year, with the current year marked as partial, and the
+field mix as bars. Never draw a trend through the partial year, and never draw a
+value that is not in the response.
+
 ## Reporting
 
 1. **The paper** — canonical title, authors, year, venue, total citations, and
@@ -88,14 +101,16 @@
 2. **Trajectory** — accelerating, steady, declining, or unreadable, with the
    three-year counts and peak year behind it.
 3. **Where it spread** — the citing fields, calling out any far from the paper's
-   own subfield.
-4. **Who is citing** — the institution mix, then the leading citing authors.
+   own subfield, then where it is being picked up now (`field_drift`).
+4. **Which sectors cite it** — the institution mix, work types, and funders.
 5. **What to read next** — the most-cited citing papers, and the references if
    the user asked what it was built on.
-6. **Sample size and caveats** — how many citers the breakdowns cover.
+6. **Coverage and caveats** — whether the breakdowns are exact, and any notes.
 
 ## Related workflows
 
 - To size the whole field rather than one paper's reach, use
   `survey-a-research-field`.
+- To see how a researcher's whole body of work connects to the fields around
+  it, use `map-my-research`.
 - To confirm a reference exists and is not retracted, use `verify-citations`.