agentic/code/frameworks/research-complete/skills/funder-network/SKILL.md
Build the bipartite funder↔paper analytics — per-funder paper/A-grade/mean-grade rollup, mean CD-index + novelty bias, and co-funding clusters. Runs via `aiwg corpus funder-network`.
npx skillsauth add jmagly/aiwg funder-networkInstall 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.
Per-funder analytics over the funder↔paper bipartite graph (funder linkage comes
from each REF's funders[]). Complements the by-funder view (#1492).
aiwg corpus funder-network # funder table + co-funded papers to stdout
aiwg corpus funder-network --out indices/funder-network.md
aiwg corpus funder-network --scan-acks # also scan REF acknowledgement text (uses funder-aliases.yaml)
Per funder (PROF-F / PROF-O): paper count, A-grade count, mean grade, mean CD-index + novelty bias (vs the corpus novelty baseline — below/at/above), reusing the #1501 CD-index. Plus co-funding clusters (papers with ≥2 funders).
funders[] (both {id, grant-id}
and bare-string forms). No funder list is hardcoded.--scan-acks reads a corpus-local documentation/profiles/funder-aliases.yaml
(raw-name → PROF-F/PROF-O id; absent → no aliasing) and scans REF acknowledgement
sections — the externalized alias path.type: funder)./funder-networkdata-ai
Report which research-corpus radar sidecars are overdue for refresh. Computes staleness (days since last refresh vs the cadence window) for every radar, sorted most-overdue-first. Runs via `aiwg corpus radar-status`.
data-ai
Aggregate research-corpus radar sidecars into a corpus or per-cluster freshness report — totals, overdue count, per-cluster / per-GRADE / per-trajectory breakdowns, an overdue table, and per-radar rationale snippets. Runs via `aiwg corpus radar-report`.
testing
Scaffold radar/freshness sidecars for research-corpus REFs. Pulls title/authors from the citation sidecar and GRADE from the analysis doc, defaults the refresh cadence from GRADE and the cluster from a corpus-local map, and stamps documentation/radar/REF-XXX-radar.md. Runs via `aiwg corpus radar-init`.
data-ai
Compute an entity's publication trajectory — per-year paper counts, topic drift, hot-streak detection (≥3 consecutive A-grade years), and career phase. Runs via `aiwg corpus profile-temporal`.