agentic/code/frameworks/research-complete/skills/discovery-log/SKILL.md
Record the source-tracking `discovery` block on a research-corpus citation sidecar — where/how a paper was found (surface, via, curator). Runs via `aiwg corpus discovery-log`.
npx skillsauth add jmagly/aiwg discovery-logInstall 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.
Record how a paper was discovered — the optional discovery: block in a
citation sidecar's frontmatter (SOURCE-TRACKING schema). The read views
by-source / by-curator (#1492) consume this.
aiwg corpus discovery-log --ref REF-640 --surface x-account --via "x.com/@askalphaxiv" --curator PROF-S-askalphaxiv # dry-run (prints the block)
aiwg corpus discovery-log --ref REF-640 --surface x-account --via "x.com/@askalphaxiv" --curator PROF-S-askalphaxiv --write # splice into the sidecar
aiwg corpus discovery-log --ref REF-641 --surface x-search --write # surface only, no curator
discovery: block in the sidecar frontmatter,
preserving the rest of the file. Dry-run unless --write.--surface (required) vocab: x-account | x-search | x-bookmarks | x-foryou | x-following | rss | newsletter | web | referral | direct.--curator (optional) is a PROF-S- id; set it only when the source came
through a named, repeatable curator. Omit for direct/search-found papers
(curator-id: null). The block is OPTIONAL by design — absence is never an error.Distinct from radar
sources-searched(surfaces queried during a freshness refresh):discoveryrecords where a paper was originally found.
/discovery-logdata-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`.