원클릭으로
enrich-claims
Enrich existing source-branch claims by updating them through pks source propose-claim.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Enrich existing source-branch claims by updating them through pks source propose-claim.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Credentialed-source backend for retrieving books from Bookshare (bookshare.org) into the papers/ collection. Given a book title or ISBN and a target directory name, it searches Bookshare and downloads the EPUB via the published `bookshare` CLI. Download-only (produces book.epub). Enable only if you have a Bookshare account; requires credentials in a gitignored .secrets/bookshare.json.
Paywalled-access backend for paper-retriever. Retrieves a paywalled paper's PDF through an institutional / library subscription (a library proxy such as EZproxy or OpenAthens, or an institutional login), given an identifier (DOI/URL) and the target paper directory name. Invoked by paper-retriever when open-access channels fail. Enable this skill only if the install has institutional access configured.
Paywalled-access backend for paper-retriever. Retrieves a paywalled paper's PDF via sci-hub browser automation, given an identifier (DOI/URL) and the target paper directory name. Invoked by paper-retriever when open-access channels fail; enabled by default. Disable this skill to remove sci-hub from the retrieval waterfall.
Retrieve a scientific paper PDF given an arxiv URL, DOI, or paper title. Downloads to papers/ directory. Handles open-access retrieval (arxiv direct, Chrome print-to-pdf for publisher-direct HTML, Unpaywall, title-based open-repository search); for paywalled papers it hands off to whichever paper-retriever-* access skill is enabled (sci-hub by default, or institutional).
Read scientific papers and extract implementation-focused notes. Converts PDFs to page images, then reads them. Papers <=300pp are read directly by the assigned worker; papers >300pp use a chapter-aligned chunk protocol (preferred) or 50-page chunks (fallback) and synthesize a master notes.md that links to per-chapter files. Creates structured notes in papers/ directory.
Cross-reference a paper against the collection. Finds which cited papers are already collected, which are new leads, which collection papers cite this one, and reconciles all cross-references bidirectionally. Run on a single paper directory or use --all for the entire collection.
| name | enrich-claims |
| description | Enrich existing source-branch claims by updating them through pks source propose-claim. |
| argument-hint | <papers/Author_Year_Title> |
| disable-model-invocation | false |
| compatibility | Claude Code, Codex CLI, and Gemini CLI. |
Improve claims that already exist on a propstore source branch. Reuse each claim's local id and call pks source propose-claim again with the enriched fields. Do not edit claim batch files.
Ontology-policy reference:
plugins/research-papers/docs/ontology-authoring-policy.mdpaper_dir="$ARGUMENTS"
source_name=$(basename "$paper_dir")
ls "$paper_dir"/notes.md 2>/dev/null || echo "MISSING: notes.md"
ls knowledge/.git 2>/dev/null || echo "MISSING: knowledge/.git"
pks source finalize "$source_name" 2>&1 || true
If the source branch or claims are missing, run paper-process or extract-claims first.
Inspect the source branch's current claims and local ids using the propstore source state. If you need a filesystem view for reading only, materialize the source branch with pks source sync into a scratch/report directory; do not treat that materialized file as an authoring target.
Read:
<paper_dir>/notes.md<paper_dir>/pngs/ for exact values and provenanceFor each correction or enrichment, rerun pks source propose-claim with the same --id and the full intended claim payload:
pks source propose-claim "$source_name" \
--id claim7 \
--type observation \
--statement "Corrected and enriched claim statement." \
--context "ctx_<author>_<year>_<slug>" \
--concept-ref concept_a \
--concept-ref concept_b \
--condition "endpoint == 'primary_endpoint'" \
--page 8 \
--section "Discussion" \
--quote-fragment "Brief supporting quote" \
--notes "Methodological qualifier."
Parameter enrichment:
pks source propose-claim "$source_name" \
--id claim8 \
--type parameter \
--concept hazard_ratio \
--value 0.88 \
--lower-bound 0.79 \
--upper-bound 0.97 \
--uncertainty-type "95% CI" \
--context "ctx_<author>_<year>_<slug>" \
--page 5
Rules:
pks source propose-claim reports missing concepts, propose those concepts first and rerun the claim command.pks source propose-claim; do not run file validators.If enrichment discovers important uncaptured findings, add them with new local ids through pks source propose-claim.
Claims enriched for: papers/[dirname]
Claims updated: N
New claims added: N
Missing concepts encountered and fixed: [...]
Validation boundary: pks source propose-claim