paper-trail-acquire
Troisième passe du pipeline cible refondu. Lance la cascade PDF (10 sources : Crossref OA + arXiv + OpenAlex + Unpaywall + HAL + CORE + éditeur par DOI +…
Resolve incomplete textbook references in the registry. Reads candidates via `pipeline resolve-textbooks --list`, invokes the `textbook-resolver` sub-agent to produce a decisions JSON (merge_into / complete / blocked), and applies via `pipeline resolve-textbooks --apply-from`.
$ npx -y skills add roomi-fields/paper-trail --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/paper-trail-resolve-textbooksContext preview
What this command does when you run it.
Resolve incomplete textbook references in the registry. Reads candidates via `pipeline resolve-textbooks --list`, invokes the `textbook-resolver` sub-agent to produce a decisions JSON (merge_into / complete / blocked), and applies via `pipeline resolve-textbooks --apply-from`.
description: Resolve incomplete textbook references in the registry. Reads candidates via `pipeline resolve-textbooks --list`, invokes the `textbook-resolver` sub-agent to produce a decisions JSON (merge_into / complete / blocked), and applies via `pipeline resolve-textbooks --apply-from`. Fully automated cleanup pass after INGEST.
Nettoie les refs ingérées avec year/title manquant. Process 100% automatisé, pas de décision humaine ad-hoc.
/paper-trail:resolve-textbooks # dry-run : montre les décisions /paper-trail:resolve-textbooks --apply # applique
1. **Liste les candidates** :
python3 -m pipeline resolve-textbooks --list > /tmp/textbook_candidates.json
Le JSON contient : slug, author, year, title, state, ingest_source, pdf_path, et `siblings` (autres refs du registre avec même lastname, pour aider à la fusion).
2. **Invoque le sub-agent `textbook-resolver`** avec le JSON en input :
Agent(subagent_type="textbook-resolver",
prompt="<contenu de /tmp/textbook_candidates.json>")Le sub-agent applique les règles définies dans son contrat (cf. `agents/textbook-resolver.md`) :
3. **Sauve le JSON de décisions** retourné par le sub-agent dans `/tmp/textbook_decisions.json`.
4. **Mode dry-run** (par défaut) : affiche le résumé des décisions (nb par action), demande confirmation avant `--apply`.
5. **Mode `--apply`** :
python3 -m pipeline resolve-textbooks \
--apply-from /tmp/textbook_decisions.json6. **Récap final** : N merged, N completed, N blocked.
Confidence < 80% → `blocked` (l'utilisateur tranchera via `/paper-trail:decide <slug>`).
`retracted_reason: merged_into:<target>`. Réversible via git.
lui-même, il délègue au sub-agent. Process reproductible.
textbooks que l'INGEST a créés sans year/title
registre
Anti-hallucination plugin for academic research in Claude Code. Create literature reviews and papers guaranteed without fabricated citations.
Troisième passe du pipeline cible refondu. Lance la cascade PDF (10 sources : Crossref OA + arXiv + OpenAlex + Unpaywall + HAL + CORE + éditeur par DOI +…
Batch audit of every SOTA in the vault. For each SOTA, identifies refs that are page1_validated (technical OK) but not yet sota_cited_confirmed (content…
Per-citation audit of an academic article (LaTeX or Markdown). Produces RECEIPTS.md classifying each citation as VALID/ADJUST/INVALID/UNVERIFIABLE. Optional…
Audit a SOTA's bibliography. Classify each cited ref by validation state. Optional --purge removes citations to retracted refs from the SOTA (with .bak backup).
Acquire PDFs via the 8-source cascade (11 with opt-in extended sources) for a single ref by slug, or a batch filtered by state. Validates page 1 anti-homonymy…
Inspect a single reference in detail (identity, PDF status, acquisition history with verdicts, citation context in vault, state transitions) and decide its…