russellian-book-suite

Compile chapter drafts from a validated book workspace. Loads chapter contracts, obtains the chapter-retrieval bundle scaffold, drafts claim-first prose, records and checks writer assertions, applies Russellian style, runs release-gate validation, and produces release bundles (Markdown plus optional PDF/EPUB/LaTeX). All processing is local — no external APIs. Use when user says "draft chapter X", "compile chapter from contract", "build release bundle for chapter X", "render chapter to PDF", "build the book release", or "publish the book". Do NOT use for source ingestion (use book-knowledge) or prose-only rewrites (use russellian-style). Also builds book-level releases (manuscript Markdown, React+Tailwind HTML browser, Playwright PDF). Stage 4 includes a multi-persona editorial review (Gottlieb, Lay Reader, Domain Expert, Copyeditor, Enjoyment Reader) via the book-review sibling; chapter releases soft-gate on `persona_critical_count == 0`.

Run a single-pass review→revise→re-validate cycle on one chapter. Dispatches the book-review panel via gemma4:31b, aggregates findings, synthesizes revision instructions, runs a gemma4 reviser persona to produce paragraph-level rewrites, applies them, re-runs the panel, and emits a before/after delta report. Use when user says "revise chapter X based on the panel", "run a revision cycle on this chapter", "what does the cycle say about ch-N". Do NOT use for cross-chapter consistency (chapter is the unit), voice-level prose tightening absent panel findings, or auto-iteration (single pass only — operator re-runs manually for further passes).

Ingest technical sources (PDFs, markdown, papers) into a book workspace and maintain its persistent epistemic state — wiki synthesis, claim ledger with provenance, RDF graph with SHACL validation. All processing is local — no external APIs. Use when user says "ingest this paper", "add this source to the book", "update the book wiki", "extract claims from this section", "audit the knowledge graph", "validate claims", "find contradictions in the wiki", "check what's stale", or asks to refresh sources for a chapter. Do NOT use for chapter drafting (use book-compose), prose rewrites (use russellian-style), or casual document Q&A.

Post-build mechanical and editorial quality gate for non-fiction book artifacts. Runs after build_book and before shipping; the last gate. Deterministic linting (D1-D8) plus per-chapter agent swarm (C1-C15) plus optional metabook defects (D9-D12 from book-thesis) plus optional verifier defects (D13). Use after book-compose builds manuscripts to lint, aggregate QA findings, and drive bounded fixes. Do NOT use for source ingestion (use book-knowledge), prose rewrites (use russellian-style), persona reviews (use book-review), or chapter drafting (use book-compose).

Run multi-persona editorial reviews on a drafted chapter. Seven personas (Robert Gottlieb, Lay Reader, Domain Expert, Copyeditor, Enjoyment Reader, AI-Slop Detector, First-Time Visitor) read the chapter and return severity-tagged feedback. Critical findings soft-gate chapter release. Use when user says "review chapter X with personas", "Gottlieb pass on this chapter", "run the editorial reviews", "what would Gottlieb say about this draft", "is this chapter ready for review", "soft-gate this chapter". Do NOT use for source ingestion (use book-knowledge), prose-only style fixes (use russellian-style), chapter drafting (use book-compose), or persona reviews on prose outside the book pipeline.

Metabook reasoning layer for the book-* skill suite. Owns the intent substrate: a thesis tree, paragraph back-pointers to thesis nodes, per-paragraph entailment checks, and an EDN/Cozo consistency pass over claim facts for transitive cross-chapter contradictions. Use when a book needs to enforce three properties simultaneously: factual accuracy, cross-chapter consistency, and preservation of the core point across revisions. Composes with book-knowledge (facts), russellian-style (prose), book-compose (orchestrator), book-review (qualitative), book-qa (mechanical gate). Do NOT use for chapter drafting (use book-compose), claim ingestion (use book-knowledge), or sentence-grain prose discipline (use russellian-style).

General-purpose knowledge-curation layer for a book/knowledge workspace. Five capabilities — Acquire (grow the source set by citation-graph traversal and ingest via book-knowledge), Synthesize (topic maps, disputed questions, concept reconciliation over the claim ledger), Lens (project a per-chapter view book-compose reads), Gap (score thesis-node coverage and feed uncovered nodes back to acquisition), and Govern (partition rule/claim support by curated schools of thought; render reports, consensus map, adversarial review, induction gate). Use when the user wants to acquire or expand sources, synthesize a cross-source view, project a per-chapter lens, find coverage gaps, or position induced/asserted rules against schools of thought. The skill never touches the network directly (only via scrapling-fetch) and never mutates the canonical workspace (only via book-knowledge); it writes only under syntopical/.

HFR v2 evaluation. Runs the 20×20 comparison between triadic-voice (v1) and triadic-voice-v2 (v2): generate in-session, gate on the russellian-style v1 floor, score the 8 liveliness signals, judge blind pairwise, monitor formula-drift, and report pass/fail. Use to decide whether v2 beats v1. The running model generates and judges; no API key.

Advisory positive prose signals (cadence, verb-energy, concreteness, curiosity, analogy, cohesion, worked-case) plus the Hoskinson corpus style-profiler for HFR v2. Use to score a passage's liveliness or to (re)build the corpus profile. Advisory only — never a gate in phase 1.

Neurosymbolic verifier for Bermuda Verifier. Use when verifying claim sets in this domain with FOL/SMT/e-graph/Datalog reasoning. Scaffolded by neurosym-forge.

HFR v2 generator. Same in-session Russell+Feynman+Hoskinson fusion as triadic-voice, but register-routed, chassis-varied, and profile-target-driven, with an anti-copy self-check. Use when generating v2 passages for the HFR comparison. The running model is the generator; no API key.

Rewrite technical prose in Bertrand Russell's analytic style — lexical economy, logical atomism, declarative active-voice sentences, no hedging, axiomatic structure. Use when user says "apply Russell style", "rewrite in Russellian style", "tighten this prose", "remove hedging", "atomize this paragraph", "Russell pass on this draft", or asks to enforce signal density on a markdown passage. Do NOT use for marketing copy, fiction, persuasive essays, launch announcements, casual conversational drafts, or social media posts.

Sequential cross-chapter linkage review. Use when drafting chapter N to audit how it builds on chapters 1..N-1 — concept linkage, handoff seams, and spiral coherence in Paul Halmos's sense. Emits halmos-review.md + halmos-verdict.json and soft-gates the chapter via halmos_critical_count == 0. Do NOT use for logical entailment (book-thesis) or persona review (review-conductor).

Scaffold and extend ClojureScript + Rust neurosymbolic verification projects. Use when user says "scaffold a neurosymbolic project", "verify these claims with Z3", "add a rewrite rule", "ground this predicate in Rust", "extend the atomspace IR", "build a CLJS+Rust verifier", "FOL/SMT/e-graph/Datalog verifier", or mentions MeTTa-style modeling. Composes with book-knowledge to verify ledger claims. Does NOT run verification itself — the scaffolded project does, via shadow-cljs and cargo. Do NOT use for prose review (use book-review), claim ingestion (use book-knowledge), or chapter drafting (use book-compose).

Deterministic harsh review of cryptography papers under the EUROCRYPT 2022 review rubric. Dispatches ten expert-persona reviewers in parallel (game-based crypto, UC, concrete security, BFT consensus, P2P networks, TEE hardware, formal methods, applied crypto, post-quantum, economics/MEV), each filing a full A-I review form, then consolidates findings into a single ledger sorted by severity. Use when user says "review this paper to IACR standards", "Eurocrypt review of <paper>", "harsh review the EpochPoET paper", "what would a PC think of this", "run the IACR panel on <paper.pdf>". Do NOT use for prose-only style review (use book-review), chapter drafts (use book-compose), or non-cryptography papers (use review-conductor with a different panel).

Rewrite already-Russellized technical prose in Richard Feynman's voice — concrete analogy and physical intuition, conversational directness, honest curiosity, plain playful diction — without altering the argument. Use when user says "apply Feynman style", "make this click", "warm up this prose", "explain this simply", "Feynman pass on this draft", or asks to lower reading difficulty after a Russell pass. Do NOT use before russellian-style, and do NOT use for formal proofs, legal/specification text, API reference, bureaucratic boilerplate, or academic abstracts.

Neurosymbolic verifier for ADSC Clinical Verifier. Use when verifying claim sets in this domain with FOL/SMT/e-graph/Datalog reasoning. Scaffolded by neurosym-forge.

Neurosymbolic verifier for Epidemiology Verifier. Use when verifying claim sets in this domain with FOL/SMT/e-graph/Datalog reasoning. Scaffolded by neurosym-forge.

Neurosymbolic verifier for Osmotic pressure. Use when verifying claim sets in this domain with FOL/SMT/e-graph/Datalog reasoning. Scaffolded by neurosym-forge.

The sole network-touching skill of the russellian-book-suite. Wraps Scrapling 0.4.8 with arxiv, OpenAlex, Semantic Scholar HTML, and DOI adapters, plus a streaming PDF downloader. Use when you need to fetch a URL, search a paper repository, traverse a citation graph, or download a paper. Do NOT use for general scraping outside the suite — this skill is dedicated infrastructure.

Generate or rewrite prose in a fused writing voice — Bertrand Russell's analytic rigor, Richard Feynman's intuition-first warmth, and Charles Hoskinson's candor and momentum — grounded in a committed corpus of Hoskinson's real transcribed speech. Runs entirely inside the Claude session: you, the running model, ARE the generator. No API key, no external model call. Use this whenever the user wants to write, draft, generate, or rewrite something "in Charles's voice", "in Hoskinson's voice", "in the triadic voice", "in the Russell/Feynman/ Hoskinson blend", or asks for a post, essay, explainer, announcement, or passage in that style — even if they don't name the skill. Also use when the user wants pure-Hoskinson voice on its own. Do NOT use for generic marketing copy, unrelated authors, or code.

Write or revise mathematical and protocol prose for IACR submissions (Crypto, Eurocrypt, Asiacrypt, TCC, PKC, CHES, FSE). Enforces notation discipline, iacrtrans/amsthm environment usage, and the three accepted IACR proof styles (game-based, UC-simulation, concrete-security/asymptotic). Use when user says "draft this theorem", "write the security proof", "format this protocol as a Construction", "rewrite for IACR", "fix the proof prose for Crypto submission", or asks to format definitions/lemmas/reductions. Do NOT use for marketing copy, blog posts, slide decks, or non-cryptography mathematical work.

Thread a collection of existing paragraphs toward a goal (argument, emotion, or narrative) by reordering them, writing bridges, and lightly editing seams. Use when the user has paragraphs and a goal and wants them assembled into a coherent, goal-directed whole. Bodies stay immutable. Do NOT use for drafting from scratch (no source paragraphs), for sentence-grain prose discipline (use russellian-style), or for thesis/consistency checking (use book-thesis).

Orchestrate configurable multi-persona editorial review panels over book-review. Use when user says "run the panel", "review chapter with the conductor", "run the seven-persona panel", "soft-gate this chapter via review-conductor". Loads a panel YAML config, calls book-review's dispatch primitives, applies per-persona severity gates (gating vs advisory), emits panel-review.md plus verdict.json. Do NOT use for source ingestion (use book-knowledge), prose-only style rewrites (use russellian-style), chapter drafting (use book-compose), or persona definition (use book-review).