Skill Explorer

Deep manual bibliography health check — dangling \cite keys, orphan .bib entries, duplicates, malformed/placeholder DOIs, missing required fields, inconsistent author/journal formatting, and \ref↔\label integrity

Walk every substantive claim in a section, classify it (cited / author's-own / common-knowledge / UNSUPPORTED), verify the citation licenses the claim's verb and quantifier, and report supported/overstated/uncited counts

Breadth-first scan of a draft for unsupported and uncited claims and missing-evidence gaps — classify every claim, list what is UNCITED/UNSUPPORTED, and for true gaps emit search directions (keywords, venues, citation-chaining), never a fabricated source

Assess a manuscript's fit to a target journal/venue — scope, novelty bar, length & structure limits, reference style (ACS/IEEE/APA/Nature), audience, article types — and output a fit score with reasoning and a prioritized gap list

Reproducibility check of the Method(s) section against agent_docs/reproducibility.md — enumerate what an independent team needs to rerun the work, check the section, and flag every missing ingredient as a pass/GAP checklist

Aggregate reports/session-audit.log (one JSON line per session, written by the SessionEnd hook) into a per-session table plus a windowed summary — citation-gate pass rate, which guardrail hooks fired, SKIP_QUALITY_GATE bypasses, and session durations. Pure telemetry; flags trends, does not judge process.

Run the agent_docs/statistics.md checklist over a Results section — flag bare p-values, missing N/effect-size/CI, causal overclaim on observational data, multiple-comparison issues, and numbers that disagree across text/tables/abstract

Draft or tighten the abstract as a contract — every number and claim in it must appear identically in the body, within the venue's word limit, calibrated to what the paper actually shows

Draft a concise, honest editor cover letter from MANUSCRIPT_MAP — states the contribution, fit to the venue, and required declarations, with no fabricated significance or invented metrics

Synthesize a related-work / literature-review section from the project's OWN library (references.bib + sources/ + vault) — thematic, gap-driven, calibrated, real citations only. Proposes concrete search directions for gaps without fabricating a single source.

End-to-end orchestrator — runs the whole CLAUDE.md research lifecycle for a section or manuscript as one command (outline → ground → draft → verify → review → revise), halting on any gate failure.

Turn a thesis + target venue into a claim-driven IMRaD outline — each section is the one claim it establishes plus the evidence needed and a word budget — ready for MANUSCRIPT_MAP.md, flagging evidence missing from the library

Run a full simulated peer review — dispatch the peer-reviewer and integrity-reviewer agents over the manuscript, dedupe their findings, and produce a referee report with a recommendation. Pre-empt Reviewer 2 before submission

Draft a lay / plain-language summary for a general audience, funder, or a journal's required PLS — accessible to a non-specialist without distorting the science, with a claim-by-claim fidelity check against the paper

Convert or normalize the bibliography's citation style via the toolchain (biblatex/biber, CSL via pandoc, bibtex .bst) — deterministic, presentation-only, never altering the underlying facts and never inventing a missing field

Draft a point-by-point response letter — quote each reviewer comment, state the change made and its exact location, stay courteous, and NEVER claim a change not actually made. Produces the letter plus an edit checklist, logging recurring critiques to tasks/reviews/

Windowed retrospective on the writing process — what shipped (sections drafted, commits over the window), recurring reviewer critiques (tasks/reviews/ by applies_to frequency), what was learned (journal findings folded into handoffs), and what is still open (tasks/todo.md). Saves a timestamped retro to tasks/ as persistent history. Process, not telemetry.

Pre-submission review battery — runs the peer-reviewer, integrity-reviewer, and fact-checker agents plus the deterministic audits in parallel over the whole manuscript, dedupes, confidence-gates, and saves one go/no-go report.

Append a timestamped tagged line (finding / decision / summary) to the session journal at .hook-state/session-journal.md, so a discovered fact, a settled choice, or a transient breadcrumb survives context compaction in a long writing session. Delegates to scripts/note.sh.

Surface dormant reviewer-feedback notes from tasks/reviews/ (and _archive/) whose applies_to topics match the current task, returning POINTERS ONLY — paths plus frontmatter, never bodies. Recovers a past reviewer rule relevant to the work at hand without bloating Tier-1 boot. Delegates the deterministic scan and scoring to scripts/review-resurface.sh.

A short "since last time" briefing from vault/log.md + vault/index.md — recently ingested sources, open follow-ups and citation-chaining leads, and gaps relative to MANUSCRIPT_MAP.md → Thesis (themes the argument needs that the library lacks). Read-only; outputs a tight briefing whose gaps become search directions for /literature-review. Never fabricates a source to fill a gap.

Ingest ONE raw source (a sources/ PDF or .txt path, or pasted text) into the Literature Vault — read it, write a vault/summaries/<bibkey>.md annotated page with claims+locators and verbatim quotes, propose a references.bib entry extracted FROM the document (never fabricated), cross-reference concepts/entities, and update index + log. Never modifies sources/; flags uncertain metadata as [VALUE — verify].

Health-check the Literature Vault — find cross-source contradictions, orphan pages (a summary with no matching references.bib key, or a .bib key with no summary), broken [[wikilinks]], claims missing locators, metadata-only pages never upgraded, stale entries, and quotes without page numbers. Read-only/advisory — reports a categorized findings list with fixes; never edits sources or auto-rewrites the vault.