wanshuiyin/Auto-claude-code-research-in-sleep
Plugin Claude Code
Bundles 84 skills, 1 command · 5,875 tokens together
ARIS research workflow as a Claude Code plugin: literature review, idea discovery, experiments, paper writing, rebuttal, slides — with a cross-model Codex reviewer. Run /aris:setup once after installing.
Skill Claude Code needs its repo
Generate a fact-checked academic personal homepage from a CV, optionally augmented by an existing manual homepage and an assets directory. Produces editable structured source files (profile.yml + publications.bib + bio.md + news.md) and a single-file HTML page. Uses Codex MCP for independent factual review against…
Skill Claude Code
Render an ARIS Markdown / JSON artifact (IDEAREPORT, AUTOREVIEW, KILLARGUMENT, PAPERPLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Academic template outputs are gated by a fresh cross-model Codex review for render fidelity + safety (the ARIS invariant). Use when the user says…
Skill Claude Code
Synthesize the single strongest EVIDENCE-BOUND reviewer case to reject a paper, built ONLY from the evidence ledger (claims.json) + the other auditors' confirmed findings — never free-floating LLM critique. Two fresh cross-model codex threads: an attack writes the 200-word rejection paragraph (every accusation tagged…
Skill Claude Code
Transparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a deterministic defensive-hedge density screen (tools/checkaistyle.py, AIS-DEFENSIVE-HEDGE) plus a fresh cross-model GROSS-cases-only semantic pass over the 13 AIS- style tells (broken narrative arc, LLM…
Skill Claude Code
Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent…
Skill Claude Code
Citation-integrity forensics: is every reference real, correctly attributed, and used in a context the cited work actually supports? Catches hallucinated references (no paper at the claimed arXiv id/DOI/venue, fabricated authors/year), metadata drift (wrong year/venue/version), and wrong-context citations (a real…
Skill Claude Code
Flagship intra-paper self-consistency forensics: does the paper contradict ITSELF across abstract/intro/tables/body/appendix, and does the method DESCRIBED match the method EVALUATED? Needs no external ground truth — works PDF-only (L0). Runs a deterministic arithmetic pass + a fresh cross-model semantic pass, every…
Skill Claude Code
Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan…
Skill Claude Code
Build the deterministic evidence ledger (artifactmanifest.json + claims.json) that every other Anti-Autoresearch auditor reads. One pass inventories artifacts, derives the observability level (L0 PDF-only / L1 +LaTeX / L2 +repo+results) by fixed rule, and extracts span-anchored, hashed, checkable claims (numbers…
Skill Claude Code
Audit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, verified-scope…
Skill Claude Code
MEMO-ONLY prior-work overlap advisory: surfaces the two ADVISORY taxonomy signals neither a tool nor a model can decide from the paper alone — ADV-TRIVIAL-COMBINATION (standard A+B+C / 缝合 stapling) and ADV-DUPLICATE-PUBLICATION (repackaged / duplicate submission). The executor RETRIEVES candidate prior work (DBLP…
Skill Claude Code
Checkable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover pipeline/template strings, too-few or LLM-looking figures, and page-padding. AUXILIARY ONLY and weak by design: a deterministic pass (tools/checkpresentation.py — dup-table + pipeline-artifact) plus a fresh…
Skill Claude Code
Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation …
Skill Claude Code
End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output). Orchestrates the whole pipeline: ingest (arxiv-id | pdf | dir → working dir + pdftotext for L0) → /evidence-ledger (artifact manifest + observability level L0/L1/L2 + span-anchored claims.json) →…
wanshuiyin/ARIS-Movie-Director
Skill Claude Code needs its repo
Phase-1 (S4) of a comic movie — PRODUCE the canonical reusable references the whole spiral conditions on. Per asset it bakes ONE canonical 1:1 white-bg identity ref via the agent mcpcodexcodex sidecar bake (Codex native imagegen — conditioned, never hand-pasted) OR, for a deterministic motif…
wanshuiyin/ARIS-Movie-Director
Skill Claude Code needs its repo
Phase-1 (S5) UPSTREAM ref-asset gate — the bounded cross-model adversarial loop that LOCKS one reusable identity-locked asset (character sheet / location plate / prop cutout / text-panel / logo-free symbol) BEFORE it can be composited into any panel. This is NOT the panelgate (composed-output) or the assemblygate…
wanshuiyin/ARIS-Movie-Director
Skill Claude CodeCodex needs its repo
Phase 1 ORCHESTRATOR of a movie/comic — turn a fuzzy story idea into the Authored Source of Truth (a schema-valid comic.json + its locked asset library) by driving the detailed author skills in order (intent → style → outline → storyboard → assets → blueprints → prompts → comic.json), each gated by…
wanshuiyin/ARIS-Movie-Director
Skill Claude CodeCodex
Phase-1 comic-author step (post-final eval) — a DOUBLE-BLIND A/B of two FINAL whole comics: our cross-model-audited progressive render (the comic-author + comic-director output) vs a naive single-shot baseline. A single sealed coin-flip hides which is which; two cross-model reviewers (Codex + Gemini) score both on a…
wanshuiyin/ARIS-Movie-Director
Skill Claude CodeCodex
Phase-1 (S7 of the comic-author suite) — turn ONE locked panelspec into a deterministic content-SVG blueprint that becomes the bake condition (reference #1 of the agent mcpcodexcodex sidecar bake), by WRITING A PYTHON GENERATOR (never raw SVG in chat — LLMs botch coordinates). The HEADLINE comic-pivot rule: the image…
wanshuiyin/ARIS-Movie-Director
Skill Claude CodeCodex
The authoring-side DIEGETIC continuity AUDIT — it produces the world-state evidence that comic-cross-layer-gate --gate continuity adjudicates against the storyboard's MOTIF STATE TABLE (motifledger). It checks each baked panel STRICTLY against the pre-committed table row, then emits a continuity review-node the gate…
wanshuiyin/ARIS-Movie-Director
Skill Claude CodeCodex needs its repo
The ONE parameterized score-fuser for EVERY comic-author authoring gate — --gate intent|outline|asset|storyboard|blueprint|continuity|p0proof|compile. A single fuser (not a per-layer split) prevents drift. It NEVER re-runs a reviewer; it collects the reviewer score-nodes already on the wiki (via reviews edges), fuses…
wanshuiyin/ARIS-Movie-Director
Skill Claude CodeCodex
Phase 2/3 of a movie — bake + cross-model-verify a movie from an authored comic.json. Per frame: render the content-SVG blueprint, bake via the agent mcpcodexcodex sidecar, gate with a 3-reviewer cross-model panel (narrative [currently the codex CLI] ‖ Gemini visual ‖ Codex visual, deterministic fuse)…
wanshuiyin/ARIS-Movie-Director
Skill Claude CodeCodex
Phase-1 Layer-0 of the comic-author suite — turn ANY raw idea / a locked video skeleton / an audience note into ONE schema-valid intentspec node that fixes the logline (an editorial climax), the tagline, and the named DUAL-IDENTITY design constraint the whole comic optimizes against. Codex-as-parser (raw bytes +…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: