GitHub user
Agent skills by wanshuiyin
- skills
- 33
- repositories
- 3
Repositories by wanshuiyin
- Auto-claude-code-research-in-sleepARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.17k stars · 25 skills
- Anti-AutoresearchDon't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.160 stars · 5 skills
- ARIS-in-AI-OfferBilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱574 stars · 3 skills
Skills by wanshuiyin, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). | wanshuiyin/ | 574 | 1 repo | ~3.4k | Automated safety check: Notes | MIT | yesterday |
| 2 | Builds an academic conference poster as a single HTML and CSS file with measurement-based gates, real paper figures and a print-ready PDF rendered through headless Chromium. | wanshuiyin/ | 17k | 1 repo | ~4.5k | Automated safety check: Notes | MIT | today |
| 3 | Runs a mathematical proof project as a stateful pipeline of run directories: a local attempt first, then a manual GPT Pro handoff package, with an optional DeepSeek audit. | wanshuiyin/ | 17k | 1 repo | ~4.7k | Automated safety check: Pass | MIT | today |
| 4 | Render an ARIS Markdown / JSON artifact (IDEAREPORT, AUTOREVIEW, KILLARGUMENT, PAPERPLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. | wanshuiyin/ | 17k | 1 repo | ~5.4k | Automated safety check: Notes | MIT | today |
| 5 | Generate a fact-checked academic personal homepage from a CV, optionally augmented by an existing manual homepage and an assets directory. | wanshuiyin/ | 574 | — | ~4.8k | Automated safety check: Notes | MIT | yesterday |
| 6 | Render an ARIS Markdown / JSON artifact (IDEAREPORT, AUTOREVIEW, KILLARGUMENT, PAPERPLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. | wanshuiyin/ | 574 | — | ~4.9k | Automated safety check: Notes | MIT | yesterday |
| 7 | Audit experiment integrity before claiming results. An agent skill from wanshuiyin/Auto-claude-code-research-in-sleep. | wanshuiyin/ | 17k | 1 repo | ~2.7k | Automated safety check: Notes | MIT | today |
| 8 | Run the Anti-Autoresearch integrity-forensics DETERMINISTIC slice (numeric core + rules-only reporter) against a paper via a SHA-pinned thin launcher, then convert the verdict into a typed policy… | wanshuiyin/ | 17k | 1 repo | ~1.5k | Automated safety check: Pass | MIT | today |
| 9 | 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… | wanshuiyin/ | 160 | — | ~11k | Automated safety check: Notes | MIT | yesterday |
| 10 | Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). | wanshuiyin/ | 17k | 1 repo | ~3.3k | Automated safety check: Notes | MIT | today |
| 11 | Citation-integrity forensics: is every reference real, correctly attributed, and used in a context the cited work actually supports? | wanshuiyin/ | 160 | — | ~12k | Automated safety check: Notes | MIT | yesterday |
| 12 | 12.Meta Apply Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved, with a fresh landing review and human approval. | wanshuiyin/ | 17k | 1 repo | ~2.1k | Automated safety check: Notes | MIT | today |
| 13 | 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? | wanshuiyin/ | 160 | — | ~10k | Automated safety check: Notes | MIT | yesterday |
| 14 | Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. | wanshuiyin/ | 17k | 1 repo | ~3.5k | Automated safety check: Notes | MIT | today |
| 15 | Build the deterministic evidence ledger (artifactmanifest.json + claims.json) that every other Anti-Autoresearch auditor reads. | wanshuiyin/ | 160 | — | ~11k | Automated safety check: Notes | MIT | yesterday |
| 16 | Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and… | wanshuiyin/ | 17k | 1 repo | ~3.7k | Automated safety check: Pass | MIT | today |
| 17 | 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… | wanshuiyin/ | 160 | — | ~13k | Automated safety check: Notes | MIT | yesterday |
| 18 | 18.Wiki Enrich Fill in the per-paper TODO sections of research-wiki/papers/<slug.md pages that literature-ingest skills leave as bare scaffolds. | wanshuiyin/ | 17k | 1 repo | ~4.1k | Automated safety check: Notes | MIT | today |
| 19 | Plans the ablation studies a paper needs after main results support its claim: Codex designs them like a reviewer, Claude Code checks feasibility and runs them. | wanshuiyin/ | 17k | — | ~1.3k | Automated safety check: Notes | MIT | today |
| 20 | Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong… | wanshuiyin/ | 17k | 1 repo | ~7.7k | Automated safety check: Notes | MIT | today |
| 21 | Rigorous mathematical proof verification and fixing workflow. | wanshuiyin/ | 17k | 1 repo | ~7.3k | Automated safety check: Notes | MIT | today |
| 22 | Audit experiment integrity before claiming results. An agent skill from wanshuiyin/Auto-claude-code-research-in-sleep. | wanshuiyin/ | 17k | — | ~3.2k | Automated safety check: Notes | MIT | today |
| 23 | Run the Anti-Autoresearch integrity-forensics sweep (span-anchored evidence ledger → GPT auditors propose findings → a rules-only reporter that lists every proposal with what the auditor said about… | wanshuiyin/ | 17k | — | ~4.2k | Automated safety check: Notes | MIT | today |
| 24 | Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. | wanshuiyin/ | 17k | — | ~5.4k | Automated safety check: Notes | MIT | today |
| 25 | 25.Meta Apply Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved — the ONLY skill permitted to mutate the skill corpus from a self-modification proposal, with cross-model jury… | wanshuiyin/ | 17k | — | ~2k | Automated safety check: Notes | MIT | today |
| 26 | 26.Paper Poster DEPRECATED — superseded by /paper-poster-html. An agent skill from wanshuiyin/Auto-claude-code-research-in-sleep. | wanshuiyin/ | 17k | 1 repo | ~206 | Automated safety check: Pass | MIT | today |
| 27 | Rigorous mathematical proof verification and fixing workflow. | wanshuiyin/ | 17k | — | ~14k | Automated safety check: Notes | MIT | today |
| 28 | Build a working artifact from a plain "implement X for me" request: a running end-to-end spine first, then one feature per rung, with every under-determined decision written to an assumption ledger… | wanshuiyin/ | 17k | — | ~7.8k | Automated safety check: Notes | MIT | today |
| 29 | Build a working artifact from a plain "implement X for me" request: a running end-to-end spine first, then one feature per rung, with every under-determined decision written to an assumption ledger… | wanshuiyin/ | 17k | — | ~5.3k | Automated safety check: Notes | MIT | today |
| 30 | Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. | wanshuiyin/ | 17k | 1 repo | ~6.9k | Automated safety check: Warn | MIT | today |
| 31 | Workflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. | wanshuiyin/ | 17k | 1 repo | ~13k | Automated safety check: Warn | MIT | today |
| 32 | Full end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. | wanshuiyin/ | 17k | 1 repo | ~5.8k | Automated safety check: Warn | MIT | today |
| 33 | Autonomous multi-round research review loop. An agent skill from wanshuiyin/Auto-claude-code-research-in-sleep. | wanshuiyin/ | 17k | — | ~17k | Automated safety check: Warn | MIT | today |
Questions, answered from the data.
What is the best skill by wanshuiyin?
Interview Cheatsheet from wanshuiyin/ARIS-in-AI-Offer ranks first of the 33 skills by wanshuiyin listed here, with the highest score: its repository has 574 GitHub stars, 1 other GitHub owner carry a copy, its SKILL.md loads about 3.4k tokens and it has informational notes only in the automated safety check. Next come Academic Poster Builder and Proof Run Orchestrator.
Are wanshuiyin's skills official?
None yet. All 33 skills by wanshuiyin listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.