Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add yujie-jason-zhang/polish_skill --skill idea-novelty-auditorgit clone --depth 1 https://github.com/yujie-jason-zhang/polish_skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yujie-jason-zhang/polish_skill/idea-novelty-auditor)<a href="https://agentmods.dev/skills/yujie-jason-zhang/polish_skill/idea-novelty-auditor"><img src="https://agentmods.dev/badge/skills/yujie-jason-zhang/polish_skill/idea-novelty-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yujie-jason-zhang/polish_skill/idea-novelty-auditor"><img src="https://agentmods.dev/badge/skills/yujie-jason-zhang/polish_skill/idea-novelty-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00110 | $0.00944 |
| Opus 5 | $0.00055 | $0.00472 |
| Sonnet 5 | $0.00022 | $0.00189 |
| Haiku 4.5 | $0.00011 | $0.00094 |
Grade A, and why
idea-novelty-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Novelty Auditor
Scope
Use this skill when the user asks whether a research idea is novel, defensible, worth writing, how to position it, what baselines may invalidate it, how reviewers may attack it, what claims should be avoided, or what experiments are required before packaging.
For a full audit, read references/idea_novelty_risk_audit.md.
Use another skill when the task is primarily:
- literature review, related work, reference selection, citation-role assignment, or direct-competitor coverage after the idea boundary is known: use
problem-driven-literature-review(if available); - manuscript structure or section rewriting after the defensible claims are known: use
paper-argument-reconstructor(if available); - TeX-safe academic English polishing: use
paper-polisher(if available). - auditing an existing experiment section or concrete experiment plan against fixed claims, ablations, resource constraints, and results narration: use
experiment-section-auditor(if available).
If the user asks for "packaging" before novelty has been checked, run the novelty-risk audit first.
Verification Mode
This skill has two modes. By default it audits as described above. When the input is a positioning, claim, or contribution statement another tool or skill has already drafted, switch to verification mode instead of re-auditing from scratch:
- do not overwrite the other tool's wording;
- check it against this skill's discipline: whether novelty is overstated, whether a dangerous baseline was missed, and whether any claim is stronger than the evidence allows;
- report only the deviations; tighten an overclaim in place only if it breaks the evidence discipline.
The suite's value is bounded, defensible claims, not a competing rewrite. Verify rather than replace what a stronger generator already produced.
Core Principle
Audit before packaging:
break it down -> compare with known paradigms -> identify dangerous baselines -> define what cannot be claimed -> define cautious claims -> design evidence -> then package the paper story
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 121 lines · 110 tokens per session scan A 64c6674b1f14
idea-novelty-auditor is a skill published in the GitHub repository yujie-jason-zhang/polish_skill (18 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 944 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
systems-paper-writing
Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.
overleaf
Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.
paperjury
A tool for reviewing and editing computer-science conference papers in LaTeX or Markdown, the document formats commonly used for research papers. It supports direct edits, structured pre-submission review, and an optional unattended mode for selected fixes.
parallel-subagents
When a task decomposes into independent slices — separate files, OR separate sections of ONE file — fan it out: write job files to the subagent queue and the host runs real parallel Codex workers for you. For a single file, extract per-section slice files into the queue's work/ zone, let workers polish them in…