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 journal-recommendergit 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/journal-recommender)<a href="https://agentmods.dev/skills/yujie-jason-zhang/polish_skill/journal-recommender"><img src="https://agentmods.dev/badge/skills/yujie-jason-zhang/polish_skill/journal-recommender/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/journal-recommender"><img src="https://agentmods.dev/badge/skills/yujie-jason-zhang/polish_skill/journal-recommender.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 53 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00211 | $0.04608 |
| Opus 5 | $0.00105 | $0.02304 |
| Sonnet 5 | $0.00042 | $0.00922 |
| Haiku 4.5 | $0.00021 | $0.00461 |
Grade A, and why
journal-recommender 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Journal Recommender
Scope
Use this skill when the manuscript is finished or nearly finished and the user needs to choose where to submit it: a target-journal shortlist, a fit check for a specific journal, a comparison across SCI/non-SCI, open-access/subscription, or Chinese/English options, or a realistic read on which journals a paper's level can support.
Read references/journal_recommendation_guide.md for the full intake question bank, the source-authority table, the fit-rationale and adjustment templates, the predatory/early-warning red flags, and the output template before producing a full recommendation. For a single-journal fit check, the rules below are enough.
Use another skill when the task is primarily:
- estimating whether the underlying idea is novel or strong enough to publish at all, before venue choice: use
idea-novelty-auditor(if available). Reuse its level read here rather than re-deriving it; - literature review, related work, or reference selection: use
problem-driven-literature-review(if available); - manuscript storyline, contribution framing, or section structure: use
paper-argument-reconstructor(if available); - drafting the cover letter once a target journal is chosen: use
paper-cover-letter(if available). This skill runs before the cover letter; - TeX-safe or final-language polishing: use
paper-polisher(if available).
This skill matches a manuscript to venues. It does not judge whether the science is correct, and it does not write the submission letter.
Verification Mode
This skill has two modes. By default it produces a recommendation as described above. When the input is a journal shortlist or a fit claim another tool, advisor, or skill has already produced, switch to verification mode instead of regenerating:
- do not overwrite the other source's list;
- check it against this skill's discipline: does each journal actually match the stated scope and the paper's level; does recent related-paper evidence support the scope fit; are indexing, open-access, APC, metric, and review-speed claims asserted as fact when they should be flagged; is any journal on an early-warning list or showing predatory red flags; is the paper's level over-estimated so that "reach" is really "unrealistic";
- report only the problems; correct one in place only if it breaks a non-negotiable rule (an asserted-as-fact metric, a predatory venue, or an early-warning-listed journal).
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 · 184 lines · 211 tokens per session scan A 29d60ba17e4e
journal-recommender is a skill published in the GitHub repository yujie-jason-zhang/polish_skill (18 stars, last pushed 1mo ago), licensed MIT. It adds 211 tokens to every session and 4,608 once invoked, about $0.0011 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…