Borrowing it
Nothing to install: this file belongs to fbabelle/PrettySeriousResearcher. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fbabelle/PrettySeriousResearcher/main/.claude/skills/research-submission/SKILL.mdgit clone --depth 1 https://github.com/fbabelle/PrettySeriousResearcherWrote 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/fbabelle/prettyseriousresearcher/research-submission)<a href="https://agentmods.dev/skills/fbabelle/prettyseriousresearcher/research-submission"><img src="https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-submission/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/fbabelle/prettyseriousresearcher/research-submission"><img src="https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-submission.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 | $0.00056 | $0.01586 |
| Opus 5 | $0.00028 | $0.00793 |
| Sonnet 5 | $0.00011 | $0.00317 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
research-submission 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 10d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research submission — from approved packet to published paper
The research-mock-review packet ends with the user's submit decision — this skill owns everything after it: executing the submission, the review cycle, camera-ready, and release. Production papers spend real effort here (multi-edition builds, supplements, response passes); an unmanaged tail loses an accepted-quality paper to a missed form, a broken anonymization, or a sloppy rebuttal.
Ground rules
- Everything outward-facing is user-confirmed before it leaves. The agent stages, verifies, and drafts; the user uploads, clicks, and sends. A submission, an arXiv post, and a rebuttal are all irreversible publications — the same autonomy inversion as
research-mock-review. - Every portal fact is re-verified against the venue's current pages (forms, field limits, deadlines change every cycle) — the recency discipline of
research-venue-selection, never recalled.
Step 1 — Execute the submission
- Rerun the audits on the exact artifact being submitted — not the working draft:
research-provenance(all RESOLVED),research-references(no UNVERIFIABLE),research-visuals(fonts/vector/Type-3), and — if multiple editions exist — a version-consistency check that shared numbers and claims match across them. - Walk the venue checklist literally: page limit (incl./excl. references — venues differ), official template, required sections (ethics/broader impact, reproducibility checklist, AI-use disclosure per the venue's policy), and for double-blind an anonymization sweep: author names, acknowledgements, funding, repo/dataset links, self-revealing citation phrasing ("we showed [12]" → "[12] showed"), and PDF metadata (author fields survive compilation — check them).
- Package the supplement separately when the venue splits main paper from supplementary (appendix overflow, extra ablations, code zip) — each side self-contained, cross-references stated as "see supplementary §X".
- Artifact / code release: double-blind review → an anonymized mirror (e.g. an anonymous-repo service) with an install + one-command-reproduces-the-headline-table README; acceptance → public repo + archival DOI (e.g. Zenodo). License stated; data availability consistent with the licenses recorded at experiment time (
docs/local-env.md; finance data perresearch-finance-rigor). - Stage the portal fields (OpenReview / CMT / EasyChair): draft every form field — title, abstract (portal field limits differ from the paper's abstract), keywords, COI/conflicts — into
docs/submission/<venue>-form.mdfor the user to paste and confirm. - arXiv (when the Phase-1 arXiv-vs-double-blind reconciliation says post): category, license selection, and the processor-matched, preview-verified LaTeX source from
research-writing's submission build (arXiv recompiles the source — the PDF alone is not a submission). Mind the announcement schedule if timing/priority matters. - Record it: submission date + venue + edition tag in the changelog; the fee as a
publicationcost row (research-tracking); the decision ETA intostate.json.target_submission_datecontext.
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.
- 10d ago First seen · 56 lines · 56 tokens per session scan A 2394f0b7a0ab
research-submission is a skill published in the GitHub repository fbabelle/PrettySeriousResearcher (2 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 1,586 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…