PrettySeriousResearcher: Skill for Claude Code

.claude/skills/research-topic-selection/SKILL.md

research-topic-selection is a skill for Claude Code from fbabelle/PrettySeriousResearcher. It costs 57 tokens per session (2,264 once invoked), scanned A, original, Apache-2.0.

A first-phase research workflow for choosing and narrowing a paper topic. It examines existing work, looks for a gap, and creates research questions, hypotheses, and a paper outline.

In plain words
What is it for?
Starting or reframing research in AI or finance, comparing possible topics, checking novelty, and producing an initial paper skeleton.
Why use it?
It helps prevent spending time on a topic that is too broad, already solved, or lacks a clear contribution.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is fbabelle/PrettySeriousResearcher's own configuration. It tells Claude Code how to work on PrettySeriousResearcher itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything PrettySeriousResearcher configures →

Part of the research-paper-skills plugin — 17 skills shipped together

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/fbabelle/PrettySeriousResearcher/main/.claude/skills/research-topic-selection/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fbabelle/PrettySeriousResearcher

Made for: Claude Code.

Or install research-paper-skills, the plugin that ships this one along with the rest of its 17 skills.

Wrote 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.

agentmods badge for research-topic-selection

README.md
[![agentmods](https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-topic-selection.svg)](https://agentmods.dev/skills/fbabelle/prettyseriousresearcher/research-topic-selection)
Your own site
<a href="https://agentmods.dev/skills/fbabelle/prettyseriousresearcher/research-topic-selection"><img src="https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-topic-selection.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,264 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.02264
Opus 5 $0.00028 $0.01132
Sonnet 5 $0.00011 $0.00453
Haiku 4.5 $0.00006 $0.00226

Measured yesterday against content hash 6942a26d8f98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

research-topic-selection 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 yesterday.

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.

.claude/skills/research-topic-selection/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 1 — Topic research, selection & skeleton

The most leveraged phase: a well-chosen, well-scoped topic with a defensible gap is worth more than any later cleverness. Output of this phase is a confirmed topic + direction, a novelty/gap claim, and a paper skeleton.

Step 1 — The two-direction interview (hard stop; do not skip)

Before any investigation, confirm scope with the user. These answers shape everything downstream — never assume them:

  • Domain & sub-area (e.g. LLM agents for financial QA; portfolio optimization; time-series forecasting; market-microstructure RL; risk/factor models).
  • Target problem(s) — the specific pain or open question.
  • Expected outcome — a new method/system, or an analysis/understanding result?
  • Improve vs challenge — patch/extend existing systems, or test/break a prevailing thesis?
  • Direction (a) vs (b):
    • (a) Algorithm/technical — push the field: new architecture, mechanism, or thesis (think Attention Is All You Need, ResNet, MoE). Demands deep, comprehensive investigation before any claim. Higher risk, higher novelty.
    • (b) Experimental/analytical — survey, benchmark, replication, ablation/variation study, limitation analysis, or parameter refinement of existing systems. Lower invention, high rigor and interpretation.
  • Venue & length target (sets the bar and the skeleton): NeurIPS/ICML/ICLR/AAAI/ACL; or finance venues — Journal of Finance, RFS, JFE, arXiv q-fin, SSRN; workshops vs full track. Fire research-venue-selection early to turn this into a venue profile (rubric, acceptance bar, section/length template, disclosure/anonymity rules, deadline windows) that becomes a scored input to topic choice below — the topic is picked partly for venue fit, not retrofitted to a venue later (venue-as-input).

Record the answers as the project charter (top of architecture.md). The orchestrator will not advance past this without them.

Step 2 — Broad prior-art & novelty-gap investigation (breadth)

Read the full file on GitHub · 84 lines

Changes

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.

  1. yesterday Changed · +1 lines 6942a26d8f98
  2. 6d ago First seen · 83 lines · 57 tokens per session scan A 1286e514a92d

Subscribe to this mod's changes

research-topic-selection is a skill published in the GitHub repository fbabelle/PrettySeriousResearcher (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 2,264 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens