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 Haohaha-11/Paper-Writing --skill research-problem-framergit clone --depth 1 https://github.com/Haohaha-11/Paper-WritingWrote 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/haohaha-11/paper-writing/research-problem-framer)<a href="https://agentmods.dev/skills/haohaha-11/paper-writing/research-problem-framer"><img src="https://agentmods.dev/badge/skills/haohaha-11/paper-writing/research-problem-framer/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/haohaha-11/paper-writing/research-problem-framer"><img src="https://agentmods.dev/badge/skills/haohaha-11/paper-writing/research-problem-framer.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 | $0.00000 | $0.01714 |
| Opus 5 | $0.00000 | $0.00857 |
| Sonnet 5 | $0.00000 | $0.00343 |
| Haiku 4.5 | $0.00000 | $0.00171 |
Grade A, and why
research-problem-framer 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Problem Framer
Purpose
Evaluate and sharpen candidate research problems before method design, using a falsifiable problem-first rubric rather than a solution-first idea list.
When To Use
Use this skill after an initial literature scan and before investing in method design or full experiments. It is especially useful when there are several possible ideas and the project needs to decide which problem to lock, revise, or kill.
Inputs
- Frontier problem map from
research-scout. - Candidate problem list.
- Closest papers and preliminary observations.
- User assets and constraints.
- Possible decisive tests or pre-experiments.
Procedure
- Convert each candidate into a one-line contradiction.
- Score each candidate from 0 to 3 on all rubric dimensions.
- Reject or revise candidates with any critical dimension below 2.
- Require at least one score of 3 in violated assumption, falsifiability, or novelty boundary before recommending a primary direction.
- Build an idea bank using
examples/idea-bank-template.md. - Build a candidate comparison table.
- Write the problem statement, novelty boundary, and non-claim for the best candidate.
- Design a falsification sprint before method design.
- Apply provenance gates: unchecked observations cannot become paper claims.
- Run multi-perspective critique from closest-work, feasibility, mechanism, reviewer-attack, venue-fit, and domain/ethics perspectives.
- Anticipate reviewer attacks and map each one to a control, baseline, or wording boundary.
Candidate Scoring Rubric
Score each dimension from 0 to 3.
| Dimension | 0 | 1 | 2 | 3 |
|---|---|---|---|---|
| Violated assumption | No assumption | Minor practice | Recognizable default | Central field belief |
| Surprise | Expected | Mildly interesting | Non-obvious | Strong reversal or paradox |
| Falsifiability | No direct test | Expensive/ambiguous | Feasible test | Simple decisive diagnostic |
| Consequence | Local metric | One model/task | Several settings | Changes evaluation or workflow |
| Novelty boundary | Already solved | Crowded/incremental | Clear residual gap | Distinct unresolved question |
| Mechanism | Pure speculation | Generic story | Testable explanation | Competing mechanisms separable |
| Breadth | Single run | Single dataset | Multiple conditions | Stable across meaningful regimes |
| Resource fit | Infeasible | Major missing assets | Feasible | Unusually enabled by user assets |
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 · 181 lines · 0 tokens per session scan A fb61aa57df9a
research-problem-framer is a skill published in the GitHub repository Haohaha-11/Paper-Writing (3 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,714 tokens. 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…