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 appleweiping/WEIPING_WIKI --skill research-refinegit clone --depth 1 https://github.com/appleweiping/WEIPING_WIKIWrote 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/appleweiping/weiping_wiki/research-refine)<a href="https://agentmods.dev/skills/appleweiping/weiping_wiki/research-refine"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/research-refine/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/appleweiping/weiping_wiki/research-refine"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/research-refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.00836 |
| Opus 5 | $0.00036 | $0.00418 |
| Sonnet 5 | $0.00015 | $0.00167 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
research-refine 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 9d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Refine
Transform a raw research idea into a publication-ready research question. This is where most bad papers die — skip nothing.
Decision Gate
Before running:
- Is there a raw idea or direction to refine? (If not, run idea-discovery first)
- Is the target venue clear? (NeurIPS/ICML/ICLR oral level)
- Do you have access to the project's
refine-logs/directory?
Phase 1 — Problem Decomposition
Break the idea into atomic claims:
- State the core claim in one sentence: "We show that X improves Y by doing Z"
- Identify the gap: What existing work fails to do? Why?
- Novelty check: Is this a new problem framing (required) or just A+B stitching (forbidden)?
- Scope the contribution: Theory? Method? System? Empirical finding?
Output: refine-logs/CLAIM_DECOMPOSITION.md
Phase 2 — Literature Stress Test
Kill the idea before it kills your time:
- Search for prior art that already solves this (or claims to)
- Find the 3 closest papers — read abstracts + methods
- Differentiation matrix: For each close paper, state exactly how your approach differs
- Kill argument: Write the strongest reviewer objection. If you can't refute it, pivot.
Quality check: If differentiation from closest work is < 1 fundamental insight, STOP and reformulate.
Output: refine-logs/LITERATURE_STRESS_TEST.md
Phase 3 — Feasibility Assessment
- Data: What datasets? Available? Size sufficient for statistical significance (20+ seeds)?
- Compute: GPU hours estimate. Can you run full experiments on available hardware?
- Baselines: List 8+ baselines (minimum per quality standards). Are implementations available?
- Timeline: Weeks to first meaningful result? Weeks to full paper?
- Risk factors: What could make this impossible? (data access, compute, theoretical dead-end)
Quality check: If any risk factor has >30% probability of blocking, define a pivot plan.
Output: refine-logs/FEASIBILITY.md
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.
- 9d ago First seen · 77 lines · 73 tokens per session scan A 0fdb833f079f
research-refine is a skill published in the GitHub repository appleweiping/WEIPING_WIKI (122 stars, last pushed 14d ago), licensed MIT. It adds 73 tokens to every session and 836 once invoked, about $0.0004 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
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…