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 Geek96/paper-research-skill --skill paper-wikigit clone --depth 1 https://github.com/Geek96/paper-research-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/geek96/paper-research-skill/paper-wiki)<a href="https://agentmods.dev/skills/geek96/paper-research-skill/paper-wiki"><img src="https://agentmods.dev/badge/skills/geek96/paper-research-skill/paper-wiki/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/geek96/paper-research-skill/paper-wiki"><img src="https://agentmods.dev/badge/skills/geek96/paper-research-skill/paper-wiki.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 | $0.00087 | $0.03292 |
| Opus 5 | $0.00044 | $0.01646 |
| Sonnet 5 | $0.00017 | $0.00658 |
| Haiku 4.5 | $0.00009 | $0.00329 |
Grade A, and why
paper-wiki 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 11d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Wiki (Karpathy Style)
Philosophy
Karpathy's writing style is the model: intuition before formalism, concrete before abstract, honest about what's new vs. borrowed. A good wiki entry reads like a smart friend explaining a paper over coffee — not an abstract. Every concept earns its place by connecting to something the reader already knows.
This skill produces two kinds of output that compound over time:
- Paper pages (
Wiki/Papers/) — deep chapter-by-chapter breakdowns of each paper - Concept entries (
Wiki/Concepts/) — standalone deep dives into methods, terms, and phenomena, augmented each time a new paper touches them
Running this on 5 papers produces a small wiki. Running on 50 produces a rich, interconnected knowledge graph.
Visual Design System
All wiki pages use a consistent visual language optimized for Obsidian reading experience:
Frontmatter (Dataview Integration)
Every paper and concept page includes structured YAML frontmatter for Dataview queries. This enables automatic indexing, filtering, and dashboard generation.
Callout Types
Use Obsidian callouts to highlight key sections:
| Callout | Usage | Example |
|---|---|---|
> [!abstract] |
TL;DR / one-line summary | Paper and concept summaries |
> [!success] |
Key Findings / positive results | Findings with evidence |
> [!warning] |
Critical questions / limitations | "What I'd Question" sections |
> [!tip] |
Practical advice / adoption | Adoption Guide, "When to Use" |
> [!info] |
Prerequisites / context | Background knowledge needed |
> [!example] |
Concrete examples / case studies | Task examples, data instances |
> [!danger] |
Safety concerns / red flags | Medical safety, data leakage risks |
Emoji Section Headers
Use emoji sparingly but consistently as visual anchors:
| Emoji | Section |
|---|---|
| 🎯 | Why This Exists / Motivation |
| 📋 | Quick Reference / Overview |
| 🔬 | Method / Architecture / Task Definitions |
| 📊 | Results / Baseline / Performance |
| 💡 | Key Findings / Insights |
| ⚠️ | What I'd Question / Limitations |
| 🧩 | Key Concepts |
| 🔗 | Related Papers |
| 🛠️ | Adoption Guide / Practical |
| 📦 | Dataset Construction |
| 📐 | Evaluation Framework |
| 🗺️ | Taxonomy / Framework (surveys, frameworks) |
| 🏗️ | Architecture (technical reports) / The Framework (frameworks) |
| 🔎 | Study Design (analyses) |
What ships with it
8 files 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.
- 11d ago First seen · 295 lines · 87 tokens per session scan A d751abe2ed88
paper-wiki is a skill published in the GitHub repository Geek96/paper-research-skill (21 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 3,292 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.