paper-first-principles

paper-first-principles is a skill for Claude Code, Codex from Dqz00116/skill-lib. It costs 27 tokens per session (932 once invoked), scanned A, original, MIT.

A method for turning academic research papers into documentation that software engineers can understand and use. It explains the paper’s main idea, design, algorithms, and practical applications.

In plain words
What is it for?
It is for studying papers, extracting system designs or algorithms, sharing technical findings, and mapping research ideas to software projects.
Why use it?
It reduces the effort needed to translate research language into concrete engineering knowledge.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is kimi paper-first-principles paper.pdf --output ./docs/analysis.md.

Good fit It is for studying papers, extracting system designs or algorithms, sharing technical findings, and mapping research ideas to software projects.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Dqz00116/skill-lib
agentmods
npx agentmods add skills/dqz00116/skill-lib/paper-first-principles

Made for: Claude Code, Codex.

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 paper-first-principles

README.md
[![agentmods](https://agentmods.dev/badge/skills/dqz00116/skill-lib/paper-first-principles.svg)](https://agentmods.dev/skills/dqz00116/skill-lib/paper-first-principles)
Your own site
<a href="https://agentmods.dev/skills/dqz00116/skill-lib/paper-first-principles"><img src="https://agentmods.dev/badge/skills/dqz00116/skill-lib/paper-first-principles.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 932 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 $0.00027 $0.00932
Opus 5 $0.00014 $0.00466
Sonnet 5 $0.00005 $0.00186
Haiku 4.5 $0.00003 $0.00093

Measured 8d ago against content hash 6f6912b00e88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

paper-first-principles 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 8d 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.

paper-first-principles/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper First Principles

Overview

Convert academic papers into progressive, engineer-friendly documentation using first principles thinking.

When to Use

Use when:

  • You need to understand a research paper deeply from an engineering perspective
  • Extracting design patterns, system architectures, or algorithms from academic literature
  • Preparing technical knowledge sharing or documentation for engineering teams
  • Mapping theoretical research to practical software engineering applications

Don't use for:

  • Papers without clear technical contributions (survey papers, opinion pieces)
  • One-off reading without need for structured documentation
  • Standard practices already well-documented elsewhere

Quick Start

# Basic usage
kimi paper-first-principles https://arxiv.org/abs/xxxx.xxxxx

# Engineer perspective with domain focus
kimi paper-first-principles paper.pdf --audience engineer --domain distributed-systems

# Output to file
kimi paper-first-principles paper.pdf --output ./docs/analysis.md

Output Structure

Generated documents contain 8 standard sections:

Section Content Audience
Opening One-sentence core insight All
Mechanism Breakdown Comparative analysis tables Engineers, Researchers
First Principles Problem essence and design rationale All
Progressive Deep Dive Layered complexity (simple → complex) Engineers, Researchers
Edge Cases Common pitfalls and misconceptions Engineers
Decision Tree When/how to apply Engineers, Managers
Engineering Checklist Actionable verification items Engineers
Summary Reusable design patterns All

Paper Types & Progressive Paths

Type Characteristics Progressive Path
Algorithm New algorithms/models Example → Core mechanism → Optimizations
System Architecture/engineering Single-node → Distributed → Production
Theory Theoretical analysis Problem → Theorem → Proof → Application

Read the full file on GitHub · 117 lines

Files

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.

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. 8d ago First seen · 117 lines · 27 tokens per session scan A 6f6912b00e88

Subscribe to this mod's changes

paper-first-principles is a skill published in the GitHub repository Dqz00116/skill-lib (22 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 932 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

release-sync

Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.

yonatangross/orchestkit · 62 tokens

openclaw-debugger

Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger". Walks through the standard OpenClaw 2026.4 diagnosis checklist and prints a report.

mergisi/awesome-openclaw-agents · 71 tokens

tweetclaw

OpenClaw guide for Twitter search, follower exports, monitoring, media, and approved X automation through Xquik. Not affiliated with X Corp.

Xquik-dev/tweetclaw · 34 tokens

rosclaw-embodied

A set of rules for completing robot tasks in ROSClaw, a system for running and checking robot work. It covers approved robot files, acceptance evidence, and separate rules for simulation and real hardware.

ros-claw/rosclaw · 54 tokens

git-commit-writer

Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.

mergisi/awesome-openclaw-agents · 53 tokens

growth-ideas

Describe your product or project and get three actionable growth ideas tailored to your stage.

mergisi/awesome-openclaw-agents · 20 tokens