theory-design

theory-design is a skill for Claude Code from gyf9712/stat-theory-skills. It costs 227 tokens per session (6,979 once invoked), scanned A, original, MIT.

A planning tool for designing the theory section of a statistics or machine-learning research paper. It chooses assumptions and target results based on whether the paper explains a phenomenon, proposes a method, or applies an existing method.

In plain words
What is it for?
Use it to structure a theory, methodology, or application paper before writing proofs or running simulations.
Why use it?
It prevents the paper's mathematical framework from being designed in the wrong order or without clearly defined assumptions and goals.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions Codex.

Good fit Use it to structure a theory, methodology, or application paper before writing proofs or running simulations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gyf9712/stat-theory-skills/theory-design
Install

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.

Any agent
npx skills add gyf9712/stat-theory-skills --skill theory-design
Clone the repo
git clone --depth 1 https://github.com/gyf9712/stat-theory-skills

Made for: Claude Code.

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 theory-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/gyf9712/stat-theory-skills/theory-design/github.svg)](https://agentmods.dev/skills/gyf9712/stat-theory-skills/theory-design)
Your own site
<a href="https://agentmods.dev/skills/gyf9712/stat-theory-skills/theory-design"><img src="https://agentmods.dev/badge/skills/gyf9712/stat-theory-skills/theory-design/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.

agentmods 80×15 button for theory-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/gyf9712/stat-theory-skills/theory-design"><img src="https://agentmods.dev/badge/skills/gyf9712/stat-theory-skills/theory-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 227 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,979 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 $0.00227 $0.06979
Opus 5 $0.00113 $0.03490
Sonnet 5 $0.00045 $0.01396
Haiku 4.5 $0.00023 $0.00698

Measured 11d ago against content hash 1b5bd7670c4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

theory-design 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.

skills/theory-design/SKILL.md · 777 lines

How it starts

The opening of the file, as written. The whole thing — 777 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Theory-Design — Paper-Type-Aware Theoretical Framework Design

🔬 Model Recommendation: Run this skill on Claude Opus for best results. Framework design requires deep reasoning across mathematical and methodological dimensions. If your session is not on Opus, run /model opus.

Goes from "I have a new research topic" to a structured FRAMEWORK_DESIGN.md that downstream skills can consume. The skill's central insight: the logical order of theoretical-framework design depends on what kind of paper you're writing.

Context: $ARGUMENTS


Pipeline Position

research-refine  →  /theory-design  →  /proof-writer  →  /theory-simulation  →  /proofcheck  →  /theory-sharpen  →  /proof-repair
(rough idea)        (framework)        (theorems)        (verify)              (audit)         (improve)           (fix)

This skill is the planning layer — chooses the framework, declares assumptions, sets target results — before any theorem is written or experiment run.


Step 0: Declare paper type (MANDATORY first decision)

Statistics papers come in three types with fundamentally different logical orders. The skill REFUSES to proceed until the user declares type. If unsure, the skill helps classify based on the topic description.

The three paper types

Type Contribution Theory's role Estimator Lower bound Simulation Real data
THEORY New theoretical tool, explanation of phenomenon, impossibility result The contribution itself Often none/abstract Often equally important to upper bound Illustrative Rarely
METHODOLOGY A new method (estimator/test/algorithm) Guarantees statistical correctness of method The centerpiece Sometimes Validating Usually demonstrating
APPLICATION New empirical insight on scientific data Supports / justifies method choice Uses existing Almost never Almost never The main event

Read the full file on GitHub · 777 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. 11d ago First seen · 777 lines · 227 tokens per session scan A 1b5bd7670c4f

Subscribe to this mod's changes

theory-design is a skill published in the GitHub repository gyf9712/stat-theory-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 227 tokens to every session and 6,979 once invoked, about $0.0011 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

did

Design, estimate, validate, and write up a difference-in-differences analysis, using the post-2018 heterogeneity-robust toolkit with an explicit statement of which parallel-trends assumption is imposed. TRIGGER on "difference-in-differences", "DiD", "TWFE", "event study", "staggered adoption", "parallel trends"…

ericluo04/claude-academic-workflow · 0 tokens

iv

Design, estimate, validate, and write up an instrumental-variables analysis: single-instrument LATE designs, weak-instrument-robust inference, shift-share instruments, formula instruments that need recentering, and leniency (judge and examiner) designs estimated by UJIVE. TRIGGER on "instrumental variable", "IV"…

ericluo04/claude-academic-workflow · 0 tokens

conjoint

Design, analyze, and write up conjoint experiments in both traditions: as randomized experiments identifying average marginal component effects, and as preference-measurement instruments (hierarchical Bayes partworths, WTP, choice-share simulation), with measurement-error correction, multiple-testing correction, and a…

ericluo04/claude-academic-workflow · 0 tokens

research-talk

Author a Quarto reveal.js deck for a research talk: seminar, conference, job talk, brown bag. TRIGGER on "slides for my talk", "seminar deck", "job talk", "turn this paper into slides", "add an appendix slide", "export a handout". Classroom material is teaching-lecture; auditing an existing deck is slide-review.

ericluo04/claude-academic-workflow · 0 tokens

field-experiment

Design, analyze, and write up randomized experiments (field experiments, A/B tests, RCTs): stratified and clustered designs, randomization inference, covariate adjustment done right, noncompliance, attrition and gated outcomes, treatment-effect heterogeneity, and interference. TRIGGER on "A/B test", "randomized…

ericluo04/claude-academic-workflow · 0 tokens

rdd

Design, estimate, validate, and write up a regression discontinuity analysis, in both the continuity and local-randomization frameworks, with the full falsification battery and a refusal rule for designs that fail validation. TRIGGER on "regression discontinuity", "RDD", "running variable", "cutoff", "rdrobust"…

ericluo04/claude-academic-workflow · 130 tokens