proof-trace-summarizer

proof-trace-summarizer is a skill for Claude Code, Codex from ArabelaTso/Skills-4-SE. It costs 109 tokens per session (2,658 once invoked), scanned A, original, Apache-2.0.

A summarizer for Isabelle and Coq proof scripts, which are step-by-step formal arguments checked by software. It turns detailed scripts into a high-level outline of the reasoning.

In plain words
What is it for?
Use it to understand complex proofs, document their reasoning, and create readable proof outlines.
Why use it?
Verbose proofs can hide the main idea and make them difficult to explain or document. This highlights the strategy, cases, key steps, and facts used.

Skill for Claude CodeCodex

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

Good fit Use it to understand complex proofs, document their reasoning, and create readable proof outlines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arabelatso/skills-4-se/proof-trace-summarizer
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 ArabelaTso/Skills-4-SE --skill proof-trace-summarizer
Clone the repo
git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE

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 proof-trace-summarizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/arabelatso/skills-4-se/proof-trace-summarizer/github.svg)](https://agentmods.dev/skills/arabelatso/skills-4-se/proof-trace-summarizer)
Your own site
<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/proof-trace-summarizer"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/proof-trace-summarizer/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 proof-trace-summarizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/proof-trace-summarizer"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/proof-trace-summarizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,658 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00109 $0.02658
Opus 5 $0.00055 $0.01329
Sonnet 5 $0.00022 $0.00532
Haiku 4.5 $0.00011 $0.00266

Measured 9d ago against content hash 24937c5a58d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

proof-trace-summarizer 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.

skills/proof-trace-summarizer/SKILL.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proof Trace Summarizer

Summarize long proof scripts into high-level logical steps and reasoning flow.

Overview

This skill transforms verbose Isabelle or Coq proof scripts into clear, hierarchical summaries that capture the essential reasoning structure. It identifies proof patterns (induction, case analysis, equational reasoning), extracts key steps, and presents them in a readable outline format.

How to Use

Provide a proof script with:

  1. System: Isabelle or Coq
  2. Proof script: The complete proof to summarize
  3. Context (optional): Theorem statement, definitions, or background

The skill will produce a hierarchical outline showing:

  • Main proof strategy
  • Case structure (if applicable)
  • Key reasoning steps
  • Important lemmas or facts used

Summarization Workflow

Step 1: Identify Proof Structure

Recognize the high-level proof pattern:

Induction proof: Look for proof (induction ...) (Isabelle) or induction ... as [|...] (Coq)

Case analysis: Look for proof (cases ...) (Isabelle) or destruct ... as [...] (Coq)

Direct proof: Sequential reasoning without major branching

Equational reasoning: Chain of rewrites or calculations

Hybrid: Combination of patterns

Step 2: Extract Major Components

Identify the key structural elements:

  • Base cases: Initial cases in induction or case analysis
  • Inductive cases: Recursive cases with induction hypotheses
  • Subgoals: Intermediate facts or lemmas
  • Key tactics: Non-trivial reasoning steps
  • Automation: Where automatic methods are used

Step 3: Group Related Steps

Combine sequences of tactics into logical units:

  • Multiple simplification steps → "Simplification proves..."
  • Rewrite sequences → "Rewriting chain: ..."
  • Automation → "Automatic proof handles..."

Step 4: Create Hierarchical Outline

Structure the summary as a tree:

Main theorem: <statement>
├─ Proof strategy: <induction/cases/direct>
├─ Case 1: <description>
│  ├─ Subgoal 1.1: <description>
│  │  └─ <how proven>
│  └─ Subgoal 1.2: <description>
│     └─ <how proven>
└─ Case 2: <description>
   └─ <how proven>

Read the full file on GitHub · 337 lines

Files

What ships with it

2 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. 9d ago First seen · 337 lines · 109 tokens per session scan A 24937c5a58d5

Subscribe to this mod's changes

proof-trace-summarizer is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (252 stars, last pushed 22d ago), licensed Apache-2.0. It adds 109 tokens to every session and 2,658 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories

understand-explain

Use when you need a deep-dive explanation of a specific file, function, or module in the codebase.

Egonex-AI/Understand-Anything · 27 tokens

eli5

WHAT: Explains a codebase, a folder, a feature, a command or a pull request to someone who knows nothing about it, as a PR Lens canvas whose walkthrough builds the picture one part at a time. WHEN: /eli5 , or asked to explain code simply, for a beginner, a new hire, a non-engineer, or 'like I'm five'. KEYWORDS: eli5…

coldteadotai/pr-lens · 105 tokens

master-debate

A skill for running an adversarial, multi-round debate between two Buddhist teachers. It is designed for questions where the teachers argue from different positions.

xr843/Master-skill · 127 tokens

master-milarepa

A reference skill for answering questions about Milarepa, a Tibetan Buddhist teacher associated with the Kagyu tradition. It covers retreat, hardship, Mahamudra, inner heat practices, and devotion to a teacher.

xr843/Master-skill · 258 tokens

learning-and-development

Builds capability — skills gaps, career frameworks, training that transfers to the job, and internal mobility. Use this to design a career ladder, close a capability gap, decide whether to build or hire a skill, structure onboarding into a role, or work out why training keeps failing to change anything.

cbrock84/headcount · 64 tokens

team-onboarding-playbook

Design a structured onboarding experience that gets new team members productive in 30, 60, and 90 days. Use when a new hire is joining, when contractors or agency partners need to ramp up, when an existing team is restructuring and members are switching focus, or when current onboarding feels chaotic and slow. Also…

rampstackco/claude-skills · 124 tokens