Agent skill · Workflow & Productivity

proof-skeleton-generator

Generate structured proof skeletons with tactics, strategies, and intermediate lemmas for theorems in Isabelle/HOL or Coq. Use when users need to: (1) Create proof outlines for theorem statements, (2) Generate proof structure with tactic placeholders, (3) Identify key lemmas needed for a proof, (4) Plan proof strategies (induction, case analysis, forward/backward reasoning), (5) Scaffold proofs with intermediate steps and subgoals, or (6) Convert theorem statements into detailed proof templates. Supports both Isabelle/HOL and Coq equally.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill proof-skeleton-generator --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 7 KB
Bundled scripts: none
Path: skills/analysis/proof-skeleton-generator/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Proof Skeleton Generator Generate structured proof skeletons with tactics, proof strategies, and key lemmas for theorems in Isabelle/HOL or Coq. ## Workflow ### 1. Analyze the Theorem Statement Examine the theorem to understand: - **Quantifiers**: Universal (∀/forall) or existential (∃/exists) - **Logical structure**: Implications, conjunctions, disjunctions - **Data types involved**: Lists, natural numbers, custom types - **Complexity**: Simple equality vs. complex property ### 2. Choose Target System Ask the user which proof assistant to target: - **Isabelle/HOL**: Uses Isar structured proofs, automatic tactics - **Coq**: Uses Ltac tactics, more explicit proof terms - **Both**: Generate skeletons for both systems If not specified, default to generating both versions. ### 3. Determine Proof Strategy Based on the theorem structure, identify the appropriate proof technique: **Induction** - When theorem involves recursive types: - List induction for list properties - Natural number induction for arithmetic - Structural induction for custom datatypes - Strong induction when needed **Case Analysis** - When theorem involves: - Boolean conditions - Option types (None/Some) - Sum types

What's inside
Steps it walks through
  1. Workflow
  2. 1. Analyze the Theorem Statement
  3. 2. Choose Target System
  4. 3. Determine Proof Strategy
  5. 4. Identify Required Lemmas
  6. 5. Generate Proof Skeleton
  7. 6. Structure the Output
  8. Key Principles
  9. Clarity
  10. Completeness
  11. Practicality
  12. Correctness
  13. Proof Strategy Selection Guide
  14. When to Use Induction
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the proof-skeleton-generator skill do?

Generate structured proof skeletons with tactics, strategies, and intermediate lemmas for theorems in Isabelle/HOL or Coq. Use when users need to: (1) Create proof outlines for theorem statements, (2) Generate proof structure with tactic placeholders, (3) Identify key lemmas needed for a proof, (4) Plan proof strategies (induction, case analysis, forward/backward reasoning), (5) Scaffold proofs with intermediate steps and subgoals, or (6) Convert theorem statements into detailed proof templates. Supports both Isabelle/HOL and Coq equally.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill proof-skeleton-generator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going