Library Advisor logo

Library Advisor

Community
ArabelaTso
library-advisor

Recommend relevant Isabelle/HOL or Coq standard library theories, lemmas, and tactics based on proof goals. Use when: (1) Users need library lemmas for their proof, (2) Proof goals match standard library patterns, (3) Users ask what libraries to import, (4) Specific lemmas are needed for list/set/arithmetic operations, (5) Users are stuck and need to know what library support exists, or (6) Guidance on find_theorems/Search commands is needed. Supports both Isabelle/HOL and Coq standard libraries.

Overview

PublisherArabelaTso
RepositorySkills-4-SE
Skill namelibrary-advisor
Stars
258
Forks
25
Bundled files
3
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ArabelaTso on GitHub. Read the source before you install it.

Installation

Install the Library Advisor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/library-for-proof-advisor
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git /tmp/Skills-4-SE
mkdir -p .claude/skills
cp -r /tmp/Skills-4-SE/skills/library-for-proof-advisor .claude/skills/library-advisor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Library Advisor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Library Advisor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Library Advisor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Library Usage Advisor

Recommend relevant libraries, lemmas, and theories from Isabelle/HOL or Coq standard libraries based on proof goals.

Workflow

1. Analyze the Proof Goal

Examine the goal to identify:

  • Domain: Lists, sets, arithmetic, logic, etc.
  • Operations: Specific functions or operators involved
  • Pattern: Commutativity, associativity, distributivity, etc.
  • Complexity: Simple property vs. complex relationship

2. Determine Target System

Identify which proof assistant:

  • Isabelle/HOL: Use Main library and extensions
  • Coq: Use standard library (List, Arith, etc.)
  • Both: Provide recommendations for both systems

3. Identify Relevant Libraries

Based on the domain, recommend appropriate libraries:

For list operations:

  • Isabelle: Main (List theory included)
  • Coq: Require Import List. Import ListNotations.

For arithmetic:

  • Isabelle: Main (Nat theory included)
  • Coq: Require Import Arith Lia.

For sets:

  • Isabelle: Main (Set theory included)
  • Coq: Require Import MSets.

For logic:

  • Isabelle: HOL (automatically available)
  • Coq: Require Import Logic.

4. Search for Specific Lemmas

Look for lemmas that directly match the goal:

Exact matches: Lemmas that prove the goal directly Component lemmas: Lemmas for parts of the goal Related lemmas: Similar properties that might help

Use the library reference files:

5. Recommend Usage

Provide concrete recommendations:

Direct application:

isabelle
lemma "goal"
  by (simp add: relevant_lemma)

With additional steps:

coq
Lemma goal : statement.
Proof.
  apply relevant_lemma.
  (* additional steps *)
Qed.

Manual proof with lemmas: Show how to use lemmas in a structured proof

6. Suggest Search Commands

Teach users how to find lemmas themselves:

Isabelle:

isabelle
find_theorems "pattern"
find_theorems name: "keyword"
sledgehammer

Coq:

coq
Search pattern.
Search "keyword".
Locate "notation".

Domain-Specific Recommendations

Lists

Common goals:

  • Length properties: length_append, length_rev, length_map
  • Reverse properties: rev_rev_ident, rev_append
  • Append properties: append_assoc, append_Nil
  • Map properties: map_append, map_map
  • Membership: in_set_member, set_append

Libraries:

  • Isabelle: Main (automatic)
  • Coq: List library

Arithmetic

Common goals:

  • Commutativity: add_commute, mult_commute
  • Associativity: add_assoc, mult_assoc
  • Distributivity: add_mult_distrib
  • Inequalities: Use arith/lia tactics

Libraries:

  • Isabelle: Main (Nat theory)
  • Coq: Arith, Lia, Nia

Sets

Common goals:

  • Union/intersection: Un_commute, Int_commute
  • Subset: subset_refl, subset_trans
  • Membership: Un_iff, Int_iff

Libraries:

  • Isabelle: Main (Set theory)
  • Coq: MSets or custom definitions

Logic

Common goals:

  • Conjunction: conjI, conjE
  • Disjunction: disjI1, disjI2
  • Implication: impI, mp
  • Quantifiers: allI, exI

Libraries:

  • Isabelle: HOL (automatic)
  • Coq: Logic (mostly automatic)

Recommendation Patterns

Pattern 1: Exact Lemma Match

When goal exactly matches a known lemma:

Isabelle:

isabelle
lemma "rev (rev xs) = xs"
  by (simp add: rev_rev_ident)

Coq:

coq
Lemma example : forall l, rev (rev l) = l.
Proof.
  apply rev_involutive.
Qed.

Pattern 2: Combination of Lemmas

When goal needs multiple lemmas:

Isabelle:

isabelle
lemma "length (rev (xs @ ys)) = length xs + length ys"
  by (simp add: length_rev length_append)

Coq:

coq
Lemma example : forall l1 l2,
  length (rev (l1 ++ l2)) = length l1 + length l2.
Proof.
  intros.
  rewrite rev_length.
  rewrite app_length.
  reflexivity.
Qed.

Pattern 3: Automation

When goal is provable by automation:

Isabelle:

isabelle
lemma "n + m = m + n"
  by simp
(* Or: by auto, by arith *)

Coq:

coq
Lemma example : forall n m, n + m = m + n.
Proof.
  intros. lia.
Qed.

Pattern 4: Induction with Lemmas

When manual proof needed but lemmas help:

Isabelle:

isabelle
lemma "property xs"
proof (induction xs)
  case Nil
  show ?case by simp
next
  case (Cons x xs)
  show ?case using Cons.IH by (simp add: helper_lemma)
qed

Coq:

coq
Lemma example : forall l, property l.
Proof.
  induction l as [| x xs IHxs].
  - simpl. reflexivity.
  - simpl. rewrite IHxs. apply helper_lemma.
Qed.

Search Strategies

Strategy 1: Pattern-Based Search

Isabelle:

isabelle
find_theorems "rev (rev _) = _"
find_theorems "length (_ @ _)"
find_theorems "_ + _ = _ + _"

Coq:

coq
Search rev.
Search (_ ++ _).
Search (?x + ?y = ?y + ?x).

Strategy 2: Name-Based Search

Isabelle:

isabelle
find_theorems name: "append"
find_theorems name: "comm"

Coq:

coq
Search "append".
Search "comm" (_ + _).

Strategy 3: Type-Based Search

Coq:

coq
Search (list _ -> nat).
Search (_ -> _ -> _ + _).

Strategy 4: Sledgehammer/Auto

Isabelle:

isabelle
lemma "goal"
  sledgehammer
  (* Suggests relevant lemmas and tactics *)

Coq:

coq
Lemma goal : statement.
Proof.
  auto.  (* Try automatic tactics *)
Qed.

Common Recommendations by Goal Type

"rev (rev xs) = xs"

  • Isabelle: rev_rev_ident or by simp
  • Coq: rev_involutive

"length (xs @ ys) = length xs + length ys"

  • Isabelle: length_append or by simp
  • Coq: app_length

"n + m = m + n"

  • Isabelle: add_commute or by simp
  • Coq: plus_comm or lia

"x ∈ set (xs @ ys) ⟷ x ∈ set xs ∨ x ∈ set ys"

  • Isabelle: set_append
  • Coq: in_app_iff

"map f (xs @ ys) = map f xs @ map f ys"

  • Isabelle: map_append
  • Coq: map_app

Examples

For complete examples with specific proof goals and library recommendations, see examples.md.

Tips

  • Search first: Use find_theorems/Search before proving manually
  • Check automation: Try simp/auto/lia before complex proofs
  • Use sledgehammer: In Isabelle, sledgehammer finds relevant lemmas
  • Import early: Import all needed libraries at the start
  • Learn patterns: Common properties (commutativity, etc.) have standard names
  • Read library docs: Browse standard library documentation
  • Build intuition: Learn which libraries contain which lemmas
  • Combine lemmas: Complex goals often need multiple lemmas
  • Simplify first: Use simp/simpl to reduce goals before searching

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Library Advisor AI skill do?

Recommend relevant Isabelle/HOL or Coq standard library theories, lemmas, and tactics based on proof goals. Use when: (1) Users need library lemmas for their proof, (2) Proof goals match standard library patterns, (3) Users ask what libraries to import, (4) Specific lemmas are needed for list/set/arithmetic operations, (5) Users are stuck and need to know what library support exists, or (6) Guidance on find_theorems/Search commands is needed. Supports both Isabelle/HOL and Coq standard libraries.

Why use Library Advisor on TypingMind?

Because you install it once and use it with any model. Library Advisor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Library Advisor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/library-for-proof-advisor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Library Advisor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Library Advisor?

As many as you like. As long as a model supports skills, you can use Library Advisor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Library Advisor AI skill free?

Yes. It is published on GitHub by ArabelaTso under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇