Skip to content
Agent Orchestration
Skill

/construct-toy-examples

Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal. Use when you are stuck in reasoning and need simpler examples to regain traction, or when you want to see where the assumptions take effect and gain

From plugin
danus
16017 skills20 agents3 MCP
Install
$ npx -y skills add frenzymath/Danus --skill construct-toy-examples --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/construct-toy-examples

Context preview

The summary Claude sees to decide when to auto-load this skill.

Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal. Use when you are stuck in reasoning and need simpler examples to regain traction, or when you want to see where the assumptions take effect and gain

SKILL.md

construct-toy-examples.SKILL.md
name: construct-toy-examples
description: Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal. Use when you are stuck in reasoning and need simpler examples to regain traction, or when you want to see where the assumptions take effect and gain intuition.

Construct Toy Examples

Use this skill when the agent is stuck in reasoning and needs simpler examples that satisfy both the assumptions and the conclusion in order to understand why the statement works.

Input Contract

Read:

  • current statement/subgoal
  • relevant `immediate_conclusions`
  • relevant `counterexamples` and failed branch notes
  • relevant background/results when available

Procedure

1. Construct simpler cases (low degree, small dimension, special forms, canonical objects). 2. Ensure the toy example satisfies all assumptions of the target statement or subgoal. 3. Check that the conclusion also holds in the toy example. 4. Study where each assumption takes effect and what mechanism makes the conclusion true. 5. Identify repeated patterns, invariants, or proof ideas suggested by the example. 6. Use search/reasoning/decomposition as needed to find examples or simplify the situation.

Output Contract

Publish each toy example to global memory with `gm_add` (kind `example`): `claim` = what the example shows, `evidence` = the construction, plus these fields:

{
  "example": "...",
  "why_relevant": "...",
  "assumptions_satisfied": ["..."],
  "conclusion_verified": true,
  "where_assumptions_take_effect": "...",
  "observed_pattern": "...",
  "supports_branch_ids": ["optional"],
  "subgoal_id": "optional"
}

Tools

  • `gm_add` (publish the example finding)
  • `gm_search` (recall related findings)
  • `search_arxiv_theorems` for matching examples/known motifs
  • Codex built-in web search for known example families and standard constructions
  • use `$search-math-results` when broader retrieval is needed

Failure Logging

If generated examples are inconclusive, append an `events` record:

  • `event_type="toy_examples_inconclusive"`
  • include attempted example families
Read more
Ships withdanus

Danus orchestrates mathematical reasoning agents with fact-graph memory. A main agent (Claude Code) steers a swarm of autonomous codex workers that prove; a cold-start verifier is the sole authority on correctness: a result becomes real only once it passes.

Get the whole plugin

Other skills on danus.