/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
$ npx -y skills add frenzymath/Danus --skill construct-toy-examples --agent claude-codeHow 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.mdname: 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
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
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.
Other skills on danus.
- /consult
Consult a strong reasoning model for strategy — feed it the current elaboration, take its reply as the next master_guidance, and dispatch workers from it. This is the main agent's high-intelligence step (workers prove; the consult decomposes and steers). Runs over the gpt_pro
Open skill - /elaboration
Write a high-signal-to-noise mathematical progress synthesis of a project from the shared stores (global memory + fact graph), following a fixed verdict→routes→interfaces→dangers→bridges template and a strict honesty discipline. Use it each strategic cycle, right before the
Open skill - /human-summary
Write a human-readable mathematical progress report (compiled PDF) on a project for the operator / the mathematician who posed the problem. This is NOT `elaboration` (dense input for the strategy consult) and NOT the dashboard. Render from the fact graph's verified
Open skill - /initialize
First-run setup interview for a Danus deployment. Run it on the FIRST session, whenever runtime/.danus-initialized is absent or OPERATOR.md is still the blank template, or when the operator asks to set up / initialize / onboard / re-configure. It greets the operator, explains
Open skill - /write-paper
Turn a project's verified fact graph into a publishable LaTeX paper in a configurable house style — a standalone amsart .tex with a real bibliography, compiled to PDF. Use when a project's target theorem is established and the operator wants the paper, or asks to
Open skill - /check-referenced-statements
Validate externally referenced theorems by querying arXiv theorem search first and Codex's built-in web search second. Use when a markdown proof cites statements from external papers.
Open skill

