check-referenced-state…
Validate externally referenced theorems by querying arXiv theorem search first and Codex's…
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.
/construct-toy-examplesContext 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
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.
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.
Read:
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.
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"
}If generated examples are inconclusive, append an `events` record:
🚀✨ News: This branch is the version that solved YTD. 🎉 Danus orchestrates mathematical reasoning agents with fact-graph memory.
Validate externally referenced theorems by querying arXiv theorem search first and Codex's…
Aggregate all detected errors and gaps into the final verification report, apply strict…
Verify a markdown proof in the order it is written. Use when the task is to check local…
Construct candidate counterexamples to test a proposed conjecture, lemma, or intermediate…
Screen a decomposition plan by first trying to prove all of its subgoals directly, then…
Synthesize the common stuck points across failed decomposition plans. Use when the current…