siddhartha-gadgil/leanaide/12-example-counterexample

Claude Code and agent skill by siddhartha-gadgil/leanaide

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Install

npx vskill@latest install siddhartha-gadgil/leanaide/12-example-counterexample

SKILL.md

Skill: Example and Counterexample Construction

Goal: Construct useful examples, test examples, boundary cases, and counterexamples that clarify a problem, stress-test a conjecture, or guide a proof strategy.

Scope: This skill supports both PROBLEM_SOLVING and EXPLORATORY_RESEARCH. Examples are evidence and diagnostic tools. They do not prove universal claims unless the domain has been reduced to a finite exhaustive list and exhaustion is explicitly justified.

Instructions:

  1. Classify the Target:
  • theorem sanity check;
  • conjecture testing;
  • hypothesis necessity;
  • boundary/degenerate case;
  • model/example for definitions;
  • counterexample search.
  1. Extract Constraints: List the hypotheses that examples must satisfy and the conclusion or behavior to test.
  2. Choose Construction Families:
  • Small finite objects: sets of size 0, 1, 2, 3, finite groups, small graphs, small categories.
  • Degenerate objects: empty set, zero object, identity map, constant function, discrete/indiscrete topology.
  • Extremal objects: maximal/minimal examples, equality cases, sharpness examples.
  • Standard pathological objects: non-Hausdorff spaces, non-Noetherian rings, nonmeasurable sets, discontinuous functions, singular spaces.
  • Free or universal examples: free groups, polynomial rings, quotient objects, products/coproducts.
  1. Compute Explicitly: Verify each hypothesis and conclusion directly. For candidate counterexamples, state exactly which hypothesis holds and which conclusion fails.
  2. Compare Variants: If no counterexample appears, try weakening one hypothesis at a time.
  3. Record Outcome: Label each constructed object as:
  • supporting_example;
  • counterexample;
  • boundary_case;
  • sharpness_example;
  • inconclusive_test.
  1. Feed Back Into Workflow:
  • In proof mode, a valid counterexample should stop the proof attempt and trigger a correction or failure report.
  • In research mode, examples and counterexamples should update conjectures, hypotheses, and next probes.

Output: Save to artifacts/02_examples.md for early examples or append to artifacts/04_research_trace.md / artifacts/04_execution_trace.md when used inside a loop. If structured output is requested, use schema.json.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
119
Repository forks
17
7-day trend score
24

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/siddhartha-gadgil/leanaide/12-example-counterexample/badge)](https://verified-skill.com/skills/siddhartha-gadgil/leanaide/12-example-counterexample)

Something wrong with this skill or its page? Tell us.