predicate-logic — Claude Code skill: mathematical logic problem-solving
A skill for tackling predicate logic in mathematical logic. Handles quantifier analysis, normal form conversion, proof construction, and countermodel search.
MIT 1 installs ★ 3,951 updated 2026-01-26
npx skills add parcadei/Continuous-Claude-v3 --skill predicate-logic -a claude-codeWhat predicate-logic does
The skill includes tools for quantifier identification (universal and existential), prenex normal form transformation, Skolemization, and resolution-based proof generation. Built on Z3 solver and SymPy.
Ready-made commands let you prove statements, check formula satisfiability, apply universal instantiation, and construct models. Requires Bash for execution and Read access for documentation.
What it helps with
- prove or refute a statement in predicate logic
- convert a formula to prenex normal form
- find a countermodel to an invalid argument
- apply Skolemization to existential quantifiers
- check satisfiability of a quantified formula
Example prompts for the agent
- Prove that ForAll([x], P(x)) implies P(a) using universal instantiation
- Find a model for Exists([x], And(P(x), Not(Q(x))))
- Transform a formula into prenex normal form via sympy
How to install predicate-logic
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill predicate-logic -a claude-code2Manually: put the files in place
~/.claude/skills/predicate-logic/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/predicate-logic/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill predicate-logic -a codex2Manually: put the files in place
.agents/skills/predicate-logic/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill predicate-logic -a cursor2Manually: put the files in place
.cursor/skills/predicate-logic/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install parcadei/Continuous-Claude-v3 .claude/skills/math/mathematical-logic/predicate-logic2Manually: put the files in place
.github/skills/predicate-logic/SKILL.md1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill predicate-logic -a gemini-cli2Platform CLI
gemini skills install https://github.com/parcadei/Continuous-Claude-v3 --path .claude/skills/math/mathematical-logic/predicate-logicManually: put the files in place
.devin/skills/predicate-logic/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill predicate-logic -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about predicate-logic
How do I install predicate-logic in Claude Code?
Run npx skills add parcadei/Continuous-Claude-v3 --skill predicate-logic -a claude-code, then check the docs at ~/.claude/skills/predicate-logic/SKILL.md.
What does predicate-logic do?
The skill provides methods for mathematical logic problems: analyzes quantifiers, transforms formulas, builds proofs, and finds countermodels using Z3 solver and SymPy.
Which platforms support predicate-logic?
The skill installs on Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode, each with its own installation path.
Source text
SKILL.md · MIT
--- name: predicate-logic description: "Problem-solving strategies for predicate logic in mathematical logic" allowed-tools: [Bash, Read] --- # Predicate Logic ## When to Use Use this skill when working on predicate-logic problems in mathematical logic. ## Decision Tree 1. **Quantifier Analysis** - Identify: ForAll (universal), Exists (existential) - Scope of quantifiers and free/bound variables - `z3_solve.py prove "ForAll([x], P(x)) implies P(a)"` 2. **Prenex Normal Form** - Move all quantifiers to front - Standardize variables to avoid capture - `sympy_compute.py simplify "prenex(formula)"` 3. **Skolemization (for Exists)** - Replace existential quantifiers with Skolem functions - Exists x. P(x) -> P(c) or P(f(y)) depending on scope - Needed for resolution-based proofs 4. **Resolution Proof** - Convert to CNF, negate conclusion - Apply resolution rule until empty clause or saturation - `z3_solve.py prove "resolution_valid"` 5. **Model Theory** - Construct countermodel to refute invalid argument - Finite model for finite domain - `z3_solve.py model "Exists([x], P(x) & Not(Q(x)))"` ## Tool Commands ### Z3_Forall ```bash uv run python -m runtime.harness scripts/z3_solve.py prove "ForAll([x], Implies(P(x), Q(x)))" ``` ### Z3_Exists ```bash uv run python -m runtime.harness scripts/z3_solve.py sat "Exists([x], And(P(x), Not(Q(x))))" ``` ### Z3_Universal_Instantiation ```bash uv run python -m runtime.harness scripts/z3_solve.py prove "Implies(ForAll([x], P(x)), P(a))" ``` ### Z3_Model ```bash uv run python -m runtime.harness scripts/z3_solve.py model "Exists([x], P(x))" ``` ## Cognitive Tools Reference See `.claude/skills/math-mode/SKILL.md` for full tool documentation.
© parcadei · MIT · parcadei/Continuous-Claude-v3