Agent skill
limits
Problem-solving strategies for limits in real analysis
Install this agent skill to your Project
npx add-skill https://github.com/vibeeval/vibecosystem/tree/main/skills/math/real-analysis/limits
SKILL.md
Limits
When to Use
Use this skill when working on limits problems in real analysis.
Decision Tree
-
Direct Substitution
- Try plugging in the value directly
- If you get a determinate form, that's the answer
-
Indeterminate Form? (0/0, inf/inf)
- Try algebraic manipulation (factor, rationalize)
- Try L'Hopital's rule:
sympy_compute.py diffon numerator/denominator
-
Squeeze Theorem
- If bounded: find g(x) <= f(x) <= h(x) where lim g = lim h
- Verify bounds with
z3_solve.py prove
-
Epsilon-Delta Proof
- For rigorous proof: set up |f(x) - L| < epsilon
- Find delta in terms of epsilon
- Verify with
math_scratchpad.py verify
Tool Commands
Sympy_Limit
uv run python -m runtime.harness scripts/sympy_compute.py limit "sin(x)/x" --var x --at 0
Sympy_Diff
uv run python -m runtime.harness scripts/sympy_compute.py diff "x**2" --var x
Z3_Prove
uv run python -m runtime.harness scripts/z3_solve.py prove "limit_bound" --vars x
Cognitive Tools Reference
See .claude/skills/math-mode/SKILL.md for full tool documentation.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
python-testing
Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.
golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.
tdd-migration-pipeline
Orchestrator-only workflow for migrating/rewriting codebases with full TDD and agent delegation
hizir
Hızır'ın kullanım kılavuzu. Tüm komutlar, agent'lar, workflow'lar, sistemler burada. /hizir yaz, her şeyi gör.
secret-patterns
30+ service-specific secret detection regex patterns, entropy-based detection, PEM/JWT/Base64 identification, and false positive filtering.
agentica-prompts
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
Didn't find tool you were looking for?