Skill Creator
hanialshater
7 published skills · 0 GitHub stars across the catalog. View on GitHub ↗
code-evolution
Autonomous multi-agent code evolution system for optimization problems. Use when solving complex optimization problems (packing, geometry, scheduling, search) through evolutionary approaches with multiple independent AI agents. Multi-start hybrid heuristic+SLSQP methods significantly outperform single approaches. Triggers include genetic algorithms, evolutionary optimization, multi-agent problem solving, parameter tuning at scale, AlphaEvolve-style research, or evolving code solutions across generations.
edu-demo-evaluator
Evaluate educational demos using Chrome tools for E2E testing. Executes testcases from test_cases.json, captures screenshots, verifies learning outcomes.Scores QUALITY relative to benchmark. Uses real browser interaction viamcp__claude-in-chrome__* tools.
edu-demo-evaluator-tests
Execute test_cases.json against educational demos. Systematic testing via ChromeE2E. Single tab, sequential agents. Output: agent_X_tests.json with PASS/FAIL/PARTIALresults. Captures screenshots and identifies bugs/blockers.
edu-demo-builder
Build educational demos with excellent UX. Use when spawned by orchestratorto create or improve interactive visualizations. Focus on: obvious next action,no scrolling, persistent state display. You don't see benchmarks - follow UXprinciples. Copy base file to your output, then edit your copy.
edu-demo-orchestrator
Orchestrate evolution of educational demos through multi-agent exploration.NEW WORKFLOW: First develop test cases, then spawn builders, then evaluatewith Chrome E2E testing. Test cases define LEARNING outcomes to verify.
edu-demo-evaluator-free
Watch educational demo like a learner (BLIND evaluation). No test cases. Nobenchmark. No rubric. Honest assessment of: impression, what works, what doesn't,learner impact, recommendation. Output: agent_X_free_eval.json
edu-demo-test-cases
Develop educational test cases for demos. Creates test_cases.json with specificscenarios that verify LEARNING outcomes, not just UI interactions. Test casesdefine what a learner should experience and verify. Uses Chrome tools to prototypeinteractions.