ReddRadar
Topic: self-learning
274 skills in this topic.
-
agent-qa-testing
Agent davranis testi ve protokol uyumluluk dogrulamasi. Agent'larin tanimli rollerine uygun davranip davranmadigini assertion-based test'lerle olcer. Personality drift, role violation ve output kalite regresyonu tespit eder.
vibeeval/vibecosystem 458
-
agentic-workflow
Agentic Workflow Pattern
vibeeval/vibecosystem 458
-
agentica-claude-proxy
Guide for integrating Agentica SDK with Claude Code CLI proxy
vibeeval/vibecosystem 458
-
agentica-infrastructure
Reference guide for Agentica multi-agent infrastructure APIs
vibeeval/vibecosystem 458
-
agentica-sdk
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
vibeeval/vibecosystem 458
-
agentica-spawn
Spawn Agentica multi-agent patterns
vibeeval/vibecosystem 458
-
async-repl-protocol
Async REPL Protocol
vibeeval/vibecosystem 458
-
autonomous-pr
Otonom PR yasam dongusu. PR olustur, CI bekle, hata varsa duzelt, review feedback'i uygula, merge'e hazirla. Budget ve zaman limiti ile kontrol altinda tutulan tam otonom PR pipeline'i.
vibeeval/vibecosystem 458
-
clone-website
Reverse-engineer and clone a website in one shot — extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in worktrees as it goes. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy any website. Also triggers on phrases like "make a copy of this site", "rebuild this page", "pixel-perfect clone". Provide the target URL as an argument.
vibeeval/vibecosystem 458
-
commit
Create git commits with user approval and no Claude attribution
vibeeval/vibecosystem 458
-
completion-check
Completion Check: Verify Infrastructure Is Wired
vibeeval/vibecosystem 458
-
compound-learnings
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".
vibeeval/vibecosystem 458
-
config-security-scan
Scan .claude/ directory for security misconfigurations, exposed secrets, unsafe permissions
vibeeval/vibecosystem 458
-
continuity_ledger
Create or update continuity ledger for state preservation across clears
vibeeval/vibecosystem 458
-
continuous-learning
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
vibeeval/vibecosystem 458
-
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
vibeeval/vibecosystem 458
-
dead-code
Find unused functions and dead code in the codebase
vibeeval/vibecosystem 458
-
debug
Debug issues by investigating logs, database state, and git history
vibeeval/vibecosystem 458
-
debug-hooks
Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.
vibeeval/vibecosystem 458
-
describe_pr
Generate comprehensive PR descriptions following repository templates
vibeeval/vibecosystem 458
-
django-security
Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.
vibeeval/vibecosystem 458
-
django-tdd
Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.
vibeeval/vibecosystem 458
-
django-verification
vibeeval/vibecosystem 458
-
environment-triage
Environment Triage
vibeeval/vibecosystem 458