VibeTechnologies/VibeTeam

github-apps

Create and configure role-scoped GitHub Apps for VibeTeam, map credentials to agents placeholders, and validate installation permissions/identity.

Idioma do texto original: inglês

github-handoff-evals

Run VibeTeam GitHub/Slack handoff validation with unit tests, Slack evals, GitHub webhook evals, and permission checks. Use when validating multi-agent GitHub communication (issues, discussions, PR comments) or when asked to prove changes via tests/evals and…

Idioma do texto original: inglês

slack-app

Create and configure VibeTeam Slack apps (one ingress app plus role-scoped responder apps), wire role tokens/secrets, and validate routing/identity behavior.

Idioma do texto original: inglês

task-completition-evaluation

Final completion gate for VibeTeam tasks. Use at the end of implementation to verify diff quality, real testing, GitHub/Slack multi-agent communication evidence, and PR health before declaring done.

Idioma do texto original: inglês

knowledgebase-search

Search shared knowledgebase content using docs_tools (BM25 + fallback keyword scoring) before answering from memory.

Idioma do texto original: inglês

knowledgebase-search

Shared workflow for knowledgebase retrieval using docs_tools and injected OpenClaw context.

Idioma do texto original: inglês

knowledgebase-file-ingestion

Ingest user-provided files into the shared agents knowledgebase and verify retrieval.

Idioma do texto original: inglês

sentry-response

Handle Sentry issues end-to-end for SoftwareEngineer (investigate, fix, PR, and close).

Idioma do texto original: inglês

k3s-ops

Deploy VibeTeam services to k3s, scale worker nodes, and manage node naming (vibe-backend-vm, vibe-worker-0N, k3s-vmss-<suffix>).

Idioma do texto original: inglês

agent-evaluation

Instruct OpenCode to run VibeTeam agent benchmarks using agents/benchmark.py and report results in table format

Idioma do texto original: inglês

agent-evaluation-direct

Evaluate VibeTeam agents by running tasks directly via scripts/run_agent.py and comparing responses

Idioma do texto original: inglês

researcher-evaluation

Technical playbook for GenAI agent evaluation using agents/benchmark.py with G-Eval methodology

Idioma do texto original: inglês

vibeteam-readiness

Run VibeTeam system readiness checks - validates infrastructure, LLM, integrations (Slack, GitHub, Gmail, Sentry, Langfuse), and K8s agents

Idioma do texto original: inglês