vibestack is a portable skill pack for AI coding agents. Slash commands like /office-hours, /ship, /investigate, /tdd, /review install once and work across every agent that supports the Agent Skills open standard — Claude Code, Cursor, Kiro, and a growing list of others.
This repository also configures its own agents. See what vibestack tells them →
Skill Claude Code
Update the installed vibestack pack to the latest release — detect the install (global git checkout or a project-local vendored copy), run the upgrade, run version migrations, and show what changed.
Skill Claude Code
Work a pull request's open review threads and failing CI checks to a close: read each unresolved thread, fix or explain, run the tests, commit and push, then reply on every thread and resolve the ones that were addressed. Use after a PR exists on the current branch and reviewers or CI have come back with something.
Skill Claude Code
Build an evaluation harness for an LLM agent, prompt template, or tool-using workflow — a task set, deterministic and judge-based scoring, per-tag metrics, and a regression gate — then run it. Use it when a prompt or model change needs to be measured instead of eyeballed, or when a project ships LLM behavior with no…
Skill Claude Code
Find every code path that can run up a paid-inference bill without a ceiling (loops, retries, fan-out, agent steps, queues) and require a written dollar cap both in code and at the provider. Use before shipping anything that calls an LLM, speech, or image API, or when a bill was larger than expected.
Skill Claude Code
Read-only AWS cost review for the account at hand: where the money went last month, what changed versus the month before, and the three actions worth taking. Uses the AWS billing MCP tools when the session has them, otherwise the aws CLI (ce, compute-optimizer, budgets). Use when someone asks why the AWS bill went up…
Skill Claude Code
Audit the guardrail layer around Amazon Bedrock usage: region pinning and cross-region inference profiles, IAM scoping to model ARNs, Bedrock Guardrails configuration (PII, denied topics, content and word filters, grounding, versioning), invocation logging and KMS, per-tenant isolation, prompt injection boundaries…
Skill Claude Code
Review an Amazon Connect contact-center solution built on Lex bots and Bedrock-backed conversational logic: contact flows, bot design, Lambda integrations, prompts, latency budget, state handling, observability and cost per contact. Produces a severity-ranked findings report with a latency table, a cost estimate and…
Skill Claude Code
Read-only review of a retrieval-augmented setup, Amazon Bedrock Knowledge Bases first and hand-built RAG pipelines second: sources, chunking, metadata and tenant filtering, embedding model, vector store, sync, retrieval quality and cost per query. Builds a golden question set, measures recall@5 and MRR against the…
Skill Claude Code
Review an MCP server (Python FastMCP or the TypeScript SDK) for tool design, scope, auth, input validation, error shape, transport and prompt-injection exposure. Use it before publishing a server, before wiring one into an agent, or when someone asks whether an MCP server is safe to run. Produces a findings table with…
Skill Claude Code
Finds machine-sounding writing patterns in English prose (README, release notes, CHANGELOG, PR bodies, articles, posts, chat replies) and rewrites the text in a specific human voice while keeping every fact, number, name and claim. Use when a draft reads like a bot wrote it and it should read like the author did.
Skill Claude Code
Router for the vibestack skill suite — name the task and it points you at the right skill. Use when you know vibestack is installed but not which of its skills fits, or when an agent has no slash-command picker (Codex) and needs to find the pack by name.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: