terroir-feedback

Terroir 온보딩 — 처음 시작하는 사람이 인증 없이 설치해 환경 셋업과 제공 기능 안내를 받는 진입점

6 skills · hooks

전 직원 공통 컨텍스트 — 직군과 상관없이 모두에게 필요한 사내 안내의 목차를 세션 시작 시 Claude 에 올린다

1 skill · hooks

Knowledge mesh storage — save/ingest/query/lint over a plain-markdown knowledge base at ~/harness-mesh-storage

1 skill

Claude 사용량 표시 — Claude Code 입력창 아래(데스크톱 애플리케이션은 입력창 위)에 5시간·주간 한도 중 남은 비율, 컨텍스트 사용률, 모델, git 브랜치를 표시

AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server

3 skills · 1 command · 1 agent · 1 MCP server

Bring Pendo product analytics into Claude Code: account health, feature adoption, session replay lookup and triage, feedback analysis, and data-informed planning grounded in real usage data. Requires the Pendo connector and a Pendo subscription.

Bring Pendo product analytics into Claude: account health, feature adoption, session replay lookup and triage, feedback analysis, and data-informed planning grounded in real usage data. Requires the Pendo connector and a Pendo subscription.

6 skills · 2 MCP servers

Human-verification gate for an agent loop: builds a single-file review page (the page itself makes no network request; a reviewed HTML artifact's own https: assets still load), collects batched feedback as structured batch.v1 data instead of chat prose, and refuses to close while a BLOCKER is open, the reviewer is unnamed, or nobody has reviewed. Non-blocking, headless-guarded, round-capped. Stdlib-only.

1 skill · 1 command · 1 agent

PUA productivity coaching — modular skills, 15 workplace/corporate flavors including Ding Inside/Outside, completion-quality checks, retry/change-approach reminders, and feedback tools.

29 skills · 22 commands · 7 agents · hooks

把课题拆成连续学习文章，并根据用户反馈调整后续深度、角度和节奏。用户要求系统学习一个主题、继续下一篇或按反馈调整课程时使用。

1 skill