Claude Code and Codex plugins their authors filed under "productivity". All categories.
Try Liminal from your terminal. Bounded agents (Analyst / SDR / Auditor) read a brief and disagree; the in-lane agent works while the others refuse and name the correct agent. Your correction becomes the record. On enable it offers to install the Liminal desktop app so the vault outlives the session. Bounded agents run on Opus.
11 skills · 4 commands · 3 agents · hooks
Bring your organization's context lake into your coding agent — fused org search across code, decisions, tickets, PRs, docs, and people; graph-powered code navigation (callers, blast radius, tests-for); standing org rules and durable memories, served over the bonez MCP.
12 skills · 5 commands · 1 MCP server · hooks
AIPOS skills for product strategy, evidence-based discovery, rapid validation, and governed AI-assisted delivery. Create and evolve product opportunity briefs, write and ratify product visions, plan exploration, facilitate solution framing canvases, test assumptions, define and refine behavior, select release scope, prepare commitment packages, write agent contracts, report signal-source coverage, review problem clusters, check repository readiness, inspect portfolio lifecycle records, visualize work, generate synthetic data, and emit delivery metrics. Skills support the pillars and their handoffs in one installation; product approval remains with the accountable authority.
19 skills
Wheelhouse Revenue Management agent skills and MCP plugin for mcp.usewheelhouse.com. Read: portfolio pacing, pricing diagnostics, leaderboards, occupancy-vs-market charts, a portfolio map and local data caches. Write: preferences, Events & Seasons and Custom Rates (confirm-before-write MCP skills and dry-run/--apply API skills), plus a PriceLabs migration reference.
18 skills · 1 MCP server
Stack-agnostic orchestration framework. Synthesize a binder of work items (karta-plan), deliver it in parallel waves onto a per-binder integration branch (karta-deliver), build each item in an isolated git worktree (karta-build), and gate it on behavioral (karta-verify) or visual (karta-validate) acceptance — no PR, ends at the integration branch. Stack-agnostic across frontend, backend, CLI, data, and IaC, while keeping deep frontend support (component/token mapping, DTCG, design validation). Ships five agents: three read-only gates (karta-acceptance-reviewer, karta-safety-auditor, karta-design-reviewer) and two opt-in writers that edit only what you enable (karta-doc-gardner for docs, karta-kaizen for stack packs).
13 skills · 5 agents · hooks
Skill-only reposting workflow plugin. Skills + slash commands instruct the running agent (OpenClaw via its built-in browser, Claude Code or another harness via its explicitly configured browser automation) how to scrape a source website, dedupe against history + destination, apply custom user skip rules, expand shortened URLs, post via the user's logged-in browser, append history, manage source-item fanout manifests for scheduled backfills, and notify the user via configured delivery. Works with websites the agent can safely operate; ships documented example surfaces for LinkedIn, X, Bluesky, Threads, and Facebook. JSON state lives at ~/.repost-with-agent/. No code on disk performs any of the work — the agent does it all with native tools.
15 skills · 4 commands
Portable workbench for codebase study, opportunities, decisions, bounded experiments, research, audits, and context preservation, connected through modular workflow recipes.
16 skills · 2 commands · 1 agent
Context Layered Engineering for Agentic Resources - Persistent memory and intelligent context management for Claude Code sessions
15 skills · 3 agents · hooks
Document processing (Excel, Word, PowerPoint, PDF) and example skills (design, MCP builder, web artifacts).
19 skills
CLI wrapper skills: Slack, Jira, GitHub, TestRail, vault operations, log analysis, and file utilities
18 skills · hooks
Dual-host engineering discipline for Claude Code and Codex: workflow skills, agents, commands, and registry-driven quality hooks.
7 skills · 5 commands · 6 agents · hooks
ADHD-friendly productivity coaching: daily planning (/today, /energy), end-of-day capture (/checkin), weekly scheduling (/plan-week) and review (/weekly), life-direction reviews (/review), goal-to-project alignment (/align), project lifecycle (/intake, /breakdown, /reentry, /sunset), idea capture (/spark), brain dump (/dump), task triage (/triage), decision journaling (/decide), and pattern analysis (momentum, overdue-rescue) with adaptive tone calibration
16 skills · 3 agents
Shared SQL, C#/Designer and PowerBuilder development skills with optional local checks.
14 skills · 4 agents · hooks
Guided bootcamp for learning Senzing entity resolution with Codex, from first demo to production deployment.
17 skills · 1 MCP server · hooks
Search selected laboratory-protocol publishers through the hosted MCP service, with per-source toggles and safe browser-assisted retrieval.
18 skills · 1 MCP server
汎用ユーティリティ（フック・スキル）
18 skills · hooks
Core infrastructure: persistent agent identity, session lifecycle hooks, operational memory, and meta skills. Customizable agent name and memory path.
15 skills · 2 agents · 1 MCP server · hooks
Active write-back, human-approved, tax-aware YNAB budget review and categorisation assistant.
3 skills · 13 commands · 1 agent · 1 MCP server · hooks
18 coding skills plus an enforcing Stop hook: Codex reviews every turn that leaves changed files.
18 skills · hooks
Engineering workflow: plan, build, review, and ship a change with two human gates
14 skills · 4 agents · hooks
Work out the real baggage allowance for every segment of an itinerary, inventory what is carried by weight, solve the pack against the binding limit, price excess-baggage options, rank a leave-behind list, and render a counter card and packing list with Typst.
9 skills · 10 commands
Portable engineering skills and deterministic gates.
18 skills · hooks
Generate reproducible topographic SVG and PNG assets from synthetic landscapes or real-world terrain.
18 skills · 1 MCP server
Delegate tasks, plan execution, and code reviews to the local agy CLI. Background jobs, session hooks, stop-review gate, rescue subagent.
4 skills · 11 commands · 3 agents · hooks
Claude Code orchestrates its own explore/implement subagents (codex or grok on request), isolated adversarial review
2 skills · 12 commands · 4 agents · hooks
Session manager for a markdown vault: hooks that deliver rules, today's daily, open todos, newest lessons and the project hub into every session and re-deliver them after compaction, drift checks on every prompt, session wrap and daily logs, a per-session ledger, ruling capture, per-object decision records, agenda and weekly review, vault scaffolding, and vault health (audit, grooming, canon size budgets).
15 skills · 3 agents · hooks
How work is run: best-practices, learning-loop, model-delegation, visual-loop, token-efficiency, actions-cost, netlify-cost, session-continuity, delivery-loop, knowledge-base-builder, plugin-experience-design, product-passport, and the cheap-reviewer subagent.
18 skills · 1 agent
Orchestrate, trace, review, and safely conclude approved OLI Indexer jobs through explicit technical and human gates.
18 skills
FinOps 교재·2026 프레임워크를 4단계(WHY→Inform→Optimize→Operate) + 검증·PPT로 HBT 가상 기업 데이터에 적용해 체득하는 멀티클라우드 FinOps + FinOps for AI 실습 플러그인
9 skills · 9 commands
Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search to Claude workflows.
16 skills · 1 MCP server · hooks