optim-agent
claudecodexOptimize configurable systems against measurable objectives.
1 skill
Every plugin for OpenAI Codex on GitHub — repos with a .codex-plugin/plugin.json or a Codex marketplace. Install with codex plugin marketplace add owner/repo then codex plugin add name@marketplace. Many work in both tools; see Claude Code plugins.
Optimize configurable systems against measurable objectives.
1 skill
15 proven business books distilled into AI skills for founders: customer discovery, positioning, pricing, offers, sales, and growth.
16 skills
Self-improving Claude Code, Codex, and OpenCode plugin that turns corrections and successful workflows into Preferences, Project-specific skills, and Shared skills
1 skill · 5 commands · hooks
Hierarchical agent loops with recursive self-organization.
4 skills
Plan, delegate, and review work across your configured models from one Codex conversation.
3 skills
Workspaces for agent activity, recorded usage, and visual questions with feedback.
1 skill · 1 MCP server
Run your Aeon agent from your coding agent: connect to it, run and schedule skills, and set it up with the operator console.
2 skills · 1 MCP server
Durable, searchable project memory for Claude Code, shared with Codex and your MemoRizz agents.
4 skills · 6 commands · 1 agent · 1 MCP server · hooks
Project memory for Claude Code and Codex. Storybloq stores tickets, issues, handovers, and lessons in a .story/ folder inside your repo.
1 skill
[PowerShell] Навыки для разработки на 1С:Предприятие 8.3 — абстракции над XML-форматами и CLI конфигуратора, плюс глаза и руки для тестирования через веб-клиент.
80 skills · hooks
[Python] То же — для Linux/Mac или когда PowerShell недоступен.
80 skills
/skysynth: coding agents build a system specialized for your workload, checked by tests or machine-checked proofs. Includes the /skysynth skill, the agent roles, and the hook that runs the tests before anything is delivered. Also install the skydiscover Python package: uv pip install git+https://github.com/skydiscover-ai/skydiscover (or run from a source checkout).
2 skills · 1 agent · hooks
Maximum signal. Minimum noise. Write less. Ship less. Mean more.
4 skills · hooks
Overmind skills — agent observability, tracing, and platform workflows for coding agents.
10 skills · 1 MCP server
Oh My Paper research harness for Codex: research roles, slash commands, shared skills, and a structured memory system for academic projects.
Drive agterm, a native macOS terminal, programmatically via its agtermctl CLI and local control socket.
1 skill
BloodHound, AzureHound, GitHound/JamfHound/OktaHound OpenGraph attack-path query workflows, SCIM bridge references, and optional BloodHound MCP packaging.
9 skills
Report timeline ingestion, consolidation, and evidence packaging workflows.
8 skills
Development scaffolding, repository hygiene, security tooling, and implementation workflows for Specter Codex.
6 skills
Idea critic, research strategist, enhanced brainstormer, and structured brainstorming skill for research ideation
1 skill · 3 agents
Zero-dependency, spec-driven agentic SDLC: durable specs, context-fit plans, re-anchored workers, adversarial cross-model review, and receipts. Includes 21 subagents, 26 commands, 29 skills.
29 skills · 26 commands · 21 agents
Vue, Nuxt, and NuxtHub skills for AI coding assistants
30 skills · 1 MCP server
Write, edit, restructure, and audit economics papers using field-aware guidance from leading economists.
1 skill
Analyze codebase structure, dependencies, changes, risk, matched skills, and cross-agent handoffs.
7 skills · 1 MCP server
Quality-driven orchestration kernel for AI CLIs: intelligent routing, quality verification, safety guards, and notifications
15 skills
Daily workflows and self-check skills from the MiniMax Code R&D lead: independent review, subagent split checks, tool and context budget audits, long sessions, long commands, harness experiments, trajectory review, agent briefs, evidence-first review of agent output, review capacity and turning repeat corrections into checks, plus everyday engineering practice for code review, review comments, small PRs, change descriptions and emergency changes.
19 skills
MCode Review, PR review that has to prove its findings: the same rules in your agent and in GitHub or GitLab CI, a verdict decided by a script, threads that carry over between pushes, and a weekly loop that tunes the rules on your own history. Plus finding the loops where you keep acting as a manual step for your agents, and a content pipeline that turns material into Xiaohongshu image posts and short vertical videos.
7 skills
Requirement management where the requester and their agent act as the requirement's TPM: intake with a measurable expected outcome, priority recommendation for the owner, design decision record, cadence tracking that flags stale items, ship readiness, and evidence-based outcome review. Body in a Feishu doc, status in Meegle.
6 skills
Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.
35 skills · 1 MCP server
画论文级 matplotlib 图,用 MCP 工具微调并按出版规范预检,导出真矢量 PDF
1 skill · 1 MCP server