Recently added

A delegation skill, not an agent type. Ask native agents to work in the background, continue useful work in the main conversation, and incorporate their results when they return. Use for "ask an agent", named agent roles, parallel delegation, or launch-and-notify work.

Design system architecture and make technology decisions. Uses a structured inline design or an available independent reviewer for comprehensive work.

Keep the current explicitly started task across Codex context compactions.

Persist explicitly started tasks across Claude Code context compaction.

Skills for discovering, installing/connecting, evaluating, and contributing to the Awesome Agent-Native Services catalog.

Reusable SDLC workflow: Jira-to-GitLab autopilot, trunk-based conventions, and review gates for AI coding agents.

Choose a Bello configuration, then launch and monitor a supervised coding task from Codex.

Learn while your agent works. Turns coding-agent generation time into adaptive, Socratic learning grounded in the code being written.

日本語技術文書の文章規範と、技術キーワードの調査・解説ページ作成。. Includes 2 skills.

Claude の舐めた返答に頑固オヤジがツッコミを入れる。入れると ON。/gankooyaji で ON/OFF を切り替える。

Claude が走って柱を跳び越える。/claude-run で始める。1 で跳ぶ、2 でもう一度、3 でやめる。

Claudeっちを育てる。入力トークンが餌、出力トークンがウンチ。/claude-cchi で面を開き、/claude-cchi hiroba でこれまでの子を見る。

Structural graph memory for AI coding assistants — navigate any codebase by structure, not guesswork.

여러 스킬을 담는 도구 상자. 보고·공유용 HTML 자료 한 장 만들기, 소스에서 API 스펙을 뽑아 카탈로그 화면 만들기, 두 스냅샷의 API 계약 변경 화면 만들기, 성과 기록을 쌓아 대시보드로 뽑기, 사고 기록을 회고 문서로 만들기, PR 본문 쓰기, 발견한 것을 GitHub 이슈로 등재하기, 열린 이슈를 골라 닫기, 독자와 목적에 맞는 업무 문서 쓰기, 고정 코드 근거로 문서를 갱신하고 독립 리뷰 후 반영하기

애자일 계층(스프린트→레일→스토리→마일스톤→태스크)으로 멀티 레포 개발을 자율 진행하는 에이전트 하네스 — 원장은 어댑터(github·beads·notion), 보완 스킬 triage(백로그 정리)·status(현황)

Deterministic evidence-packet linter for claim-backed AI output, with compatibility skills and MCP tools.

Human-in-the-loop task supervisor for AI agents

Workspace agent that executes tasks assigned by humans or supervisors, communicates progress via reply, and manages task lifecycle within a specific AgentRQ workspace

Turn a Bible verse or chapter into a researched, one-page Bible study for a group.

Local conversation and opt-in file search, with explicit AI budget controls.

Domaine Foundation skills for Codex CLI — Agentic Assisted Development workflow for Shopify theme work.

Read the current Figma browser selection through the local Figwright Kiwi bridge.

Personal productivity plugin: brings Rashad's workflows to Codex.

通用工程工作流：从 ask-matt 路由需求澄清、Spec、设计审查、Ticket、TDD 实现到 PR 交付和合并后清理。

Reusable engineering workflow Skills for Codex.

Interactive question and graded quiz popups plus opt-in Markdown conversation logging.

Codex adapter for deepwork workflows, Deepwork agents, skills, and MCP tool registrations.

Hosted MCP messaging rooms across owners, clients, and machines, with authenticated account attribution and a human-readable transcript.

Lightweight, evidence-first software delivery for Codex. 中文优先的 AI 软件交付工作流。

fixture

fixture

fixture

fixture

Local-first shared memory, recall, and reflection hooks for Codex.

Production-grade engineering skills for AI coding agents covering the full software development lifecycle from spec to ship.

Discover and book theatre, tours, attractions, and live experiences worldwide. Search, compare, check live availability, plan itineraries, and get direct tickadoo booking links. No API key required.

Claude Code and Codex operations and reusable development utilities.

Invariant-first engineering harness for routing, verification, and failure recovery while preserving agent autonomy.

Harness OS: an orchestrated agent operating system — tier routing, circuit breaker guardrails, verification gates, WAL session memory, and self-evolving workspace rules.

用于跨领域的 GitHub Issue 生命周期管理、查重与复发判断、离线交接同步和远端写入恢复。内容、证据与领域决定由调用方负责；不承担源码调查、研发审批或辩论方法。

CodeRifts API governance for agents — preflight contract change sets, verify signed receipts, and look up past decisions before merge or ship.

CodeRifts API governance for Codex/OpenAI — preflight contract change sets, verify signed receipts, and look up past decisions before merge or ship.

Reviews and fixes frontend UI against Laws of UX — Fitts's Law, Hick's Law, Jakob's Law, and the rest of the canon, plus curated extended UX principles.

Cross-language code lint enforcement for AI coding assistants (ZCode, Claude Code, Codex CLI, Kimi Code): Java, Rust, TypeScript, Python. PostToolUse hook auto-runs the native linter on every AI-written file and blocks on failure in strict mode.

Orchestrate multiple AI coding harnesses as neurons on one durable Convoy thread.

Convoy marketplace Agent Plugin for Grok Bot with live MCP + wizard skills.

Refactoring skills — change code, docs, and config already in use, gate every change behind automated verification, and report only what needs a human decision

Agent operations skills — set up a project's memory layout once, rebuild working context at session start, and turn each session's lessons into approved edits to the memory structure the codebase already has

Coordinate visible coding agents in Damson: plan dependent tasks, run parallel implementations, verify outputs, resume durable workflows, or monitor interactive sessions.

Queries OpenTelemetry traces in Tempo. Includes 1 skill.