Agent Workflows · For developers

bkend.ai onboarding — MCP setup, resource hierarchy, tenant/user model, first project.

ww-w-ai/bkit-claude-code

Shows a markdown dashboard of basemind activity in the session: tool call counts, top operations and estimated tokens saved against a grep and Read baseline.

Goldziher/basemind

在多轮对话和多 Agent 协作场景下，帮助模型管理指令、项目状态和长上下文。通过外部文档与会话笔记实现可控的“记忆”、指令冲突检测和高质量交接。适用于任务跨多次调用、跨 Agent、需要稳定行为规范时使用。

No-Trade-No-Life/Yuan

Installs and configures the oh-my-claudecode heads-up display in the Claude Code statusline, with minimal, focused and full layouts.

Yeachan-Heo/oh-my-claudecode

Interview-based project setup — generates CLAUDE.md, ROADMAP, .gitignore, .env.example from scratch.

AlexZio00/sovereign-skills

AI Engineering from Scratch 课程的主题路由器。给它一个主题、问题或正在处理的 bug， 它会指出精确教授它的课程，以及下一条正确命令。触发短语： “在哪里学习”、“哪节课涵盖”、“课程导航”、“我卡在”、“接下来该做什么”、 “教我 MCP”、“教我 Agent Skills”、“在哪里准备 Claude certification”，或 "where do I…

fancyboi999/ai-engineering-from-scratch-zh

Configure Neovim editor with init.lua, plugin management, LSP setup, keymaps, and options.

wcygan/dotfiles

A skill your agent uses when the user wants to add a new feature, capability, or cluster of work to an existing active Piyaz project.

FrkAk/piyaz

Methodology for designing, implementing and testing Model Context Protocol servers in TypeScript or Python, covering tool design, error handling and security, in Chinese.

jnMetaCode/superpowers-zh

Pattern for progressively refining context retrieval to solve the subagent context problem.

affaan-m/ECC

Read-only Haft project cockpit for active problems, decisions, notes, evidence freshness, drift, commissions, spec lifecycle, module decision coverage, and bounded exact file-link gaps from a…

m0n0x41d/haft

Create a new task in the Bernstein orchestrator. An agent skill from sipyourdrink-ltd/bernstein.

sipyourdrink-ltd/bernstein

Let AKA autonomously add, run, inspect, and revise intra-kernel timeline probes for standalone CUDA/inline PTX or CuTe DSL when ordinary benchmark, NSYS, or NCU evidence cannot answer a specific…

alibaba/atrex-kernel-agent

Scaffold a new MCP prompt template. An agent skill from cyanheads/pubmed-mcp-server.

cyanheads/pubmed-mcp-server

Use MemoryWhale debugging evidence when the user requests recall or a recurring failure may have relevant recorded history.

wuisabel-gif/MemWhale

Build and debug Python applications using AgentScope 2.x. An agent skill from agentscope-ai/skills.

agentscope-ai/skills

Three rules for multi-step work with DeepSeek V4 thinking models: verify references, use a verifier subagent before big edits, and write plans with exact path and line.

codewhale-hq/Codewhale

Set up the ContextA8C MCP server for accessing Automattic internal resources (Slack, Linear, P2s, GitHub Enterprise, etc.)

woocommerce/woocommerce-ios

Add, rename, or wire a server config attribute end to end - a core cn=config attribute (the slap.h/libglobs.c chain) or a plugin config-entry attribute - including the schema line, defaults, upgrade…

389ds/389-ds-base

Open and operate the Cesium MCP 3D map, create map objects and GeoJSON layers, or inspect the selected object in the connected map.

gaopengbin/cesium-mcp

Diagnoses which of three failure modes a stalled AI-assisted build is in, then chooses a targeted fix, a hard reset or a rethink instead of more prompting.

jsmastery-pro/jsm-agent-skill

Plan and implement a new feature for the Megingiard Android app.

stormpanda/megingiard

Audit and improve project memory files (CLAUDE.md, AGENTS.md, .claude.local.md) — assess against a quality rubric, then apply additions and removals.

kylesnowschwartz/SimpleClaude

Этот скилл следует использовать перед любой творческой работой — созданием фич, разработкой компонентов, добавлением функциональности или изменением поведения.

AndreevED/1c-ai-feature-dev-workflow

Audits the instruction files (CLAUDE.md, .claude/rules, .claude/skills, tools/measuredax/CLAUDEWINDOWS.md) for accuracy and bloat against .claude/rules/instructions.md, and proposes a concrete edit…

antoinecellerier/speaker-tuning-to-easyeffects

Has the agent do the implementation itself and consult one persistent, stronger advisor through ask_worker only when it reaches a dead end.

Th0rgal/sandboxed.sh

Acts as an explore-first planning consultant that studies the codebase and writes a single decision-complete work plan before any implementation starts.

code-yeongyu/oh-my-openagent

Runs a long task as a checkpointed goal loop: it creates goals, mirrors each step into a todo list, gathers evidence per criterion and lands every goal before the next.

code-yeongyu/oh-my-openagent

A-MEM-inspired agentic memory workflow for structured knowledge capture.

iamtouchskyer/memex

A skill your agent uses when the user asks about Model Context Protocol details (protocol spec, transports, authorization, tools/resources/prompts, sampling/elicitation/roots, server/client…

confluentinc/mcp-confluent

Turn a reproduced or recurring Roam failure into a durable correction, regression control or narrowly scoped project skill, and reconcile conflicting lessons.

Cranot/roam-code

Control the cmux macOS terminal app: workspaces, panes, surfaces, browsers, notifications, settings, and hooks.

davidondrej/skills

A skill your agent uses when contributing to the Butterbase codebase, adding new MCP tools, creating API routes, writing migrations, or understanding the monorepo architecture

butterbase-ai/butterbase-skills

Publish a new version of the npm package. An agent skill from tomaspavlin/rohlik-mcp.

tomaspavlin/rohlik-mcp

A skill your agent uses when preparing a fix or feature PR for review and adding before/after plot evidence to the PR body.

RussellSB/pytrendy

Encodes a repository into the Forgetful knowledge base as a project, entities, atomic memories and documents, so a second run updates instead of duplicating.

ScottRBK/forgetful

Global skills manager for Google Antigravity. An agent skill from rmyndharis/antigravity-skills.

rmyndharis/antigravity-skills

A skill your agent uses when asked to create heatmaps, visualize patterns over time, show activity grids, or display aggregated data in a matrix format.

SCStelz/security-investigator

Collaborative brainstorming partner for multi-session ideation projects.

robertguss/claude-code-toolkit

Use BEFORE editing any file in supabase/migrations/ or supabase/schemas/, OR when the user runs a /database subcommand (compact local migration, rls scenarios, align).

gridaco/grida

Extended diagnostic skill that validates the full Cognithor skill lifecycle — SkillRegistry scanning, keyword matching (exact + fuzzy at 70% threshold), and async execution.

Alex8791-cyber/cognithor

A skill your agent uses when the user wants to interact with Apple Notes on macOS - creating, searching, reading, updating, deleting, organizing, or formatting notes and folders.

sweetrb/apple-notes-mcp

Configure AWS MCP servers for documentation search and API access.

zxkane/aws-skills

Ingest a coding session JSONL into AKB as structured notes — session report + parallel-drafted TIL / task / idea / decision sub-notes.

dnotitia/akb

Picks the next useful step for an app project, whether planning a new product, changing an existing app, fixing a bug or writing a handoff, loading only the context needed.

KhazP/vibe-coding-prompt-template

Extract your persona into CLAUDE.md or AGENTS.md for use in any AI agent

LilMGenius/polysona

AI Team OS 里用 CC 内置 Workflow 的两件事：产出回写 OS 的标准模板（§1-2、§4），以及审查分级与派工档位纪律（§3/§3.1）。准备调用 Workflow 编排子 agent 时，或要判定一件事该按 L0/L1/L2 哪一档审查（含「这活要不要开 workflow」）时使用。

CronusL-1141/AI-company

Run several independent Cotal features concurrently by creating one Git worktree and one spawn-capable mesh manager per feature; each manager staffs a review panel in a dedicated channel, adds one…

Cotal-AI/Cotal