Search
Agent Workflows · affaan-m/ECC
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Audits your installed Claude skills and commands for quality, with a quick mode for recently changed skills and a full mode that evaluates all of them through subagents. | affaan-m/ | 277k | 5 repos | ~3.1k | Automated safety check: Pass | MIT | today |
| 2 | Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered. | affaan-m/ | 277k | 2 repos | ~2.3k | Automated safety check: Pass | MIT | today |
| 3 | Measures whether agents actually follow a skill, rule or agent definition by generating scenarios at three strictness levels and scoring tool-call traces. | affaan-m/ | 277k | 1 repo | ~623 | Automated safety check: Pass | MIT | today |
| 4 | Pattern for progressively refining context retrieval to solve the subagent context problem. | affaan-m/ | 277k | 7 repos | ~1.6k | Automated safety check: Pass | MIT | today |
| 5 | Turns a one-line objective into a multi-step plan file with PR-sized steps, context briefs, a dependency graph, parallel-step detection and an adversarial review. | affaan-m/ | 277k | 5 repos | ~1.3k | Automated safety check: Pass | MIT | today |
| 6 | Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. | affaan-m/ | 277k | 5 repos | ~1.1k | Automated safety check: Pass | MIT | today |
| 7 | Runs several coding agent sessions side by side in tmux panes with dmux, with patterns for research, multi-file features, test-and-fix loops and parallel reviews. | affaan-m/ | 277k | 5 repos | ~1.6k | Automated safety check: Pass | MIT | today |
| 8 | Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. | affaan-m/ | 277k | 5 repos | ~1k | Automated safety check: Pass | MIT | today |
| 9 | Fetches current library and framework documentation through the Context7 MCP instead of relying on training data, resolving a library ID before each query. | affaan-m/ | 277k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | today |
| 10 | Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. | affaan-m/ | 277k | 5 repos | ~298 | Automated safety check: Pass | MIT | today |
| 11 | Adds one optional external Codex critique that tries to break a council's decision draft, sent to OpenAI only after you consent. | affaan-m/ | 277k | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 12 | Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. | affaan-m/ | 277k | 3 repos | ~1.9k | Automated safety check: Pass | MIT | today |
| 13 | Evidence-first automation inventory and overlap audit workflow for ECC. | affaan-m/ | 277k | 2 repos | ~1k | Automated safety check: Pass | MIT | today |
| 14 | Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. | affaan-m/ | 277k | 2 repos | ~2.9k | Automated safety check: Pass | MIT | today |
| 15 | 使用AgentShield扫描您的Claude代码配置（.claude/目录），以发现安全漏洞、配置错误和注入风险。检查CLAUDE.md、settings.json、MCP服务器、钩子和代理定义。 | affaan-m/ | 277k | 3 repos | ~738 | Automated safety check: Pass | MIT | today |
| 16 | Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. | affaan-m/ | 277k | 3 repos | ~1.3k | Automated safety check: Notes | MIT | today |
| 17 | 用于审计Claude技能和命令的质量。支持快速扫描（仅变更技能）和全面盘点模式，采用顺序子代理批量评估. An agent skill from affaan-m/ECC. | affaan-m/ | 277k | 3 repos | ~1.2k | Automated safety check: Pass | MIT | today |
| 18 | Engineering operating model for teams where AI agents generate a large share of implementation output. | affaan-m/ | 277k | 4 repos | ~364 | Automated safety check: Pass | MIT | today |
| 19 | Operate and extend NanoClaw, ECC's zero-dependency session-aware REPL, with persistent markdown-backed sessions and slash commands for model switching, skill loading, session branching… | affaan-m/ | 277k | 4 repos | ~286 | Automated safety check: Pass | MIT | today |
| 20 | Split an RFC into a multi-agent execution DAG — decompose into work units with dependencies and acceptance tests, run research, plan, implement, test, and review per unit, then merge through a queue… | affaan-m/ | 277k | 4 repos | ~459 | Automated safety check: Pass | MIT | today |
| 21 | Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems. | affaan-m/ | 277k | 4 repos | ~5.8k | Automated safety check: Pass | MIT | today |
| 22 | AgentShield を使用して、Claude Code の設定（.claude/ ディレクトリ）のセキュリティ脆弱性、設定ミス、インジェクションリスクをスキャンします。CLAUDE.md、settings.json、MCP サーバー、フック、エージェント定義をチェックします。 | affaan-m/ | 277k | 2 repos | ~796 | Automated safety check: Pass | MIT | today |
| 23 | 自主Claude代码循环的模式与架构——从简单的顺序管道到基于RFC的多智能体有向无环图系统. An agent skill from affaan-m/ECC. | affaan-m/ | 277k | 2 repos | ~3.8k | Automated safety check: Pass | MIT | today |
| 24 | 使用dmux（AI代理的tmux窗格管理器）进行多代理编排。跨Claude Code、Codex、OpenCode及其他工具的并行代理工作流模式。适用于并行运行多个代理会话或协调多代理开发工作流时。 | affaan-m/ | 277k | 2 repos | ~1k | Automated safety check: Pass | MIT | today |
| 25 | Full-stack diagnostic for agent and LLM applications. An agent skill from affaan-m/ECC. | affaan-m/ | 277k | 1 repo | ~2.5k | Automated safety check: Pass | MIT | today |
| 26 | 26.Agentic Os Build persistent multi-agent operating systems on Claude Code. | affaan-m/ | 277k | 1 repo | ~3.1k | Automated safety check: Notes | MIT | today |
| 27 | Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports. | affaan-m/ | 277k | 1 repo | ~1.5k | Automated safety check: Pass | MIT | today |
| 28 | Prevent AI style drift on legacy projects by scanning the codebase for implicit conventions, resolving conflicts with the operator one at a time, and writing an enforceable .ai-style-rules.md… | affaan-m/ | 277k | 1 repo | ~2.1k | Automated safety check: Notes | MIT | today |
| 29 | Design a goal-oriented agent loop or review one for failure modes: spinning, Goodhart-gaming the verifier, or running a wrong answer to completion. | affaan-m/ | 277k | 1 repo | ~2.9k | Automated safety check: Pass | MIT | today |
| 30 | Run team-based orchestration for agent squads: work items with owners and scope, agent Kanban state, branch isolation, control pane visibility, and merge gates. | affaan-m/ | 277k | 1 repo | ~1.2k | Automated safety check: Pass | MIT | today |
| 31 | 31.Team Builder Interactive picker that discovers available agent personas via the claude agents command and agents/ markdown globs, groups them into domains, has the user select up to five, dispatches them in… | affaan-m/ | 277k | 1 repo | ~1.8k | Automated safety check: Pass | MIT | today |
| 32 | Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction. | affaan-m/ | 277k | 1 repo | ~2.1k | Automated safety check: Pass | MIT | today |
| 33 | 33.Ck Persistent per-project memory for Claude Code (Context Keeper) driven by deterministic Node.js /ck commands: init, save, resume, info, list, forget, and v1-to-v2 migrate, plus a SessionStart hook… | affaan-m/ | 277k | 1 repo | ~1.2k | Automated safety check: Pass | MIT | today |
| 34 | 34.Config Gc Garbage collection for your Claude Code configuration. An agent skill from affaan-m/ECC. | affaan-m/ | 277k | 1 repo | ~2k | Automated safety check: Pass | MIT | today |
| 35 | 分析一个陌生的代码库，并生成一个结构化的入门指南，包括架构图、关键入口点、规范和一个起始的CLAUDE.md文件。适用于加入新项目或首次在代码仓库中设置Claude Code时。 | affaan-m/ | 277k | 1 repo | ~1.1k | Automated safety check: Pass | MIT | today |
| 36 | 审核Claude Code上下文窗口在代理、技能、MCP服务器和规则中的消耗情况。识别膨胀、冗余组件，并提供优先的令牌节省建议。 | affaan-m/ | 277k | 1 repo | ~709 | Automated safety check: Pass | MIT | today |
| 37 | 使用Node/TypeScript SDK构建MCP服务器——工具、资源、提示、Zod验证、stdio与可流式HTTP对比。使用Context7或官方MCP文档获取最新API信息。 | affaan-m/ | 277k | 1 repo | ~551 | Automated safety check: Pass | MIT | today |
| 38 | Read a plan document, decompose it into steps, classify each step, and emit the ready-to-paste ECC slash command for that step, carrying the step identifier and scope in the command's own documented… | affaan-m/ | 276k | — | ~4.6k | Automated safety check: Pass | MIT | yesterday |
| 39 | 39.Search First Research-before-coding workflow. An agent skill from affaan-m/ECC. | affaan-m/ | 276k | — | ~1.7k | Automated safety check: Pass | MIT | yesterday |
| 40 | Create and configure hookify rules — markdown files with YAML frontmatter that match bash, file, prompt, or stop events by regex or conditions and show warn/block messages to the agent. | affaan-m/ | 276k | — | ~1.2k | Automated safety check: Notes | MIT | yesterday |
| 41 | Statically review MCP configuration for mutable package references before approval or CI, without executing discovered MCP servers. | affaan-m/ | 276k | — | ~2.6k | Automated safety check: Pass | MIT | yesterday |
| 42 | A skill your agent uses when retrieving Jira tickets, analyzing requirements, updating ticket status, adding comments, or transitioning issues. | affaan-m/ | 276k | 1 repo | ~2.5k | Automated safety check: Warn | MIT | yesterday |
| 43 | Sets up eval-driven development for Claude Code workflows: capability and regression evals, three grader types and pass@k reliability metrics. | affaan-m/ | 276k | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 44 | Claude Codeを永続的なメモリ、スケジュール済み操作、コンピュータ使用、タスクキューイングを備えた完全自動エージェントシステムに変換します。スタンドアロンエージェントフレームワーク（Hermes、AutoGPT）を、Claude Codeのネイティブcrons、dispatch、MCPツール、メモリを活用して置き換えます。ユーザーが継続的な自動操作、スケジュール済みタスク、または自己指令… | affaan-m/ | 276k | — | ~859 | Automated safety check: Pass | MIT | yesterday |
| 45 | 将 Claude Code 转变为具有持久记忆、定时操作、计算机使用和任务队列的完全自主代理系统。通过利用 Claude Code 的原生定时任务、调度、MCP 工具和记忆，取代独立的代理框架（Hermes、AutoGPT）。当用户需要持续自主操作、定时任务或自我导向的代理循环时使用。 | affaan-m/ | 276k | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 46 | 自動Claude Codeループのパターンとアーキテクチャ — シンプルな順序パイプラインからRFC駆動マルチエージェントDAGシステムまで。 | affaan-m/ | 276k | — | ~545 | Automated safety check: Pass | MIT | yesterday |
| 47 | エージェント、スキル、MCPサーバー、ルールにわたってClaude Codeのコンテキストウィンドウ消費を監査します。肥大化、冗長なコンポーネントを特定し、優先順位付けされたトークン節約の推奨事項を生成します。 | affaan-m/ | 276k | — | ~981 | Automated safety check: Pass | MIT | yesterday |
| 48 | 48.Ecc Guide 在回答之前先读取仓库的实时状态，引导用户了解 ECC 当前的 agents、skills、命令、hooks、规则、安装配置档案以及项目接入流程。 | affaan-m/ | 276k | — | ~837 | Automated safety check: Pass | MIT | yesterday |
