Agentcfg Manage
Manage agent skills and configuration through the agentcfg CLI. Use when the user asks in natural language to inspect skills/MCP/plugins/hooks, centralize or organize scattered skills, install a local skill, link a shared skill into agent harnesses, update installed skills, or safely remove skill links/store copies.
Install
npx skills add Phoobobo/herdr-agent-config-manager --skill agentcfg-managegit clone --depth 1 https://github.com/Phoobobo/herdr-agent-config-manager.git /tmp/herdr-agent-config-manager
mkdir -p ~/.claude/skills
cp -r /tmp/herdr-agent-config-manager/skills/agentcfg-manage ~/.claude/skills/agentcfg-managePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Agentcfg Manage Translate the request into `agentcfg` commands. Prefer machine-readable output for inspection and plans; never open the interactive TUI from an agent workflow. ## Workflow 1. Confirm `agentcfg` exists with `command -v agentcfg`. 2. Inspect current state when the requested mutation depends on it: ```bash agentcfg detect --json ``` 3. For add, organize, fanout, and delete, run the command without `--apply` first and inspect its plan. Show conflicts or skipped real directories. 4. Add `--apply` only when the user explicitly requested the mutation or confirms the plan. 5. Report the command result and any skipped/error items. ## Commands
Details
- Skill name
agentcfg-manage- Repository
- Phoobobo/herdr-agent-config-manager
- Path
skills/agentcfg-manage/SKILL.md- Repo updated
- 6 September 2026
FAQ
What does the Agentcfg Manage skill do?
Manage agent skills and configuration through the agentcfg CLI. Use when the user asks in natural language to inspect skills/MCP/plugins/hooks, centralize or organize scattered skills, install a local skill, link a shared skill into agent harnesses, update installed skills, or safely remove skill links/store copies.
How do I install the Agentcfg Manage skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Phoobobo/herdr-agent-config-manager --skill agentcfg-manage. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Agentcfg Manage popular?
It lives in Phoobobo/herdr-agent-config-manager, which has 9 GitHub stars and 0 forks.
Related skills
AI Ready
9viktor-silakov/ai-ready
Analyzes repositories for AI agent development efficiency. Scores 8 aspects (documentation, architecture, testing, type safety, agent instructions, file structure, context optimization, security) with ASCII dashboards. Use when evaluating AI-readiness, preparing codebases for Claude Code, or improving repository structure for AI-assisted development.
Product Decision Agent
6atdy/maoxuan-product-agent
中文产品决策 Agent。用于中国大陆互联网产品、运营、增长、商业化、数据、项目推进和组织协作场景:产品规划、需求分析、PRD、需求优先级、排期、版本规划、Roadmap、MVP、灰度、上线、迭代、增长停滞、拉新、投放、渠道、裂变、CAC、LTV、ROI、留存、转化、DAU/MAU、GMV、漏斗、社区运营、内容供给、创作者、用户运营、活动运营、私域、会员、定价、指标异常、数据口径、埋点、A/B Test、用户反馈、客服/销售反馈、竞品冲击、资源不足、项目延期、需求反复、老板临时插需求、跨部门协作、团队冲突、OKR/KPI、目标拆解、复盘等。触发时像资深互联网产品负责人一样,先判断真实问题、当前阶段、核心阻塞、关键约束、相关方和证据充分性,再给出最值得执行的下一步。默认中文回答,不讲理论、不引用原文、不解释历史、不暴露后台方法来源。
Chaos Agent
9jasnonaz/chaos-agent
Chaos agent for skills — a vigilance-training layer that keeps humans reviewing AI output instead of rubber-stamping it. Consult this skill on EVERY substantive request (code, analysis, writing, SQL, configs, explanations — anything with a checkable answer). 95% of requests get your genuine best work; a deterministic 5%, chosen by hash, get a polished answer containing exactly one subtle, findable flaw. Trigger on all real work; skip only trivial chit-chat.
Building an Exo
10Exponential-Organizations/building-an-exo-skill
Apply ExO 3.0, the Intelligence Stack, and the REWRITE Playbook (OS Outline v25) to redesign a firm around AI. Use when a founder or CEO rebuilds as an AI-native firm in Direct Mode (≤50) or Edge Mode (>50) with a board-mandated Edge Twin. v25 adds Ch8 data-plane inversion (decision traces, log ownership) and Nadella frontier-ecosystem validation (human capital directs token capital). v24 adds Appendix A diagnostics (Readiness Score, Matrix, Miura-Ko, Dabbling, Third Anchor, Tokenmaxxing), the Sarbanes-Oxley Moment, Vendor Shortcut vs SAP's Autonomous Enterprise, the Domain Collapse Engine, Ju
Eval Driven Dev
9yiouli/pixie-qa
Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce a concrete action plan for improvements. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals, evaluate, benchmark, fix wrong behaviors, improve quality, or do quality assurance for any Python project that calls an LLM model.
Amazon Connect
8JiteshGaikwad/claude-skills
Amazon Connect contact center — flows, routing, Contact Lens, metrics, Customer Profiles, Cases, Q Connect, AI agents, Lambda integration, streaming, EventBridge, and SDK/API reference. Use when working on Amazon Connect configuration, contact flows, real-time/historical metrics, Contact Lens analytics, agent workspace development, Kinesis streaming, or AWS SDK v3 JavaScript/TypeScript code that interacts with Connect services.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.