claude-orchestrator-skills
Self-configuring agent skills (SKILL.md) for Claude Code, Cursor, and more — they ask what you do, then adapt. Install: npx skills add DylXBT/claude-orchestrator-skills
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/dylxbt--claude-orchestrator-skills)HTML
<a href="/listings/dylxbt--claude-orchestrator-skills"><img src="/api/listings/dylxbt--claude-orchestrator-skills/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Install the whole set:
npx skills add DylXBT/claude-orchestrator-skills
Or just one:
npx skills add DylXBT/claude-orchestrator-skills/context-brain
This drops the skill(s) into your agent's skills directory (e.g. `~/.claude/skills/`). In Claude Code, type the skill name or just describe the task and Claude loads it.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 43 lines
- # Claude Orchestrator Skills
- A small, curated set of **self-configuring** [Agent Skills](https://code.claude.com/docs/en/skills) for Claude Code, Codex, Cursor, and other `SKILL.md`-compatible agents.
- These aren't tied to any one job. Every skill **starts by asking what you do** — your role, your domain, your goals — and then adapts. The same skill works whether you're in HR, design, sales, ops, marketing, or engineering. The value is the *architecture*, not the examples.
- They mirror the [Orchestrator Academy](https://claude-orchestrator-academy.vercel.app) curriculum: each skill is the reusable tool behind one lesson.
- ## Install
- Install the whole set:
- ```bash
- npx skills add DylXBT/claude-orchestrator-skills
- ```
- Or just one:
- ```bash
- npx skills add DylXBT/claude-orchestrator-skills/context-brain
- ```
- This drops the skill(s) into your agent's skills directory (e.g. `~/.claude/skills/`). In Claude Code, type the skill name or just describe the task and Claude loads it.
- ## The skills
- | Skill | What it does |
- | --- | --- |
- | [`prompt-architect`](./prompt-architect) | Turn a vague request into a reliable, reusable 5-part prompt. |
- | [`context-brain`](./context-brain) | Build a reusable context pack so Claude reasons from *your* world, not generically. |
- | [`skill-author`](./skill-author) | Package a task you repeat into your own `SKILL.md` skill. |
- | [`connector-setup`](./connector-setup) | Plan a safe, least-privilege way to connect your real tools to Claude. |
- | [`pipeline-builder`](./pipeline-builder) | Break a big task into a clean pipeline where each step feeds the next. |
- | [`work-engine`](./work-engine) | Stand up a repeatable brief → deliverables → report → learnings loop. |
- | [`orchestrator`](./orchestrator) | Assemble the pieces above into one system you actually run. |
- ## How they work
- Each folder is a standard Agent Skill: a `SKILL.md` with YAML frontmatter (`name`, `description`) and instructions. The instructions are written to **interview you first, then build** — so the output is yours, not a template you have to find-and-replace.
- ## License
- MIT © DylXBT
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.