by echoVic
Boss Skill - BMAD 全自动研发流水线(多 Agent 编排)
# Add to your Claude Code skills
git clone https://github.com/echoVic/boss-skillLast scanned: 5/22/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-22T07:44:52.014Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}See how boss-skill compares with popular alternatives.
boss-skill is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by echoVic. Boss Skill - BMAD 全自动研发流水线(多 Agent 编排). It has 543 GitHub stars.
Yes. boss-skill passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/echoVic/boss-skill" and add it to your Claude Code skills directory (see the Installation section above).
boss-skill is primarily written in TypeScript. It is open-source under echoVic on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh boss-skill against similar tools.
No comments yet. Be the first to share your thoughts!
From $49 · 30 days · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
Languages / 语言 / 言語 / 언어 / Idiomas / Langues: English · 中文 · 日本語 · 한국어 · Español · Français · Português

This project is part of the AtomGit G-Star Incubation Program. GitHub is the canonical repository; AtomGit provides an automatically synchronized mirror for faster access in China. Please submit issues and pull requests on GitHub.
GitHub: https://github.com/echoVic/boss-skill · AtomGit mirror: https://atomgit.com/echoVic/boss-skill
Boss is an auditable agent-team workflow for coding agents. It turns one coding agent into a structured engineering team: PM, Architect, UI Designer, Tech Lead, Scrum Master, Frontend, Backend, QA, and DevOps. Unlike prompt-only agent teams, Boss adds runtime state, append-only events, quality gates, deterministic evals, hooks, and replayable artifacts.
Boss works with Claude Code, Codex, OpenClaw, Antigravity, and Hermes.
Prompt-only orchestration can sound organized, but it usually cannot prove that the plan was followed, tests were run, gates passed, or state was not hallucinated. Boss is built around evidence:
127.0.0.1. A source-level network-boundary test fails CI if anyone reintroduces an outbound client. See PRIVACY.md.argv (waves.json), never through a shell. Cloning a malicious repository cannot smuggle commands via tasks.md..boss/<feature>/.meta/events.jsonl and projected into read-only execution state.boss gate final and boss doctor fail when a completed stage carries a failed gate. Enforcement still relies on the orchestrating agent honoring the protocol; the CLI makes the verdict checkable, not unavoidable..boss/<feature>/.--describe, dry runs, bounded fields, and structured errors.boss doctor to confirm the resolved runtime, install locations, event-stream health, and network boundary — the zero-network claim is auditable, not just asserted.Boss is not a single monolithic command. You can run one role against an existing project, or run the full pipeline from idea to delivery.
| Command | What it does | Use when |
|---|---|---|
/boss |
Full 4-stage pipeline | You want to go from idea to shippable work |
/boss:plan |
PM + Architect planning | You want PRD and architecture before implementation |
/boss:review |
Tech Lead review | You need a read-only code, PR, or design review |
/boss:qa |
QA plus gates | You need verifiable test evidence |
/boss:ship |
DevOps build and deployment checks | You are ready to ship |
/boss:extend |
Custom agent, pack, or gate | You want to adapt Boss for your team |
/boss:upgrade |
Update Boss Skill and re-merge hooks | You want the latest marketplace version and hook config |
Boss is a skill you install into your coding agent — not a tool that installs other skills. Distribution is marketplace-only: no npm package, no global binary. The skill ships with its own CLI (skill/cli/), which hooks and the agent invoke through node.
Claude Code — plugin marketplace (recommended; hooks come wired):
/plugin marketplace add echoVic/boss-skill
/plugin install boss@boss-skill
Codex — plugin marketplace:
codex plugin marketplace add echoVic/boss-skill
Then open the plugin browser (/plugins) and install boss.
Any agent — via the skills CLI (vercel-labs/skills, skills.sh):
npx skills add echoVic/boss-skill
It discovers boss from the repo, prompts for target agent / scope (project vs global) / install method, and records a skills-lock.json you can commit. Boss ships a single skill root, so the picker shows just boss — its internal methodologies travel with it.
For Codex and other copy-based installs, wire up the Boss hooks with the bundled CLI:
node <installed-skill>/cli/bin/boss.mts install
The lowest-cost first run is a single role against existing code. It reads, it does not write:
/boss:review
You get tech-review.md under .boss/<feature>/ with risks, findings and severity. Nothing else in your repo is touched.
Want verifiable test evidence instead? /boss:qa runs the tests and the gates, and writes qa-report.md.
Inside your coding agent:
/boss Build a local personal todo app --roles core --skip-deploy
--roles core uses PM, Architect, Dev, and QA.--skip-deploy stops after implementation and test evidence.Boss ships its own CLI inside the skill — no npm install, no PATH setup. In the snippets below, <skill> is the directory that contains SKILL.md (for Claude Code plugin installs: <plugin-root>/skill; for copied installs, e.g. ~/.codex/skills/boss).
node <skill>/cli/bin/boss.mts status todo-app --json
node <skill>/cli/bin/boss.mts runtime inspect-pipeline todo-app
Expected artifact layout:
.boss/todo-app/
├── design-brief.md
├── prd.md
├── architecture.md
├── tasks.md
├── qa-report.md
└── .meta/
├── events.jsonl
├── execution.json
└── workflow-plan.json
| Good fit | Poor fit |
|---|---|
| New features that need requirements, design, implementation, tests, and delivery evidence | One-line fixes or tiny local edits |
| API, full-stack, UI, or medium-sized product work | Pure code reading or explanation |
Work where .boss/<feature>/ artifacts are valuable |
Tasks with a complete existing spec where you only need a quick patch |
| Teams that want repeatable gates and audit trails | Work that does not need coordination or review evidence |
Rule of thumb: if you do not need a traceable .boss/ folder, you probably do not need the full /boss pipeline. Use a single role or let your coding agent edit directly.
The CLI ships inside the skill, so a marketplace install always carries it. When node is unavailable or the CLI cannot be located, the workflow degrades to Markdown artifacts under .boss/<feature>/ instead of the event stream. The CLI is the auditability upgrade: event sourcing, replayable resume, deterministic evals, runtime gates, and structured diagnostics.
Boss does not mean "install once and get guaranteed autonomous delivery." It provides a runtime workflow and evidence gates; the active coding agent still has to follow the Boss protocol.
Marketplace installs copy (or link) the whole skill/ directory. The CLI ships as TypeScript source at <skill>/cli/bin/boss.mts and is executed directly by Node.js >=22.18 (native type stripping) — there is no build step, no npm package, and no global boss binary. Hooks reference it by full path.
Useful commands (run through the bundled CLI):
node <skill>/cli/bin/boss.mts install --dry-run
node <skill>/cli/bin/boss.mts uninstall
node <skill>/cli/bin/boss.mts path
node <skill>/cli/bin/boss.mts --version
Auto-detected targets for boss install:
| Agent | Detection | Install method |
|---|---|---|
| OpenClaw | ~/.openclaw/ |
Copy to ~/.openclaw/skills/boss/ and inject metadata |
| Codex | ~/.codex/ |
Copy to ~/.codex/skills/boss/, inject metadata, merge hooks |
| Antigravity | ~/.gemini/antigravity/ |
Copy to Antigravity skills directory and inject metadata |
| Hermes | ~/.hermes/ |
Copy to ~/.hermes/skills/boss/ and inject metadata |
| Claude Code | Always available | Plugin marketplace (see Quick Start) |
Boss targets Node.js >=22.18 and runs on Linux, macOS, and Windows. The CLI ships inside
the skill as TypeScript source that Node executes directly (native type stripping — no build
step), shells out only through spawnSync with explicit argument arrays (never
shell: true), and resolves npm/npx to their .cmd variants on Windows, so there is
no POSIX-only assumption in the core pipeline.
Two capabilities depend on optional external tools and degrade gracefully when they are absent:
git and a git work