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.
Overview
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.
README
boss-skill
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: · AtomGit mirror:
Boss is an expert-squad 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 enforces hard quality contracts per role, produces replayable artifacts, and chains stages automatically — start anywhere, it runs the rest until you say stop.
Boss works with Claude Code, Codex, OpenClaw, Antigravity, Hermes, and DeepSeek Harness.
DeepSeek Harness
Boss also ships a DeepSeek Harness bundle, published to npm as
dsh-boss-mode. It adds a selectable
Boss Expert Squad preset and a right sidebar that reads live Agent Teams members and
tasks.
dsh plugin --profile desktop add dsh-boss-mode
You can also install the tarball from the
GitHub Release
or add the
raw DSH market index.
Then restart DeepSeek Harness, create a new session, and pick Boss Expert Squad. Enable
DSH’s experimental Agent Teams profile when you want spawn_teammate, the native roster,
and the task board.
Why Boss
Prompt-only orchestration can sound organized, but it usually cannot prove that the plan was followed, tests were run, or gates passed. Boss is built around evidence and hard contracts:
- Hard quality contracts: every role has a non-negotiable requirements table (e.g. PRD must have Given-When-Then scenarios; architecture must compare at least two options; QA must record verified or honestly-unverified evidence). Failed contracts block the next stage unless you explicitly override.
- Artifact-driven: every stage writes a real file under
.boss//. Progress is judged by artifacts on disk, not by what the agent claims. - Continuation chain: start at any stage (
/boss:pm,/boss:dev, …) and Boss auto-runs every downstream stage untilshipor until you stop it. No manual hand-offs. - Engineering principles: the squad shares ten principles — prove it works, fix root causes, build the lever, model the domain, boundary discipline, sequence verifiable units, test behavior, minimize reader load, structured experience, autonomous rules. Each agent cites the principle it applies.
- TDD by default: development stages must write a failing test first, watch it go RED, then write the minimum code to make it GREEN.
- Zero-network by default: no telemetry, no phone-home, no remote LLM proxy. The only network surface is an opt-in loopback preview server bound to
127.0.0.1for UI prototyping. See PRIVACY.md. - Deterministic evals: captured transcripts are scored without calling a real LLM.
Expert Squad Commands
Boss is not a single monolithic command. Each slash command is an entry point; by default it auto-runs all downstream stages.
| Command | Starts at | Auto-runs through | Use when |
|---|---|---|---|
/boss |
PM | full chain → ship | Go from idea to shippable work |
/boss:pm |
PM | Architect → … → Ship | Start from requirements |
/boss:architect |
Architect | UI → … → Ship | You have a spec, need design |
/boss:ui |
UI Designer | Review → … → Ship | You have architecture, need UI |
/boss:review |
Tech Lead | Tasks → … → Ship | Need technical review + plan |
/boss:tasks |
Scrum Master | Dev → QA → Ship | Need task breakdown |
/boss:dev |
Frontend/Backend | QA → Ship | Start implementation |
/boss:qa |
QA | Ship | Need test evidence |
/boss:ship |
DevOps | (end) | Deploy only |
The full chain:
pm → architect → ui → review → tasks → dev → qa → ship
Stop the chain by saying “stop”, “only do this step”, or passing --stop-after .
Quick Start
1. Install
Boss is a skill you install into your coding agent. The skill itself is distributed through marketplaces (no global binary); the DeepSeek Harness bundle ships separately as the npm package dsh-boss-mode.
Claude Code — plugin marketplace (recommended):
/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
DeepSeek Harness — npm plugin:
dsh plugin --profile desktop add dsh-boss-mode
Then restart DeepSeek Harness, create a new session, and pick Boss Expert Squad in the mode picker (see DeepSeek Harness).
2. Try It On A Project You Already Have
The lowest-cost first run is a read-only review against existing code:
/boss:review
You get tech-review.md (and plan.md) under .boss// with risks, findings, and severity. Nothing else in your repo is touched.
Want verifiable test evidence instead? /boss:qa runs the tests and writes qa-report.md.
3. Run The Full Pipeline
Inside your coding agent:
/boss Build a local personal todo app --skip-ui
--skip-uiskips the UI design stage (pure API/CLI projects).--quickskips routine clarification prompts.
4. Inspect Results
Artifacts live under .boss//:
.boss/todo-app/
├── prd.md
├── architecture.md
├── ui-spec.md
├── ui-design.json
├── tech-review.md
├── plan.md
├── tasks.md
├── qa-report.md
└── deploy-report.md
Each Markdown artifact starts with a ## 摘要 (summary) section so downstream agents can read the conclusion first.
Workflow
User request
→ requirement clarification (unless --quick)
→ PM: requirement discovery → prd.md
→ Architect: system design → architecture.md
→ UI Designer: UI/UX spec → ui-spec.md + ui-design.json (skip with --skip-ui)
→ Tech Lead: technical review + implementation plan → tech-review.md + plan.md
→ Scrum Master: task breakdown → tasks.md
→ Frontend / Backend: TDD implementation
→ QA: test execution, bug reports, evidence → qa-report.md
→ DevOps: build, deploy, health checks → deploy-report.md
Roles & Artifacts
| Role | Responsibility | Artifact |
|---|---|---|
| PM | Requirement discovery, PRD, hidden needs, edge cases | prd.md |
| Architect | System architecture, technical design, APIs | architecture.md |
| UI Designer | UI/UX spec, renderable design JSON, HTML prototype | ui-spec.md, ui-design.json |
| Tech Lead | Technical review, risk assessment, implementation plan | tech-review.md, plan.md |
| Scrum Master | Task breakdown and acceptance criteria | tasks.md |
| Frontend | UI implementation, TDD, frontend tests | source code |
| Backend | API, storage, TDD, backend tests | source code |
| QA | Test execution, bug reports, verification evidence | qa-report.md |
| DevOps | Build, deployment, health checks | deploy-report.md |
Quality Contract
Boss has two layers of quality control:
- Hard requirements per role: each agent’s prompt defines a non-negotiable requirements table. The agent self-checks before handing off; a failed contract blocks the next stage.
- Quality gates: real commands whose verdicts are recorded in the stage artifact.
| Gate | Stage | Checks |
|---|---|---|
| Gate 0 (code quality) | After dev, before QA | TypeScript/lint pass, no high-severity dependency vulnerabilities |
| Gate 1 (testing) | After QA, before deploy | Unit + integration tests pass, coverage ≥ 70%, no P0/P1 bugs, E2E tests written |
| Gate 2 (performance) | Before web deploy | Lighthouse ≥ 80, API P99 < 500ms (web projects only) |
When To Use Boss
| 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// artifacts are valuable |
Tasks with a complete existing spec where you only need a quick patch |
| Teams that want repeatable quality 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.
Security & Privacy
Boss is local-first and makes no outbound network requests by default. The only network surface is an opt-in, loopback-only (127.0.0.1) HTML prototype server used during the UI design stage.
Release provenance lives in .agents/plugins/provenance.json. It pins the repository HTTPS URL, immutable source commit SHA, publisher identity, and SHA-256 digests for plugin manifests. Verify it with:
npm run provenance:verify
See PRIVACY.md for the full data and network boundary.
Pipeline Artifacts
.boss//
├── prd.md # PM — product requirements
├── architecture.md # Architect — system design
├── ui-spec.md # UI Designer — UI/UX spec (skipped with --skip-ui)
├── ui-design.json # UI Designer — renderable design JSON
├── tech-review.md # Tech Lead — technical review
├── plan.md # Tech Lead — implementation plan
├── tasks.md # Scrum Master — task breakdown
├── qa-report.md # QA — test evidence
└── deploy-report.md # DevOps — deployment record
Evals
Boss evals score captured fixtures without starting a real LLM:
npm run evals
npm run evals:release
The release eval includes release-evidence and pipeline-compliance checks — it verifies artifact recording, avoidance of deprecated runtime commands, and expert-squad orchestration behavior.
See test/evals/README.md.
Development
Requirements:
- Node.js >= 22.18
Setup:
git clone https://github.com/echoVic/boss-skill.git
cd boss-skill
npm install
npm run typecheck
npm test
Useful scripts:
npm run typecheck # tsc --noEmit
npm test # vitest (unit + skill behavior + evals)
npm run test:skills # skill behavior tests only
npm run evals # deterministic transcript evals
npm run lint # biome ci
Repository Layout
boss-skill/
├── skill/ # Skill bundle installed into coding agents (self-contained)
│ ├── SKILL.md # Main orchestration entry (invariants + index)
│ ├── agents/ # Role prompts (boss-pm, boss-architect, ...)
│ ├── commands/ # Slash commands (/boss, /boss:pm, ...)
│ ├── references/ # Shared methodology (principles, quality-gate, ...)
│ ├── skills/ # Per-domain methodology skills (pm/, qa/, devops/, ...)
│ └── templates/ # Artifact templates (.md.template)
├── test/ # Vitest, skill behavior, and eval tests
├── scripts/ # release.js, provenance.js
├── docs/ # Historical specs, plans, reports
├── examples/ # Example projects
├── .claude-plugin/ # Claude Code plugin manifest + marketplace
├── .codex-plugin/ # Codex plugin manifest + marketplace
├── .agents/plugins/ # Repo-scoped plugin marketplace + provenance
├── tsconfig.json # Typecheck-only config (no emit)
└── package.json # Private dev workspace (never published)
Release
Use the release script so version numbers stay synchronized across package metadata and skill/plugin manifests:
npm run release -- patch
npm run release -- minor
npm run release -- major
npm run release -- 4.1.0
npm run release -- 4.1.0 --dry-run
The release script checks for a clean worktree, runs the full verification chain (typecheck, lint, test), syncs versions across all manifests, verifies consistency, creates a commit and tag, and pushes. Release is the git tag: marketplaces read the repository — there is no npm publish step and no build step. The DeepSeek Harness bundle is versioned separately and published to npm by a tag-triggered workflow (.github/workflows/dsh-publish.yml). See docs/dsh-release.md for the full checklist.
See CONTRIBUTING.md.
Design
Boss is inspired by BMAD: Breakthrough Method of Agile AI-Driven Development, and by the “write less, higher quality code” philosophy. The expert-squad model keeps the harness lean — no runtime state machine, no event sourcing, no hooks — while preserving hard quality contracts and artifact-driven collaboration.
Read more in DESIGN.md, skill/references/bmad-methodology.md, and skill/references/principles.md.
Star History
License
MIT
Recommended Tools
Try a different keyword or remove a filter.
Install
npx skillfish add echovic/boss-skill