https://github.com/danielvm-git/bigpowers
59 agent skills for high-integrity, spec-driven, test-first software development by solo developers. bigpowers provides a prescriptive, vertical-slice methodology for building software with AI agents (Claude Code, Gemini CLI, Cursor). It bridges the gap between raw LLM capabilities and professional engineering standards.
https://github.com/danielvm-git/bigpowers
ai-agents automation bmad claude-code clean-code cursor-rules devops documentation-as-code gemini-cli productivity software-engineering solo-developer spec-driven-development tdd
Last synced: about 1 hour ago
JSON representation
59 agent skills for high-integrity, spec-driven, test-first software development by solo developers. bigpowers provides a prescriptive, vertical-slice methodology for building software with AI agents (Claude Code, Gemini CLI, Cursor). It bridges the gap between raw LLM capabilities and professional engineering standards.
- Host: GitHub
- URL: https://github.com/danielvm-git/bigpowers
- Owner: danielvm-git
- License: mit
- Created: 2026-04-24T21:03:16.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2026-06-20T19:36:17.000Z (6 days ago)
- Last Synced: 2026-06-20T20:20:52.611Z (6 days ago)
- Topics: ai-agents, automation, bmad, claude-code, clean-code, cursor-rules, devops, documentation-as-code, gemini-cli, productivity, software-engineering, solo-developer, spec-driven-development, tdd
- Language: Shell
- Homepage: https://github.com/danielvm-git/bigpowers
- Size: 4.34 MB
- Stars: 3
- Watchers: 0
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- License: LICENSE
- Audit: audit-code/HEURISTICS.md
- Agents: docs/AGENTS.md
Awesome Lists containing this project
README
# bigpowers β Best-in-Class Agentic Skills



**70 agent skills for high-integrity, spec-driven, test-first software development by solo developers.**
`bigpowers` provides a prescriptive, vertical-slice methodology for building software with AI agents (Claude Code, Gemini CLI, Cursor, pi). It bridges the gap between raw LLM capabilities and professional engineering standards.
Published on npm: [bigpowers@2.0.0](https://www.npmjs.com/package/bigpowers)
---
## π Quick Start
### npm (recommended)
```bash
# One-shot setup β downloads, syncs artifacts, and links skills to your tools
npx bigpowers
# Or install globally and run the setup command anytime
npm install -g bigpowers
bigpowers
```
Both commands sync skill artifacts and link them to Claude Code, Gemini CLI, and Cursor (see [Prerequisites](#-prerequisites)).
### From source (contributors)
```bash
git clone https://github.com/danielvm-git/bigpowers.git && cd bigpowers
npm install # runs postinstall: sync + link
# or manually:
bash scripts/install.sh
npm run sync
```
---
## π Prerequisites
- **Bash**: Required for all scripts.
- **Node.js**: v14+ (required for npm/npx).
- **jq**: (Highly Recommended) Used for robust configuration of tool settings.
- **AI Tools**: One or more of:
- [Claude Code](https://claude.ai/code)
- [Gemini CLI](https://github.com/google/gemini-cli)
- [Cursor](https://cursor.sh/)
- [pi](https://pi.dev/) β coding agent harness
---
## π Maintenance (Update & Uninstall)
### Update
**npm install:**
```bash
npm update -g bigpowers
bigpowers # re-sync and refresh symlinks
```
**git clone:**
```bash
git pull
npm run sync
```
*Install uses symlinks β re-running setup refreshes links without duplicating files.*
### Uninstall
**npm install:**
```bash
bash "$(npm root -g)/bigpowers/scripts/install.sh" --uninstall
npm uninstall -g bigpowers
```
**git clone:**
```bash
bash scripts/install.sh --uninstall
```
### Reinstall
```bash
npx bigpowers
# or, if installed globally:
bigpowers
```
---
## π pi Support
bigpowers generates pi Agent Skills and prompt templates alongside Cursor and Gemini artifacts via `sync-skills.sh`.
### Install as a pi package
```bash
# Clone and sync to generate pi artifacts
cd bigpowers
bash scripts/sync-skills.sh
# Install from local path as a pi package
pi install .
# Or install as a pi npm package (once published with pi-package keyword)
pi install npm:bigpowers
```
**What you get:**
- **62 pi skills** in `.pi/skills/` β loaded automatically into pi's system prompt as ``
- **62 pi prompt templates** in `.pi/prompts/` β slash commands like `/survey-context`, `/plan-work`
- **pi package manifest** in `.pi/package.json` β enables `pi install` with auto-discovery
Skills are loaded on-demand via progressive disclosure: only descriptions are always in context; the full SKILL.md loads when the agent reads it. Prompt templates expand in pi's editor with autocomplete.
## π§ MCP Server (Model Context Protocol)
bigpowers ships an MCP server that exposes all skills as callable MCP tools. Agents can discover and invoke skills dynamically instead of relying on a static system prompt.
### Start the server
```bash
node scripts/mcp-server.js
```
### Add to Claude Code
```bash
claude mcp add bigpowers node /path/to/bigpowers/scripts/mcp-server.js
```
Or add manually to `.claude/settings.json`:
```json
{
"mcpServers": {
"bigpowers": {
"command": "node",
"args": ["/path/to/bigpowers/scripts/mcp-server.js"]
}
}
}
```
### Available MCP tools
| Tool | Description |
|------|-------------|
| `bigpowers_list_skills` | List all 70 skills with name, description, phase. Optional `phase` filter. |
| `bigpowers_get_skill` | Get full SKILL.md content for any skill by name. |
| `bigpowers_search_skills` | Keyword/semantic search β returns ranked matches for a query. |
| `bigpowers_get_state` | Get current `specs/state.yaml` (active flow, epic, step). |
| `bigpowers_invoke_skill` | Get skill instructions with optional context for agent invocation. |
---
## π The v2.0.0 Lifecycle
Every project follows the **orchestrate-project 6-phase model** (full SOP: [`docs/WORKFLOW-SOP-v2.md`](docs/WORKFLOW-SOP-v2.md)):
```
ONE TIME seed-conventions (CLAUDE.md, .claude/, .gemini/, agents/, skill sync)
β
ONCE/PROJECT orchestrate-project
β
ββ Ph1 DISCOVER survey-context, research-first, elaborate-spec
ββ Ph2 ELABORATE model-domain, grill-me, define-language, deepen-architecture
ββ Ph3 PLAN scope-work, slice-tasks, plan-work β release-plan.yaml (BCP baseline)
ββ Ph4 BUILD build-epic Γ N stories
β
β Per story β 8-step build-epic cycle:
β 1. survey-context β stamps story_start in state.yaml
β 2. plan-work β [BCP N] tasks + verify: commands
β 3. kickoff-branch β worktree + feature branch
β 4. develop-tdd β RED β GREEN β REFACTOR
β 5. verify-work β UAT gate
β 6. audit-code β quality gate β₯ 94%
β 7. commit-message β Conventional Commits + semver
β 8. release-branch β land to main; writes story_end + cycle-times.yaml
β
ββ Ph5 VERIFY run-evals, verify-work (project-level)
ββ Ph6 RELEASE semantic-release β v1.0.0 MVP tag
```
**Semver:** projects start at `0.0.0-Ξ²`; each `feat:` story β minor bump; developer declares MVP β `1.0.0`.
**BCP accounting:** every task labeled `[BCP N]`; story total in `state.yaml`; BCP/hr logged to `specs/metrics/cycle-times.yaml`.
**next_skill signaling:** each critical-path skill writes `handoff.next_skill` to `state.yaml`. Call `survey-context` after any interruption to resume exactly where you left off.
---
## π Hierarchy of Truth
| Level | Document | Responsibility |
| :--- | :--- | :--- |
| **Vision** | `docs/PRINCIPLES.md` | Philosophical foundations and evolution. |
| **Context** | `specs/tech-architecture/TECH_STACK_LATEST.md` | Tech stack, architecture, and domain notes. |
| **Scope** | `specs/product/SCOPE_LATEST.yaml` | In-scope / out-of-scope and success criteria. |
| **Vision** | `specs/product/VISION_LATEST.yaml` | North star and initiative success criteria. |
| **Decisions** | `specs/adr/` | Architectural Decision Records (irreversible choices). |
| **Roadmap** | `specs/release-plan.yaml` + `specs/epics/` | WSJF-prioritized epics and stories with BCP baseline. |
| **Current** | `specs/state.yaml` | Session flow, active epic, `handoff.next_skill`, timestamps. |
| **Metrics** | `specs/metrics/cycle-times.yaml` | Per-story BCPs, cycle minutes, BCP/hr (v2.0.0). |
| **Index** | `SKILL-INDEX.md` | Canonical list of all active skills. |
| **Style** | `CONVENTIONS.md` | Coding, testing, and naming standards. |
---
## π Project Structure
- `scripts/`: Installation, syncing, and compliance tools.
- `specs/`: YAML cockpit β `state.yaml`, `release-plan.yaml`, `epics/`, `execution-status.yaml`, `requirements/`.
- `specs/metrics/`: Cycle-time ledger (`cycle-times.yaml`) β per-story BCPs, timestamps, BCP/hr (v2.0.0).
- `dashboard/`: Live monitoring tool β TUI (`npm run dashboard`) and web (`npm run dashboard:web`, port 7742).
- `docs/`: Guides including `WORKFLOW-SOP-v2.md` (full SDLC SOP) and `using-bigpowers.md`.
- `docs/references/`: Theoretical foundations (Uncle Bob, Ousterhout, Karpathy, etc.).
- `[skill-name]/`: Source files for each of the 70 skills.
---
## π€ References & Credits
`bigpowers` stands on the shoulders of giants. It integrates patterns from:
- **Akita**: Architectural patterns.
- **BMAD**: Bold, Minimal, Actionable, Durable documentation.
- **Clean Code**: Robert C. Martin (Uncle Bob).
- **A Philosophy of Software Design**: John Ousterhout.
- **GSD (Get Stuff Done)**: Pragmatic workflow frameworks.
---
## π License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
---
*βSimplicity is the ultimate sophistication, but integrity is the ultimate requirement.β*