Archived 2026-10-23 · Source updated 2026-10-12 · License: MIT. Check the original repository for the latest version.
SKILL.md instructions
# Run Tests
Run tests only on files touched in this branch:
```bash
git diff --name-only develop..HEAD
```
Map to scope:
- `apps/ledger-live-desktop/` → `pnpm desktop test:jest "path/to/file"`
- `apps/ledger-live-mobile/` → `pnpm mobile test:jest "path/to/file"`
- `libs/<name>/` → `pnpm --filter <package-name> test "path/to/file"`
Fix failures one at a time — never skip or comment out a test.
Report: `✅ X suites pass` or `❌ failure in ... → Fixed: [description]`
Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space…
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent…
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React,…
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML…