Core

Guide for Git operations including commits, branches, rebasing, and conflict resolution. Use when working with version control, creating commits, managing branches, or resolving merge conflicts.

Test-Driven Development methodology and discipline. Use when writing code test-first, practicing Red-Green-Refactor, building walking skeletons, applying outside-in development, or sequencing tests for incremental design.

Guide for using Bees, a lightweight SQLite-backed local issue tracker. Use when managing issues, tracking dependencies, exporting for AI context, or running local-first project management.

Guide for using mise to manage development tools and runtime versions. Use when configuring project tooling, managing environment variables, or defining project tasks.

Guide for using Nushell for structured data pipelines and scripting. Use when writing shell scripts, processing structured data, or working with cross-platform automation.

Secret detection and credential scanning using gitleaks. Use when scanning repositories for leaked secrets, API keys, passwords, tokens, or implementing pre-commit security checks.

Guide for using Apple Container CLI to run Linux containers on Apple silicon Macs (macOS 26+). Use when managing OCI containers, building images, configuring networks/volumes, running long-lived Linux machines with container machine, or working with container system services on macOS.

Engineering restraint — stop at the first rung that already solves the problem before writing new code. Use when planning, authoring tests, implementing, or reviewing any code change; loads as a standing principle alongside TDD and twelve-factor.

Generic epic-to-PR agent workflow (codename Forge) with 4-phase execution, a 6-tier hierarchy, and paired-team fan-out. Use when coordinating any feature delivery, working an issue or epic ("work epic <id>", "work issue <id>", "use Forge on the next bees ready item", "forge <id>"), picking up an epic in a fresh session (decomposing path) or with pre-existing issues (dispatching path), implementing a multi-step task that benefits from plan→test→implement→review phases, asking clarifying questions before decomposing, forming a team and assigning models per tier, or orchestrating multi-agent workflows. Loads on casual feature requests too — not only when the word "epic" appears.

Guide for conducting code reviews. Use when reviewing pull requests, auditing code quality, identifying security issues, or providing code feedback.

Guide for writing technical documentation. Use when creating README files, API documentation, guides, or inline code documentation.

Guide for 12-Factor cloud-native applications. Use when designing microservices, configuring containers, deploying to Kubernetes, or following cloud-native patterns.

Validate claims through tool execution, avoid superlatives and unsubstantiated metrics. Use when reviewing codebases, analyzing systems, reporting test results, or making any factual claims about code or capabilities.

Controlled-language rules for technical writing in two registers — strict mode for procedural text and flavored mode for explanatory prose. Strict mode covers skill descriptions, procedure steps, agent definitions, output contracts, error text, and issue acceptance criteria. Flavored mode covers references, READMEs, ADR rationale, and PR bodies. Use when authoring or editing a SKILL.md, a skill description, an agent definition, a bees issue, an ADR, or a README. Use when reviewing prose for passive voice, hedged directives, terms used with two meanings, or overlong sentences.