axiom

MUST consult this skill before answering whenever the user's task involves external versioned dependencies — even if you think you can handle it directly. This applies to: checking if packages/tools are up to date, upgrading npm/pip/cargo/go dependencies, writing or reviewing CI/CD (GitHub Actions, CircleCI, GitLab CI), pinning action versions, reviewing Dockerfiles/base images, checking Terraform providers/modules for drift, reviewing Helm chart versions, verifying Kubernetes/EKS/cloud versions, updating pre-commit hooks, writing Dependabot configs, or any task mentioning specific version numbers, package names, or config files like package.json, pyproject.toml, Dockerfile, .pre-commit-config.yaml, main.tf, or values.yaml. Even casual asks like "is this still current" or "has anything drifted" require it — training data is unreliable for volatile version facts. Do NOT use for refactoring code, writing tests, debugging errors, designing APIs, or tasks with no external versioned dependencies.

MUST consult this skill before answering whenever the user's task involves external versioned dependencies — even if you think you can handle it directly. This applies to: checking if packages/tools are up to date, upgrading npm/pip/cargo/go dependencies, writing or reviewing CI/CD (GitHub Actions, CircleCI, GitLab CI), pinning action versions, reviewing Dockerfiles/base images, checking Terraform providers/modules for drift, reviewing Helm chart versions, verifying Kubernetes/EKS/cloud versions, updating pre-commit hooks, writing Dependabot configs, or any task mentioning specific version numbers, package names, or config files like package.json, pyproject.toml, Dockerfile, .pre-commit-config.yaml, main.tf, or values.yaml. Even casual asks like "is this still current" or "has anything drifted" require it — training data is unreliable for volatile version facts. Do NOT use for refactoring code, writing tests, debugging errors, designing APIs, or tasks with no external versioned dependencies.

Use ANY time the user signals they want to commit staged changes — including bare "commit", "/commit", "commit this", "commit these changes", "let's commit", "make a commit", "git commit", "write a commit message", "make a conventional commit", "use conventional commits", or any equivalent phrasing in context (e.g., right after staging files, "ready to commit", "okay ship it"). Composes a Conventional Commits message with a gitmoji prefix: reads the staged diff, decides type, scope, emoji, subject, body, and footer using the rubrics in this file, shows one assembled message in a fenced block, and commits after a single yes/no confirmation. It writes the commit message only — NOT other prose about the staged changes: not PR/MR descriptions, not release notes, not changelogs or summaries. Also do NOT use for questions *about* git or *about* conventional commits, amending, rebasing, cherry-picking, reverting/undoing commits, or viewing log history.

MUST consult this skill before answering whenever the user's task involves external versioned dependencies — even if you think you can handle it directly. This applies to: checking if packages/tools are up to date, upgrading npm/pip/cargo/go dependencies, planning or writing CI/CD workflows (GitHub Actions, CircleCI, GitLab CI), pinning action versions, reviewing Dockerfiles or base images, checking Terraform providers or modules for drift, reviewing Helm chart versions, verifying Kubernetes/EKS/cloud resource versions, updating pre-commit hooks, writing Dependabot configs, or any task where the user mentions specific version numbers, package names, or config files like package.json, pyproject.toml, Dockerfile, .pre-commit-config.yaml, main.tf, or values.yaml. Even casual requests like "is this still current" or "has anything drifted" require this skill because your training data is unreliable for volatile version facts. Do NOT use for: refactoring code, writing tests, debugging errors, designing APIs, or tas

MUST consult this skill before answering whenever the user's task involves external versioned dependencies — even if you think you can handle it directly. This applies to: checking if packages/tools are up to date, upgrading npm/pip/cargo/go dependencies, planning or writing CI/CD workflows (GitHub Actions, CircleCI, GitLab CI), pinning action versions, reviewing Dockerfiles or base images, checking Terraform providers or modules for drift, reviewing Helm chart versions, verifying Kubernetes/EKS/cloud resource versions, updating pre-commit hooks, writing Dependabot configs, or any task where the user mentions specific version numbers, package names, or config files like package.json, pyproject.toml, Dockerfile, .pre-commit-config.yaml, main.tf, or values.yaml. Even casual requests like "is this still current" or "has anything drifted" require this skill because your training data is unreliable for volatile version facts. Do NOT use for: refactoring code, writing tests, debugging errors, designing APIs, or tas