commit-disciplineEnforces atomic commit discipline and fast PR cycles to keep the main branch always shippable. Use proactively when planning a feature, breaking work into tasks, making any code changes, staging files, writing commit messages, or discussing what to ship. Triggers on: "let's add X", "I'm working on Y
git-stacked-prsUse this skill when breaking a large change into a stack of reviewable PRs
issue-createCreate a well-structured, actionable GitHub issue from context the user gives you — picks the right template (bug/feature/docs/task/question), gathers the details that template needs, and files it with `gh issue create`. TRIGGER ONLY on `/issue-create <context>`, or an explicit ask to create/file a
no-commentsSpawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
pull-requestDefines the required shape for a pull request's title and body. ALWAYS use this skill when opening a pull request, drafting a PR description, or writing a PR title — not optional. Triggers on: "open a PR", "draft the PR description", "write the PR title", "create a pull request", or any point where
release-notesUse when drafting, rewriting, or reviewing release notes or a changelog entry for a GitHub release or tag, when an auto-generated or release-please release body needs to become readable, or when asked what changed between two versions for the people who use the software.
skill-maintenanceWhat makes an agent-skill change worth keeping, and how a skill is laid out: when to add, edit, or delete a skill, which scope it belongs in, how to write the description, and where references and scripts live and how SKILL.md links them. Use whenever you are about to create, edit, or remove a skill
technical-writingLayered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
writing-testsPrinciples for writing good tests, distilled from the TDD canon (Beck, Fowler, Meszaros, Freeman & Pryce, Cooper). Use whenever writing new tests, reviewing test code, doing TDD red-green-refactor, or deciding what and how to test — unit, integration, or end-to-end, in any language.