workflows
The `add` command registers an upstream skill reference in a workspace without vendoring its source code, preserving the original skill's metadata while allowing customization of its shelf location, workflow branch, and rationale. Use this when you want to reference external skills from the bundled library or GitHub repositories while maintaining a personalized workspace structure that reflects your specific use cases.
git clone --depth 1 https://github.com/MoizIbnYousaf/Ai-Agent-Skills /tmp/workflows && cp -r /tmp/workflows/docs/workflows/add-an-upstream- ~/.claude/skills/workflowsadd-an-upstream-skill.md
# Add an Upstream Skill Use `add` when you want a workspace entry but do not want to vendor the source. From the bundled reference library: ```bash npx ai-agent-skills add frontend-design --area frontend --branch Implementation --why "I want this on my shelf." ``` From a GitHub repo: ```bash npx ai-agent-skills add anthropics/skills --skill ask-questions-if-underspecified --area workflow --branch Planning --why "I use this to tighten vague requests." ``` `add` writes to the active workspace only. It keeps the upstream metadata: - `description` - `source` - `sourceUrl` - `installSource` - `tags` - `labels` - `requires` You still choose: - shelf - branch - why it belongs That keeps the workspace shaped like your own library instead of becoming a blind copy.
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
Use when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.
Backend API design, database architecture, microservices patterns, and test-driven development. Use for designing APIs, database schemas, or backend system architecture.
>-
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
Use when regenerating README.md and WORK_AREAS.md in a managed library workspace. Always dry-run first to preview changes.
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Writing effective code documentation - API docs, README files, inline comments, and technical guides. Use for documenting codebases, APIs, or writing developer guides.