vellum-skill-authoring
This Claude Code skill guides the authoring and review of first-party Vellum skills within the vellum-assistant repository. Use it when creating or modifying skill files in the skills/ directory, writing SKILL.md documentation, defining tool contracts, or ensuring skills maintain proper isolation from the assistant codebase and follow Vellum's portability standards.
git clone --depth 1 https://github.com/vellum-ai/vellum-assistant /tmp/vellum-skill-authoring && cp -r /tmp/vellum-skill-authoring/.cursor/skills/vellum-skill-authoring ~/.claude/skills/vellum-skill-authoringSKILL.md
# Vellum Skill Authoring ## Scope Use this for Vellum runtime skills in `skills/` and bundled assistant skills, not for Cursor Agent Skills under `.cursor/skills/`. ## Core Constraints - First-party skills must be portable and isolated. - `skills/` must not import from `assistant/`. - `assistant/` must not import from `skills/`. - Prefer skill processes and supported contracts over new daemon tool registrations. - Avoid secrets, real personal data, and machine-specific paths in skill docs, tests, and fixtures. ## SKILL.md Quality Bar Skill instructions should be concise and operational: - State what the skill does and when to use it. - Prefer concrete steps over broad advice. - Keep user-facing terminology consistent. - Use generic examples only. - Avoid requiring hidden local state unless setup instructions create it. ## Tool And Script Review When a skill adds scripts or tools: 1. Verify tool input/output contracts are explicit. 2. Check error handling and user-facing messages. 3. Confirm scripts can run in the skill process environment. 4. Avoid direct imports across isolation boundaries. 5. Add focused tests for parsing, contract handling, and failure cases. ## Catalog And Packaging When adding or renaming skills, check the relevant catalog, manifest, bundled registry, or packaging path used by the runtime. Do not assume a `SKILL.md` file alone makes the skill available to users. ## Verification Use focused tests around the changed skill, catalog entry, proxy bridge, or bundled registry. Add typecheck when contracts or generated manifests changed.
>
>
>
>
Check Vellum Assistant architecture and package boundaries. Use when editing imports, moving code, adding endpoints, touching assistant/gateway/client/skill boundaries, or reviewing architecture-sensitive changes.
Review Vellum Assistant code changes for correctness, repo-specific quality rules, security risks, and missing validation. Use when reviewing diffs, preparing a PR, finishing implementation work, or when the user asks for a code review, quality pass, or pre-merge check in this repository.
Guide Vellum Assistant feature flag changes and rollout hygiene. Use when adding, editing, reviewing, or documenting assistant feature flags, rollout-gated behavior, or platform flag follow-up work.
Validate Vellum Assistant database and workspace migrations. Use when adding, editing, reviewing, or testing migrations, release-note migrations, persisted schemas, workspace file formats, or data backfills.