@flowrail/skills
v0.0.7
Published
FlowRail skill markdown for Claude Code agents. Auto-invocable skills for design review, verify, lineage, and dep-check; copied into .claude/skills/ by @flowrail/init.
Readme
@flowrail/skills
Source of truth for FlowRail's Claude Code skills. Each skill is a thin, agent-facing pointer that calls one MCP tool on the FlowRail server:
| Skill | When the agent uses it | MCP tool |
|---|---|---|
| flowrail-design-review | You wrote a *.spec.md or asked for a threat model | flowrail_design_review |
| flowrail-verify | The hook auto-fired on a code write, or you asked "why was this blocked?" | flowrail_verify_code |
| flowrail-dep-check | The hook auto-fired on a package install, or you asked "is X@Y safe?" | flowrail_check_dep_install |
| flowrail-review-app | You asked for a whole-app review, or a snapshot was blocked on a cross-file finding | flowrail_review_app |
| flowrail-lineage | You asked "what did FlowRail decide for this task?" | flowrail_get_lineage |
What ships:
manifest.json— single source of truth for the skill names. Imported by@flowrail/init(the installer) and this package's own integrity tests.flowrail-*/SKILL.md— the agent-facing instructions. Copied into.claude/skills/by@flowrail/init.
You don't install this package directly — @flowrail/init pulls it in as a dependency and copies the skill markdown into your repo:
npx @flowrail/init@latestLinks
- Website: https://flowrail.ai
- Docs: https://flowrail.ai/docs
