raphaeltm
UserRun multiple coding agents in parallel on your own cloud VMs.
Categories
Indexed Skills (17)
field-notes-post
Generate a set of four on-brand "field notes" social media images (landscape hero, landscape grid, portrait timeline, vertical story) from a batch of user photos plus the day's SAM agent activity. Use when the user uploads photos from a walk/trip/day and wants social post images showing what their agents shipped while they were out.
prototype
Build a UI prototype for design exploration. Creates a self-contained, unauthed page in the real web app with mock data, exposes it for preview, and runs visual audits. Use when exploring layouts, information architecture, or interaction patterns before committing to production implementation.
cloudflare-specialist
Cloudflare Workers architecture specialist. Advises on D1 migrations, KV usage patterns, R2 binary distribution, wrangler configuration, and Miniflare testing. Use when modifying wrangler.toml, working with Cloudflare services, or setting up testing infrastructure.
constitution-validator
Constitution compliance validator focusing on Principle XI (No Hardcoded Values). Detects hardcoded URLs, timeouts, limits, and identifiers that should be configurable. Use proactively when implementing business logic, adding new features, or reviewing PRs for constitution compliance.
doc-sync-validator
Documentation synchronization validator. Ensures CLAUDE.md, self-hosting.md, constitution.md, and other docs match actual code implementation. Checks for stale references, missing documentation, and inconsistent descriptions. Use proactively when modifying code interfaces, adding features, or updating documentation.
env-validator
Environment variable consistency validator. Checks GH_* vs GITHUB_* naming conventions, validates documentation matches code, and ensures deployment scripts correctly map secrets. Use proactively when modifying environment variables, updating CLAUDE.md, editing configure-secrets.sh, or changing the Env interface.
go-specialist
Go code review specialist for VM Agent and CLI. Reviews PTY/WebSocket/JWT code, CLI command contracts, static-analysis findings, and Go idioms. Use when working in packages/vm-agent/, packages/cli/, or reviewing Go code changes.
security-auditor
Security review specialist for credential safety, OWASP vulnerabilities, JWT validation, and WebSocket security. Use proactively after implementing auth, encryption, credential handling, or workspace access code. Invoke before PRs touching security-sensitive files.
task-completion-validator
Task completion validator. Cross-references task file research findings, implementation checklist, and acceptance criteria against the actual git diff and test suite. Catches planned work that was never executed. Mandatory before archiving any task.
test-engineer
Test generation specialist for TDD compliance and coverage enforcement. Generates comprehensive tests following Vitest patterns for TypeScript and Go testing conventions. Use proactively during TDD phases, when implementing critical paths, or when coverage needs improvement.
ui-ux-specialist
UI/UX specialist for web surfaces. Use for any UI change in apps/web or packages/ui to enforce mobile-first layout quality, visual hierarchy, interaction clarity, and accessibility with screenshot-backed validation.
api-reference
Full API endpoint reference for SAM. Use when working on API routes, adding endpoints, writing API tests, or understanding the API surface. Trigger when asked about API endpoints, routes, or HTTP interfaces.
changelog
Recent feature changes and implementation details for SAM. Use when understanding recent changes, checking what was modified recently, or understanding feature history. Trigger when asked about recent changes, what's new, or feature history.
env-reference
Full environment variable reference for SAM. Use when adding, modifying, or documenting environment variables, configuring deployment, or working with Worker secrets. Trigger when asked about env vars, secrets, or configuration.
do
End-to-end autonomous task executor. Takes a task description and handles the full lifecycle: research, plan, implement, review with specialist skills, and merge via PR. Use when given a task to execute end-to-end.
prioritize
Identify what to work on next. Reconciles candidate work against already-merged code BEFORE ranking, so stale/shipped ideas are dropped. Use when asked what to work on next, how to prioritize the backlog, or to triage ideas/tasks/incidents into a ranked shortlist.
workflow
Orchestrate multi-step workflows by decomposing into subtasks, dispatching them, and monitoring via foreground polling loops. Prevents session timeout kills during long-running orchestration. Use when coordinating multiple agents or running multi-phase work that takes more than a few minutes.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.