Agent

Answer questions about how the evlog CLI is used in production and surface interesting findings from the telemetry dashboard's MCP. Load this when asked about CLI usage, telemetry, adoption, flags, or "what's happening in the CLI", and when the digest needs its CLI usage section.

Weekly pass over the evlog repository and Evi's own surface, in two halves — what has drifted out of coherence (a capability wired but never consumed, code contradicting a written guide, a description promising a tool the allowlist lacks), and what is missing (a capability worth having, a manual step worth automating, a gap in evlog users keep hitting). Load this when the self-review schedule fires, or when Hugo asks for a self-review, an audit, ideas for what Evi should do next, or what is inconsistent in the repo.

Produce a before/after visual comparison of an evlog surface (landing, docs, telemetry, playgrounds) and share it as public Blob URLs. Load when a change is visual, when someone asks for screenshots, a recording, or a visual diff, or when a shipped PR touches apps/docs or apps/telemetry and deserves visual evidence.

The daily pass over evlog's written surfaces. Picks the files the scanner ranks worst across the docs, the landing, the package READMEs, the skills, and the AGENTS.md files, reviews them against the content doctrine, applies what holds, and opens one draft PR whose body is the report. Also covers the enrichment half, run when nothing scores badly enough to rewrite, such as the page an index promises and nobody wrote, the integration documented at half its contract, the correction that should have become a rule. Load this when the content-pass schedule fires, or when Hugo asks for a content pass, a docs review, a rewrite of a page, a README, a skill or an AGENTS.md, or what is worth writing next.

How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the package.

Build and deliver the daily activity digest, covering GitHub activity, AI Gateway spend, visitor counts, CLI usage, and a short news section. Load this when the morning digest schedule fires, or when someone asks for a digest, a daily recap, or "what happened" over a recent period, on any channel.

Weekly review of evlog's model cost and performance. Load this when the cost-watchdog schedule fires, or when Hugo asks for a cost check, a model review, a per-surface model analysis, or a spend/drift report for the gateway.

Check the eve and Vercel Connect ecosystem for updates and new features, keep the app current with them, and replace workarounds with the real improvements. Load this when the upstream-sync schedule fires, or when asked to check for eve or @vercel/connect updates.

Bi-weekly pass over the whole evlog repository, not just the agent's own surface. Checks every SKILL.md against the real package surface, the docs tree for stale or self-contradictory pages, the repo's own conventions, and the examples against the current API. Load this when the repo-health-sweep schedule fires, or when Hugo asks for a repo health sweep, a docs audit, a skills-vs-reality check, or a convention drift review.

Bi-weekly housekeeping pass over the evlog team's Linear backlog — labels, projects, priorities, stale triage, work that is done but still open, and anything misfiled next to its siblings. Applies the mechanically verifiable fixes and surfaces the rest as decisions. Load this when the linear-maintenance schedule fires, or when Hugo asks for a Linear clean-up, a backlog pass, or a triage consistency check.