dryvist

Use when creating PRs, linking issues, managing PR comments, or creating GitHub issues

Use when creating or editing GitHub Actions workflows that call reusable workflows (uses: OWNER/repo/.github/workflows/...) — org owner references must be the literal current org, and shared-CI homes are under dryvist.

Emit a paste-ready two-part handoff for a fresh session: a `## Goal statement` hard-capped under 4000 characters (measured with wc -c, never estimated) that pastes straight into Claude Code's /goal Stop hook, plus an unbounded `## Full prompt` carrying cwd, ordered reading list, hard rules, pitfalls, and deliverables. Use when forking work to a new session, spinning up an orchestrator, or when wrap-up needs a next-session prompt with a real goal and not just a task list.

Analyzes current session state and repository status without any cleanup. Full mode (default): resolves the active plan file, reads plan checklist + TaskList, gathers unfinished work/issues from conversation history, checks git status, and emits a /handoff-built next-session prompt. Mid-session mode (`/session-status mid`): a fast plain-language 'done vs remaining' snapshot for mid-flight orientation, skipping the history scan, triage, and handoff.

End-of-session handler that first checks whether the current session's plan is actually complete. If complete: refresh repo, run quick retrospective, clean gone branches, and emit a forward-looking follow-up prompt. If incomplete: skip cleanup and emit one or more `cd`-into-worktree blocks paired with ready-to-paste resume prompts so the unfinished work can be picked up cold in a new session.

Automatically finalize pull requests for merge by resolving CodeQL violations, review threads, merge conflicts, and CI failures. Handles single PR (current branch or by number), all open PRs in the repo, or all open PRs across the org. Includes bot-authored PRs in all modes.

Work with repositories using the git-flow-next branching model (default branch is `develop`, production branch is `main`). Covers branch creation, worktree setup, atomic commits, PR targeting, validation on `develop`, and mandatory end-of-session promotion to `main`.

Verify or refresh the OpenTofu-to-Ansible inventory distribution (RustFS-published; apply is the publish boundary)

Continuously read the homelab Splunk (SIEM) as a self-directed analyst — hunt for anything anomalous with strictly bounded queries, remember baselines, and alert only when something is genuinely off

Discover current leading OpenRouter models and live prices (public keyless API), select an escalation model for complicated work or advanced coding, call it through the LiteLLM router within a $1/day budget, and request onboarding of models the router does not serve yet

Open, update, dedupe, resolve, and auto-close homelab incidents in Zammad (the ITSM system of record) via its REST API — the durable ticket + knowledge-base layer behind the splunk-monitor alerts, keyed on a stable finding_key and lifecycle-tagged so agent-managed tickets yield to any human touch

Open signed, draft, no-merge doc PRs to dryvist docs repos

Triage, create and update GitHub Issues (all repos) and manage dryvist org Projects v2

Use when you have a raw suite results JSON to turn into a published dataset shard (convert, dry-run, publish with the write token), or when RANKINGS.md needs updating after a publish. Covers the --kind/--suite selection and the mandatory same-PR RANKINGS rule.

Use when driving the agentic tool-calling benchmark specifically — running harness/agentic/run.py against an endpoint, choosing the cell matrix, reading the multi-turn degradation track, or recovering partial results after a crash. For the general five-suite flow use the run-benchmark skill.

Use when about to benchmark an MLX or locally-served model on this repo's hosts — running one or more of the five required suites, producing a dataset shard, or deciding whether a model counts as "fully benchmarked". Routes to the canonical RUNBOOK and the traps that silently corrupt results.

First fixture skill

Second fixture skill

Use whenever the pinned `vendor/ai-llm-prompts` routine catalog or local `routines/registry.yaml` deployment metadata changes. The GHA deploy workflow at `.github/workflows/deploy-routines.yml` is disabled because its `CLAUDE_CODE_OAUTH_TOKEN` cannot reach the Anthropic Routines API — see the workflow header for details. Cloud-routine bodies are now kept in sync by Claude calling `RemoteTrigger` directly during the editing session. Invoke this skill at the end of any session that modified a routine, before reporting done.

Keep the Mintlify docs site in sync with the JacobPEvans (and dryvist) GitHub repos. Use when adding new repos, when a repo is renamed or archived, or when refreshing the site's coverage. Triggers on "/mintlify-docs-update", "add docs for <repo>", "scaffold docs page", "sync docs site with repos", "update mintlify docs".