git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace /tmp/handoff && cp -r /tmp/handoff/plugins/ai-agency/hyperflow/skills/handoff ~/.claude/skills/handoffSKILL.md
# Handoff Operator interface for **two-session execution**: one session plans (`session=two` at the Step 0 gate), a second session in another environment builds, and the first session reviews. The lifecycle and package format are defined in [`../hyperflow/session-handoff.md`](../hyperflow/session-handoff.md); this skill is the thin set of verbs over it (mirrors how `/hyperflow:flush` fronts the deferred-commit machinery). Packages live at `.hyperflow-handoff/<slug>/` (committed, so they travel via git). `STATUS` (`planned → built → reviewed`) is the single source of truth and decides which side of the handoff you are on. ## Subcommands ### `list` Read-only. List every `.hyperflow-handoff/*/` (excluding `.archive/`): slug · `STATUS` · `on_complete` · age. Group by status so the user sees what is awaiting build vs awaiting review. ### `status [<slug>]` Show the `HANDOFF.md` manifest + `STATUS` for one package (or all). When `STATUS=built`, also print the `COMPLETION.md` diff range and commit count. Read-only. ### `pickup <slug>` — build side Thin alias for starting the second-session build: invoke `Skill` with `skill: dispatch` and `args: "<slug>"`. Dispatch's Step 1.0 rehydrates `artefact/` into `.hyperflow/`, runs `/hyperflow:scaffold` if the cache is missing, builds the batches, writes `COMPLETION.md` + `STATUS=built`, and then deploys or stops per `on_complete`. ### `review <slug>` — planning side 1. Require `STATUS=built` (else: "handoff `<slug>` is `<status>` — nothing to review yet"). 2. Read `COMPLETION.md` → extract `Diff range = <base>..<head>`. 3. Invoke `Skill` with `skill: audit` and `args: "<base>..<head> level=3"` (`level=5` when the originating triage flow in `HANDOFF.md` was `scientific` or `security`). The audit dispatches the matching domain specialist reviewers over the second session's diff. 4. On audit clean pass → fire the deploy gate (`AskUserQuestion` — `Run /hyperflow:deploy? Yes / No`, binary, no marker). On `NEEDS_FIX` → the audit fix-gate (`Yes` → `/hyperflow:plan` → `/hyperflow:dispatch`) handles it. 5. Set `STATUS=reviewed` once the review is accepted. ### `complete <slug>` Mark the lifecycle done: set `STATUS=reviewed` (if not already) and archive the package to `.hyperflow-handoff/.archive/<slug>/`. Commit `chore(handoff): archive <slug>`. ## Resolution - Default `<slug>` = the most-recently-modified package when omitted from `status`/`pickup`/`review`. - A package whose `STATUS=planned` is a **build-side** task (run `pickup`); `built` is a **review-side** task (run `review`). The session-start hook surfaces the right verb automatically. ## Iron rules - **Never edit the build's commits.** `review` is read-only over the diff range; fixes flow through the audit fix-gate → scope → dispatch, never by amending the second session's commits. - **Never force-push; never `--no-verify`.** Auto-push failures surface the exact `git push -u origin <branch>`. - **No AI attribution** in any commit or package file. - Honors `handoff.*` config (`autoPush`, `remote`, `packageDir`). ## Doctrine Shared rules in [`../hyperflow/DOCTRINE.md`](../hyperflow/DOCTRINE.md). Package contract + templates in [`../hyperflow/session-handoff.md`](../hyperflow/session-handoff.md).
Guard the beads execution record: enforce the write-flush-verify discipline that defeats the bd rapid-write race, audit epic dependency graphs for cycles and orphans, catch closures whose title overstates what shipped, flag open beads carrying no disposition or a disproven premise, and reconcile bd against its GitHub and Plane projections. Owns RECORD INTEGRITY; delegates graph analysis to bead-dependency-mapper and epic-closure drift to bead-epic-auditor rather than duplicating them. Use before closing an epic, after any batch of bd writes, when a bead premise looks stale, or when auditing whether the record matches reality. Trigger with "audit beads", "check the bead DAG", "did that close actually land", "bead hygiene".
Verify every factual assertion in a diff, PR body, commit message, bead note, or governing doc against the actual repository, and fail anything that cannot be substantiated by a command. Use before merging any PR that makes claims about counts, coverage, consumers, enforcement, provenance, or certification, and when auditing standing docs for rot. Trigger with "verify claims", "check this PR body", "is this claim true", "claim audit".
Design and build Omarchy (Quickshell/QML) bar-widget, panel, and service plugins that actually work on a stock install. Knows the hard runtime constraint (no node on the graphical session PATH), the first-party contracts (BarWidget, Panel, KeyboardPanel, PanelKeyCatcher, Service), the curl-from-QML data pattern, FileView persistence, and the marketplace submission bar. Use when starting a new Omarchy plugin, porting a plugin off an external runtime, wiring a service to a bar widget, or deciding how a widget should fetch and persist. Trigger with "build an omarchy plugin", "omarchy widget", "quickshell plugin", "port this plugin to QML".
Audit an Omarchy plugin before it reaches the marketplace: prove it installs and runs on a stock box (no node/python on the session PATH), run the omarchy-submit gate lane, validate on the rig with omarchy-plugin-validate and qmllint, and check the QML security invariants and first-party idiom contracts. Read-only: it reports and blocks, it does not rewrite the plugin. Use before submitting an entry, after any data-layer change, or when a plugin works on the dev box and you need to know whether it works for a real user. Trigger with "audit this omarchy plugin", "is this plugin submission ready", "will this plugin work when installed".
Audit and fix Claude Code SKILL.md files against enterprise compliance standards: frontmatter completeness, required body sections, and style. Use when validating or repairing skills in a plugin directory. Trigger with "audit skill", "fix skill compliance".
Learn how SKILL.md files work in Claude Code plugins, then build a production-quality agent skill from scratch. Covers frontmatter schema, body structure, testing, and iteration.
Step-by-step guide to writing a SKILL.md file for Claude Code. Learn how to plan, structure, and test auto-activating skills with proper frontmatter, allowed-tools, dynamic context injection, and supporting files.
|