Open a Markdown plan or document for the human to review and annotate in a Herdr pane; their feedback arrives as your next message. Use when you have written a plan, spec, or design document that needs human review before you act on it.
Before implementing a new feature, isolate it in its own git worktree (own folder + branch) AND its own Herdr pane so parallel sessions never share a checkout or a terminal. Use whenever the user asks to implement, build, add, or work on a new feature, view, panel, or other sizable change to either plugin. Skip for…
Use when implementation is complete, all tests pass, and the user needs to decide how to integrate the work - presents the integration candidates (merge locally, push and open a PR, push only, keep) and executes only the chosen one; never merges on its own.
Use when inside herdr (HERDRENV=1), the current pane is acting as the orchestrator for the task, and idle sibling agent panes can take delegated work — operational repo tasks standalone, or any routed task as the delegation transport for the orchestration skill.
Park and resume agent sessions inside Herdr tabs without manually tracking session IDs. Use when the user asks to park a tab/session, resume a parked tab, list parked sessions, free computer resources, hibernate idle agent panes, or manage Herdr Session Parker.
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
Build, test, and end-to-end verify the Multiplex visionOS/iPadOS SSH-tmux terminal app. Use this whenever you need to compile the app, run its unit tests, regenerate the Xcode project after editing project.yml or adding/ removing source files, or confirm a change works in the real app on the visionOS or iPad…
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
Run an adversarial code review by spawning a safecodex reviewer in a herdr split pane, waiting for it to finish, and interrogating its findings. Use whenever the user asks for an adversarial review, red-team review, second opinion, "attack this diff/plan", "poke holes in this", or wants their working changes…
Observe and operate durable workloads and reviewed Mission Control groups through Tether's public surfaces without depending on tmux or Herdr internals.
Select, submit, and verify useful independent coding-agent work from live worker capability/status facts while preserving explicit targets and quality requirements.
Reference for designing, changing, debugging, testing, and releasing AI-generated code so failures become durable regression assets and completion is proven across the real delivery boundary.
Control live Herdr workspaces, panes, agents, incremental state, and native long-tail methods through herdrmethods, herdrinspect, herdrcall, and herdrsince.
Bring one interactive coworker into a dispatched worker's current Herdr tab and exact worktree. Use from an in-progress worker when the user asks to pull in a colleague or a rule requires a human-facing second-agent review.