herdr-orchestrate

Solid

Manual-only orchestrator for delegating GitHub issues to agent pairs in dedicated Herdr tabs: triage, work units, worktree + pair per unit, implement → ship-it, status on demand.

AI & Automation 3 stars 0 forks Updated today MIT

Install

View on GitHub

Quality Score: 82/100

Stars 20%
20
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Herdr Orchestrate A **work unit** is the atom of delegation: one worktree, one Herdr tab, one agent pair, one PR. A unit holds one issue by default, or several issues that belong together and ship as a single PR. This skill finds free issues, splits them into units with the user, sets each unit up, kicks it off, and reviews its diff before it ships; the user reviews and interjects per tab. For herdr CLI mechanics — command syntax, IDs, JSON output — follow the `herdr` skill installed alongside this one: print the relevant command group (`herdr tab`, `herdr agent`, `herdr pane`) instead of guessing flags, and read identifiers from command responses. The CLI auto-updates and can change mid-run — when a command errors with an unknown subcommand or flag, re-read the `herdr` skill and the CLI's own help instead of retrying remembered syntax. Talk to the user in their current language. Keep commands, paths, branch names, and issue references literal. ## Preconditions - `herdr` with the agent automation commands (`herdr agent start`, `herdr agent prompt`, `herdr agent wait`) and `gh` on `PATH`, `HERDR_ENV=1`, and `HERDR_PANE_ID` set (the orchestrator must run inside Herdr). If any is missing, stop and say so. - Run from the project repository (or `cd` to the repo the user names). - Record the orchestrator's own location once (`herdr pane current`): its `workspace_id` scopes everything this skill touches. ## Guardrails 1. The recorded `workspace_id` is this skill's e...

Details

Author
hcaiano
Repository
hcaiano/skills
Created
2 months ago
Last Updated
today
Language
JavaScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category