Use whenever a sprint has a defined reset or cut time: maximize parallelization (1:1 GMs + dedicated rooms same beat), map value processes, fill high-quality gaps.
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
SSkills Directory ProSkills Directory
Get any skill into Claude in one click.
Are you the author of Sprint Parallel?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/theveller-sprint-parallel)
---
name: sprint-parallel
description: >-
Use whenever a sprint has a defined reset or cut time: maximize
parallelization (1:1 GMs + dedicated rooms same beat), map value processes,
fill high-quality gaps.
---
# Sprint Parallel
Use this the moment a sprint has a **defined reset or cut time**. Do not wait to be reminded. This skill overrides serial “one department at a time” and the “GMs-room-only” habit for the duration of that sprint.
Outside a timed sprint, follow [Loop Corp](../../agent-operations/loop-corp/SKILL.md).
## Dual channel (same beat)
Grok Bot talks **both** in the same cycle, never one then the other:
1. **1:1 to each GM** — one concrete next action (not an ack).
2. **Dedicated rooms** — GM room + each GM’s staff room + each live workspace room.
GMs then talk to **every** specialist in their room in that same beat. Bots may 1:1 each other. Do **not** DM scouts from Grok Bot.
Idle / only-ack in any lane is a bug.
## Maximize parallelization
- All GMs and all workspaces move **now**, not in sequence.
- Do not wait for one map, one hallazgo, or one GM before starting the others.
- Prefer many small simultaneous loops over one deep serial thread.
- Self-classify every loop by **workspace · process · objective · skill**.
- If a bot is in the wrong room or duplicating a live role, say so and stop. Do not invent a third format.
## Pass-a-pass (value first)
Each live area maps **one** end-to-end process that actually generates value:
`trigger → skill → output → owner` (4 boxes)
Skip theater. Skip processes that do not return ROI, learning, or a stable day. Brand/workspace loops outrank generic org chatter when those workspaces are the north star.
Formats stay [hallazgo](../../agent-operations/hallazgo/SKILL.md) and [reporte-gm](../../agent-operations/reporte-gm/SKILL.md) only.
## Fill gaps (high quality margin)
As maps land, create or update **only** when the hole is real and quality is high:
- Agent: GM proposes, Grok Bot creates, no overlap with a live role.
- Frozen unless the human unlocks: Closer, Ventas, Partnerships, publishers, identity farm, Skool/WhatsApp, caja-bot.
- Docs (roster, org, contracts, comm graph) update in the same cycle as the change.
- Routines, skills, and rules stay **non-invasive**: weekday/daytime defaults, no scout spam, no extra fields, no new DBs.
A structural or A3 change waits for the human. Everything else proceeds.
## HITL later
The human reviews **one by one** at the cut (results and decisions). Do not dump wiring into that 1:1. Do not pause the parallel machine waiting for that review.
## Cut
At reset time: one quality corte (real numbers, links, n/d if missing). Then migrate what already exists. Do not open a new serial queue.