agentleFS
Sign inStart free
TheVellerTheVeller/claude-skills/skills/agent-operations/sprint-parallel/SKILL.md

sprint-parallel

Skill4 starsChanged 11 days agoMITView on GitHub

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.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this the moment a sprint has a defined reset or cut time.

    line 10
  2. Distinctive:

    All GMs and all workspaces move now, not in sequence.

    line 27
  3. Distinctive:

    Do not wait for one map, one hallazgo, or one GM before starting the others.

    line 28
  4. Distinctive:

    Prefer many small simultaneous loops over one deep serial thread.

    line 29
  5. Distinctive:

    If a bot is in the wrong room or duplicating a live role, say so and stop.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

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 and reporte-gm 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free