Skip to content
cccskills
FreePublished on GitHub

swarm

Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.

The English summary is being prepared. Showing the original description.

neohaskell/NeoHaskell348 stars(GitHub 348 + cccskills 0)

Run score Not tested

See how to install

Files included (2)

  • SKILL.md3.1 KB
  • agents/openai.yaml43 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Swarm

Fan out N independent parallel workers. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.

Start

Open a todolist with one entry per phase before launching anything.

  1. Frame
  2. Fan out
  3. Aggregate
  4. Report

Phase A: Frame

  1. State the done predicate and the artifact or report the swarm must return.
  2. Choose the shape. Partition into slices, race N workers on identical briefs, or mix both. For a race or mixed shape, declare first pass, rank all, or best-of before spawning.
  3. Set N from the user or derive it from the shape. N is total workers, not the delegation capacity.
  4. Follow the delegation instructions in AGENTS.md. Use the current environment's configured worker roles and available delegation interface. Inherit supported defaults when no override is configured; report unsupported configuration rather than inventing identifiers. Use only supported execution settings. For a race, name each arm's role and setup up front. Shared role configuration is managed separately.
  5. Give each worker its own writable output when it writes. Keep reports and temporary artifacts under the project's intermediate-work directory (.agents-state/ here). Name writable file or directory ownership in each editing brief so workers do not overwrite one another's work. When workers verify or measure commits, each brief names the exact SHAs. A measurement brief also names the method (sample count, what one sample is, order). The worker records both in its result.

Phase B: Fan out

Launch all N workers through the available delegation interface, concurrently within its capacity or in batches when necessary. Choose execution environments with the source, tools and data access their briefs require.

Provide the requested branch or starting revision through the environment's supported checkout mechanism; ensure it matches the brief rather than relying on an implicit default.

Every brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use PASS, ISSUES, or BLOCKED with evidence. A worker that can prove a defect reports ISSUES and lists every issue it can prove, not only the first.

If a worker drops out, proceed with N-1 and note it.

Phase C: Aggregate

Read the terminal results. Drop a result that does not record the SHAs and method its brief names, and respawn that worker once. After a second miss, record a gap. A gap does not count as a pass. For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps.

Keep a compact result table, one-line evidenced issues, and explicit gaps or dropouts.

Phase D: Report

Return one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.

The English summary is being prepared. Showing the original description.

neohaskell/NeoHaskell348Updated Oct 26, 2026

arena

Free

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

The English summary is being prepared. Showing the original description.

neohaskell/NeoHaskell348Updated Oct 26, 2026

Inspect or supervise a PR or stack through review and CI to merge-ready, using current GitHub evidence and the requested mode.

The English summary is being prepared. Showing the original description.

neohaskell/NeoHaskell348Updated Oct 26, 2026

Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you benchmark or report a measured speedup or regression, including complete framework flows and compilation of projects that consume the framework.

The English summary is being prepared. Showing the original description.

neohaskell/NeoHaskell348Updated Oct 26, 2026

bro

Free

Restate the last message in plain human language, with no jargon.

The English summary is being prepared. Showing the original description.

neohaskell/NeoHaskell348Updated Oct 26, 2026

Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.

The English summary is being prepared. Showing the original description.

neohaskell/NeoHaskell348Updated Oct 26, 2026

See all skills by neohaskell

Report a problem with this skill