agentsclimarketplace
Sign in

Skills

Skill multiplex-ai/muggle-ai-teams/skills

Wrapper for superpowers:brainstorming that recognizes parent workflow context. Use this INSTEAD of superpowers:brainstorming when invoked from /muggle-ai-teams Step 1C.From its SKILL.md

Install
npx -y skills add multiplex-ai/muggle-ai-teams --skill skills

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, 433 tokens by cl100k_base, as published. Nobody here has run it

Workflow-Aware Brainstorming

This skill wraps superpowers:brainstorming with parent workflow awareness.

When Invoked from /muggle-ai-teams

If this skill is triggered as part of /workflow Step 1C (Design Proposal), the following rules apply:

Before Starting

Check that Step 1A and 1B outputs exist. If not, STOP and tell the orchestrator:

"Cannot start brainstorming — Step 1A/1B outputs are incomplete. The following are missing: [list]."

Required 1A outputs:

  • Codebase exploration results (from feature-dev:code-explorer)
  • Industry research findings (from WebSearch)
  • Library documentation (from Context7 MCP)

Required 1B outputs:

  • Clarified requirements
  • Impact analysis (files, services, flows affected)
  • Dependency mapping
  • Risk identification

During Brainstorming

Follow superpowers:brainstorming skill exactly as documented. All its rules, checklist items, and processes apply.

At "Transition to Implementation" Step

DO NOT invoke superpowers:writing-plans directly.

Instead, announce:

"This concludes the brainstorming phase (Workflow Step 1C: Design Proposal). The design spec has been written and committed.

Next steps in the parent workflow:

  • Step 1D: Panel Review — dispatch panelists to scrutinize the design
  • Step 1E: User Approval Gate — present revised design for user sign-off
  • Step 1F: Implementation Plan — write the plan AFTER panel review and approval

Control returns to the /muggle-ai-teams orchestrator."

Then STOP. Do not proceed further. The orchestrator handles Steps 1D, 1E, and 1F.

When Invoked Standalone (not from /muggle-ai-teams)

Behave exactly like superpowers:brainstorming — follow all its steps including the "transition to implementation" step which invokes writing-plans.

What ships with it: 137 files

2359.5 KB alongside SKILL.md, 17 of them executable

agents/

assets/

data/

evals/

geo-agents/

97 more files not listed here. See all 137 in the repository.

Gives 0 of the 12 instructions most automation workflows skills give in 433 tokens

Counted across 813 of the 1,214 authors here whose files we hold, read 2026-09-06

  • Use conventional commit message formatin 38 of 813, across 34 files
  • Write tests before implementing codein 26 of 813, across 12 files
  • Achieve at least 80 percent test coveragein 24 of 813, across 11 files
  • Mock external dependencies for unit testsin 22 of 813, across 10 files
  • Read product marketing context before asking questionsin 21 of 813, across 6 files
  • Implement rollback plans for every deploymentin 21 of 813, across 9 files
  • Follow the arrange-act-assert patternin 20 of 813, across 9 files
  • Delete branches after mergingin 20 of 813, across 18 files
  • Test all edge cases and error scenariosin 20 of 813, across 8 files
  • Use semantic selectors for UI testsin 19 of 813, across 7 files
  • Define sequence type and audience contextin 18 of 813, across 5 files
  • Monitor feature drift and prediction distribution driftin 18 of 813, across 5 files

Said here and by no other author read

  • Verify existence of Step 1A and 1B outputs
  • Stop if required outputs are missing
  • Follow superpowers:brainstorming rules exactly
  • Announce conclusion of brainstorming phase
  • Return control to the orchestrator
  • Stop after design proposal completion

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.