agentsclimarketplace

Brainstorming

Skill sordi-ai/skill-everything/skills/brainstorming

Git-versioned agent memory: agents that never make the same mistake twice. Anthropic-Skill folder standard, multi-runtime (Claude Code, Cursor, Gemini CLI, OpenCode).

Install
npx -y skills add sordi-ai/skill-everything --skill brainstorming

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

  • 17 stars17 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.

What its author says it does

Copied from the file, not written here

Apply when generating ideas, exploring solution space, or facilitating divergent thinking before committing to an approach.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.3 KB, as published. Nobody here has run it

Sub-Skill: Brainstorming

Purpose: Maximize the quality of the eventual solution by ensuring sufficient exploration of the solution space before converging on an approach.

Rules

Divergence First

  1. Generate before evaluating. Always complete a divergent generation phase before applying any evaluation criteria; premature judgment kills creative options.
  2. Produce at least three alternatives. Always generate at least three distinct alternatives before committing to an approach. Reference: ERR-2026-028
  3. Quantity over quality early. Prefer producing many rough ideas over polishing a single idea during the generation phase; refinement comes later.
  4. Loosen constraints deliberately. Before generating, explicitly list the constraints you are relaxing (time, cost, technology) to open the solution space.

Structured Exploration

  1. Timebox each phase. Always set explicit time limits for divergent and convergent phases to prevent open-ended exploration from blocking delivery.
  2. Use silent generation first. Before group discussion, have each participant (or reasoning thread) generate ideas independently to avoid anchoring bias.
  3. Apply devil's advocate. After generating options, explicitly argue against the leading option to surface hidden weaknesses before committing.
  4. Build on ideas, don't replace them. Prefer extending or combining existing ideas over discarding them; hybrid solutions often outperform pure alternatives.

Convergence

  1. Define decision criteria upfront. Before evaluating options, agree on the criteria (performance, cost, maintainability) and their relative weights.
  2. Categorize before ranking. Group ideas by theme or approach before ranking; ranking ungrouped lists misses structural patterns.
  3. Document rejected alternatives. Always record why alternatives were rejected so future contributors understand the decision context.

See also

  • skills/self-extension-workflow/SKILL.md
  • skills/error-log/SKILL.md

Keep looking

Skills are one crate of 328,083. 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.