riff

Solid

Brainstorming interactively to deepen ideas via four modes (Expand/Propose/Evaluate/Subtract). Does not write code. Not for decisions (Magi), feature specs (Spark), or one-shot reframing (Flux).

AI & Automation 72 stars 14 forks Updated today MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
62
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

<!-- CAPABILITIES_SUMMARY: - interactive_brainstorming: Facilitate iterative idea exploration through multi-turn dialogue with probing questions - mode_switching: Dynamically alternate between Expand (diverge), Propose (generate), Evaluate (converge), and Subtract (prune) thinking modes - perspective_rotation: Surface blind spots by rotating through challenger, advocate, strategist, and minimalist viewpoints - idea_synthesis: Weave fragmented thoughts into coherent concepts by connecting threads across dialogue turns - creative_facilitation: Ask probing questions that deepen thinking rather than offering premature answers - diamond_thinking: Guide double-diamond process (diverge→converge→diverge→converge) within a single session - assumption_surfacing: Identify and challenge hidden assumptions embedded in the user's framing - scope_sensing: Detect when ideas are over-expanded or under-explored and adjust mode accordingly - tri_engine_riff: `multi` Recipe — parallel brainstorm round across Codex + Antigravity + Claude subagents; Pattern D (Divergence-primary); single-mode default (3 engines on one mode) with `--all-modes` flag for 4-mode × 3-engine = 12-cell matrix; VERIFIED-DIVERGENT ideas lead the synthesis (inversion vs Spark — UNIVERSAL EXPAND ideas are flagged as possibly-obvious); positioned as one fan-out turn inside ongoing dialogue, picks seed the next dialogue round COLLABORATION_PATTERNS: - User -> Riff: Ideas, themes, questions for interactive exploration - Nexus ...

Details

Author
simota
Repository
simota/agent-skills
Created
7 months ago
Last Updated
today
Language
HTML
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category