summon

Solid

Channeling the documented thinking of named notable figures (an 'itako' medium) — their mental models, heuristics, and decision-style as advisory lenses. Not for decisions (Magi) or personas (Cast).

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: - figure_channeling: Apply a named notable figure's documented mental models, heuristics, and characteristic moves to the user's problem - conclave_panel: Independently channel 2-5 figures and surface their contrasts/tensions without forcing consensus - expert_critique: Have a named figure critique a plan, draft, or decision by their documented standards - figure_roster: Author and maintain reusable figure profiles (frameworks, heuristics, known positions, sources, attestation notes) - attestation_tiering: Tag every channeled claim ATTESTED / INFERRED / SPECULATIVE and strip fabricated quotes - ethics_gating: Refuse deceptive uses (impersonation, fraud, fabricated endorsement, defamation); stricter handling for living persons - caricature_guard: Channel the reasoning system, not a stereotype or catchphrase parody - magi_handoff: Package named-expert viewpoints as inputs to multi-perspective decision arbitration COLLABORATION_PATTERNS: - Pattern A: Expert Lens for Decision (Summon → Magi → Builder) — channeled named-expert viewpoints feed arbitration - Pattern B: Reframe-then-Channel (Flux → Summon) — after reframing, channel a thinker known for that frame - Pattern C: Ideation Seed (Riff ↔ Summon) — expert mental models seed brainstorming - Pattern D: Founder Mentorship (Sage → Summon) — channel a specific named founder/investor for targeted advice - Pattern E: Critique Pass (Summon → User/Builder) — a named figure critiques a plan or draft by thei...

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

AI & Automation Listed

expert

Summon domain experts (fields, schools of thought, named people) from the base: pick the ones that genuinely fit (usually 1-3), embody them or run them as sub-agents, and grow the base by proposing new experts from the model's knowledge or the web. Invoke explicitly.

0 Updated 3 weeks ago
xtompie
AI & Automation Listed

dialectic-brainstorming

Brainstorm a consequential, no-ground-truth question with a panel of diverse minds, then resolve it dialectically. A casting step derives orthogonal thinking-axes for the question (each a quality to maximize) and casts one persona per axis; the personas propose and cross-critique concrete candidates while a neutral Synthesizer prunes, recombines across axes, and holds a frontier — returning a short list, not one winner. Use for naming (products, tools, projects), positioning, or any choice of consequence with no objectively correct answer where you want many genuinely different perspectives, not one. Triggers: /dialectic-brainstorming, "brainstorm this with a diverse panel", "what should we name…", "give me a shortlist from multiple perspectives".

0 Updated 4 days ago
mehdiforoozandeh
AI & Automation Solid

deliberation

Multi-perspective synthesis structure — Innovator (propose) → Devil-Advocate (challenge) → Mediator (synthesize) 3-layer execution. Outputs conditional verdicts without binary win/loss. Activates on "deliberation", "battle this out", "weigh the pros and cons", "review from multiple angles", "which side is right?". Optional deep-insight persona jurors for domain-specific views. Designed for design decisions, skill proposals, and architectural choices.

7 Updated today
chrono-meta