sketch

Solid

Recognize and revise concrete sketches to discover a form when descriptions cannot settle intent. Type: (FitUnrecognized, Hybrid, SKETCH-RECOGNIZE-CYCLE, FormIntentSeed) → RecognizedForm

AI & Automation 163 stars 15 forks Updated today MIT

Install

View on GitHub

Quality Score: 84/100

Stars 20%
74
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Hypotyposis Protocol Discover what a form should be by encountering concrete sketches and marking what does not fit, until the user recognizes a specific version as the form for a stated purpose. Type: `(FitUnrecognized, Hybrid, SKETCH-RECOGNIZE-CYCLE, FormIntentSeed) → RecognizedForm`. ## Definition **Hypotyposis** (ὑποτύπωσις): an outline or sketch — a first drawing of a position rather than its finished statement. A dialogical act for the moment when a form has to be made and the intent behind it cannot yet be settled from descriptions: the user can say what is wrong with a thing in front of them long before they can say what the thing should be, because good fit has no positive description of its own while each misfit is immediate and can be pointed at (Alexander, 1964). So the protocol runs the other way round from a specification: the AI drafts each round's focus, the perception it needs, and its variants, relays the draft with the basis that chose each, and produces the sketches; the user marks a specific version — what does not fit and what to keep — as first-class utterances, settling or sending back the round's readings in the same answer; the AI revises the retained version under those marks; and the loop ends when the user recognizes one version as the form for a stated purpose and names where it lives. ``` ── FLOW ── Hypotyposis(I) → detect(I, ctx) → [¬fit_unrecognized(I, ctx)] no_activation_relay → exit (NoActivationRelay) bind(I) → Λ.history (each pri...

Details

Author
jongwony
Repository
jongwony/epistemic-protocols
Created
9 months ago
Last Updated
today
Language
JavaScript
License
MIT

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category