friction-p-scores

Estrelas0

Forks0

Atualizado19 de março de 2026 às 00:17

Translate turn difficulty into explicit p-scores for efficiency, friction, and skill-candidate potential.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Fonte

open-hax

open-hax/eta-mu-pi

Abrir repositório GitHub Ver repositórios do creator

Download

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Analistas de gestãoNegócios e Operações Financeiras·SOC 13-1111

Explorador de arquivos

2 arquivos

SKILL.md

readonly

name	friction-p-scores
description	Translate turn difficulty into explicit p-scores for efficiency, friction, and skill-candidate potential.

Skill: Friction p-scores

Goal

Make "this felt hard" measurable enough to reason about.

Use This Skill When

You want explicit confidence scores for whether a turn was efficient.
You want a principled threshold for when to incubate a new skill.

Do Not Use This Skill When

You only need a narrative explanation and no scoring.
The turn lacked enough evidence to justify any estimate.

p-score set

p-efficiency: confidence the path was near-minimal.
p-friction: confidence the turn was harder than it should have been.
p-skill-candidate: confidence a reusable skill would pay off.

Heuristic anchors

Repeated searching, backtracking, or tool thrash increases p-friction.
A clean first-pass path increases p-efficiency.
Patterns that obviously generalize across tasks increase p-skill-candidate.
One-off environment weirdness should lower p-skill-candidate.

Output

A small scored tuple suitable for a reflection ledger or spore gate.

Mais deste repositório

mesmo repositório

docker-no-root

open-hax/eta-mu-pi

Never run Docker containers as root. Enforce USER directive in Dockerfiles and user: in compose files. Database images are the only exception.

2026-04-090

pnpm-workspace-migration

open-hax/eta-mu-pi

Handle packages migrating between pnpm workspaces. Clean stale root copies, update workspace configs, fix broken workspace:* references.

2026-04-090

session-source-recovery

open-hax/eta-mu-pi

Recover lost source files from pi session history when files were deleted but never committed to git.

2026-04-090

clock-model-evolver

open-hax/eta-mu-pi

Improve the Hormuz clock model through new signal classes, schema changes, uncertainty modeling, and better rendering or branch logic

2026-04-060

fork-tax-concurrent-agent-guardrails

open-hax/eta-mu-pi

Revise fork-tax protocols so they assume concurrent agents by default in shared workspaces, forbid destructive repo-wide cleanup of unrelated dirt, and require path-scoped staging plus explicit blocker recording.

2026-04-040

fork-tax

open-hax/eta-mu-pi

Persist the full working state into git (commit + tag + push + manifest artifacts) as a deterministic handoff snapshot. Use when the user requests Π / fork tax / full dump.

2026-04-040

name	friction-p-scores
description	Translate turn difficulty into explicit p-scores for efficiency, friction, and skill-candidate potential.

Skill: Friction p-scores

Goal

Make "this felt hard" measurable enough to reason about.

Use This Skill When

You want explicit confidence scores for whether a turn was efficient.
You want a principled threshold for when to incubate a new skill.

Do Not Use This Skill When

You only need a narrative explanation and no scoring.
The turn lacked enough evidence to justify any estimate.

p-score set

p-efficiency: confidence the path was near-minimal.
p-friction: confidence the turn was harder than it should have been.
p-skill-candidate: confidence a reusable skill would pay off.

Heuristic anchors

Repeated searching, backtracking, or tool thrash increases p-friction.
A clean first-pass path increases p-efficiency.
Patterns that obviously generalize across tasks increase p-skill-candidate.
One-off environment weirdness should lower p-skill-candidate.

Output

A small scored tuple suitable for a reflection ledger or spore gate.