idogoldd/skills

Latest recorded source activity: October 7, 2026 at 11:00

SkillsMP catalog refreshed: November 2, 2026 at 18:02

skills collected: 1

GitHub stars: 1
GitHub forks: 0

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/idogoldd/skills.

Repository README

Repository README source: README.md

Read the source README

Expand full README

# Skills Agent skills by [idogoldd](https://github.com/idogoldd). They work with Claude Code, Codex, Cursor, and other agents that read `SKILL.md` files. ## Install ```sh npx skills add idogoldd/skills ``` To install one skill: ```sh npx skills add idogoldd/skills --skill jev-audit ``` ## jev-audit Finds the places in a codebase where rules guess at a fact that the data does not state. Examples: "is this email an out-of-office reply", "is this job title a CFO", "is this the same person". It ranks the places where a decision model such as TypeSafe's [Jev](https://docs.typesafe.ai) would replace the rules best. The agent writes one report, `JEV_OPPORTUNITIES.md`. For each opportunity, the report gives: - the file and lines, and what the current rules do - evidence that the rules miss: rule lists that keep growing, comments, and production samples when read-only access exists - scores for gap, stakes and fit - a replacement sketch that keeps the reliable checks in code - cost per 1,000 calls, the latency class, and rate-limit headroom - a plan to measure accuracy before you switch The skill does not change application code. It reads production data only when a read-only route exists and you allow it. Without that access, it continues from code and git history. Ask your agent: > Find Jev opportunities in this repo. ## License MIT

Loading the repository README…

Posts

See all →

ido gold

@idogolddOct 9, 2026 10:24 UTC

Skill release postQuote postIntegrate decision models

Post summary

jev-audit reviews a repository for bounded decisions that may suit Jev models, then presents candidate integrations and their tradeoffs. The creator shares the Skill and invites people to report useful findings.

Original post

View Skill details · skills/skills-jev-audit

Skills in this repository

classification pending

skill

occupation

description

updated

jev-audit

unclassified

Audit a repo for the top opportunities to replace brittle heuristics (regex, keyword lists, if-chains, hand-tuned scores, LLM-as-classifier prompts) with TypeSafe's Jev decision model. Returns a ranked report with evidence, a question design, and cost/latency…

2026-10-07

Showing 1 of 1 collected skill.