Genel Claude Code pazaryerlerinden 13 eklenti. Her biri birlikte yüklenen beceriler, eğik çizgi komutları, ajanlar, kancalar veya MCP sunucuları içerir.
Bu filtrelere uyan 13 eklenti gösteriliyor.
ego-jevZephyrDeng/ego-jev1
slopware-skillstranscendr/slopware-skills1.claude-plugin/marketplace.json içeren depoyu gönderin, biz de her plugini listeleyelim.
Marketplace gönderSkills (serve, use, eval, adopt, guard, mcp) and MCP tools (decide, noul, choice, score) for the local Jev-Style decision model. Needs `jev-style serve` running.
Turns a legal question, a set of draft questions, or source material such as a statute, jury instruction, rubric, contract checklist, or coding manual into a battery of narrow questions that TypeSafe's Jev, a fast classifier that returns probabilities rather than prose, can answer reliably across many documents. The skill breaks conclusions such as negligence, felony murder, or standing into element-level questions, writes the governing rule into each question, and delivers the questions alone, in Jev's request format or in plain English. Built for legal work that asks the same questions of many texts: coding statutes across jurisdictions, coding opinions or case files for empirical research, checking contracts against a review checklist, screening intake narratives, and grading student work against a rubric. Use when asked to write Jev questions, build a classifier for legal documents, or turn a legal test into yes-or-no questions. Running the questions requires Jev access; writing th
PreToolUse hook: the local Jev-Style model checks Bash/Write/Edit/Read/WebFetch/MCP calls and answers allow / ask / deny. Fails safe to ask.
Design, integrate, evaluate, self-host, and troubleshoot typed System One decision models including TypeSafe Jev, Convai Innovations Laya, CLM, and experimental Strands Decider. Use for Choice/Score/Noul judgments and experimental Jev image/Box queries inside deterministic software, app-control loops, routing, ranking, guardrails, calibration, semantic code linting and post-edit feedback, DevOps decision support, confidence-based escalation, or private open-model inference. Do not use for syntactic/style linting, exact policy or authorization, open-ended generation, or generic LLM serving without a bounded decision contract.
jev_classify, jev_check, jev_score, jev_rank, jev_ask over MCP, plus the /jev skill.
Entry point for browser tasks in ego (ego lite): multi-step clicking runs on Jev (TypeSafe System One), one ~0.4 s typed decision per step; reading, extraction and screenshots stay plain ego calls.
Block an assistant reply when Jev judges a sentence, in context, to be a shortcut instead of an explicit statement.
productivity给 ego lite 的可插拔决策层：默认 System One（Jev），可换本地 / 其他 OpenAI 兼容后端；执行层带 fail-closed 护栏。
Find, build, evaluate, and hill-climb decision-model systems. Apply composition, decision theory, calibration and outcome evaluation across software, business and everyday decisions. TypeSafe Jev is the default hosted exemplar. Independent of TypeSafe.
Teaches Claude the Jev API, when to use Choice, Score, or Noul, how to route on confidence, and where to find prior art for a design before building it.
developmentProbes which coding-agent CLIs are installed and authenticated, routes each task to the best one with TypeSafe Jev, dispatches it, and judges whether the worker finished.
Explore what to build with Jev, improve existing workflows, and plan a first experiment.
Asks TypeSafe Jev which installed skill fits the prompt and, in shadow mode, logs the answer instead of speaking it. Experiment concluded; kept as a reference implementation.
