claude

gosleep-evals

Evaluation, verification, reporting, and spend policy for gosleep — scenario runner, efficient evals, verifier-skeptic, HTML report creator, extra-usage session modifier.

0 on GitHubby Roman Lv0.1.0updated 2 months agoevals
/

Plugin gosleep-evals from marketplace gosleep-plugins in ainstance-labs/gosleep-plugins. Commands read from the repo's manifest — 5 days ago.

What it installs

Skills (5)

  • agentic-report-creator

    Turn a structured findings payload (JSON) into a professional HTML dashboard report — Vercel/Linear aesthetic, light + dark themes, English primary with a Russian translation shell, screenshots in a keyboard-navigable lightbox, and integer-numbered items that each name their Jira ticket. Zero depend

  • agentic-scenario-runner

    Use when runs, samples, evals, or a model comparison are on the table for an AI agent/LLM behaviour — before spending any API calls or agent-hours on them. Triggers - "прогнать сценарий", "протестировать агента", "сравнить модели", "сколько прогонов", "замерить поведение агента", "свип по моделям",

  • efficient-agent-evals

    Use when evaluating an AI skill, prompt, or agent/harness's BEHAVIOR (designing or running evals) and cost matters — before launching any multi-scenario RED/GREEN or LLM-as-judge eval, or when an eval run spawned a huge number of judge/sample subagents or burned excessive tokens. Keeps the same eval

  • extra-usage

    Use when the owner opts into spending at maximum — "lots of tokens", "use the best models", "ultra mode", "go wide", "don't ration", "maximum usage" — and the default token-economy policy (Sonnet verification, no orchestrator workflows, small capped fan-outs, budget/loop-guard) is too conservative.

  • verifier-skeptic

    Use when auditing a shipped Jira Epic against its design source of truth — a pixel-perfect audit across three lanes (architecture, functionality, design). Adversarial by design (skeptical review that assumes there ARE deviations and hunts as many as possible) for verification / проверка после реализ

View source on GitHub

More from ainstance-labs/gosleep-plugins

All 3 plugins →

gosleep-delivery

claude

Delivery conventions for the gosleep harness — Jira+GitHub epic/task workflow, PRD authoring, handoff protocol.

4 skills

0

gosleep-orchestration

claude

Orchestrating and steering a live gosleep fleet — delivery-agent orchestration, tmux pane discipline, remote-control from phone.

3 skills

0

Similar plugins

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

agent-skills

claudecodex

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

addyosmani/agent-skills 116,782

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

agentdb

claude

AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server

3 skills · 1 command · 1 agent · 1 MCP server

ruvnet/ruflo 81,589

ifixai

claudecodex

Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).

1 skill · hooks

ifixai-ai/iFixAi 45,158

llm-finetuning

claudecodex

Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.

10 skills · 2 commands · 3 agents

wshobson/agents 42,461

Maintain gosleep-evals?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins3 plugins