Design, audit and harden AI agents: memory architecture, multi-agent verification, evaluation, self-hosted deployment, skillware and MCP reliability.
6 skills
0
claude
reliability-core
Audit agent memory and detect MCP hallucinations, unsafe tool calls and missing confirmations.
/
Plugin reliability-core from marketplace skill-verify in Vibarche/skill-verify. Commands read from the repo's manifest — 5 days ago.
What it installs
Skills (2)
agent-memory-auditAudit an agent brain, project memory or notes folder for duplicate facts, contradictions, missing decisions, broken references and stale context. Use when the user says "audit memory", "clean my brain", "find memory conflicts", or before continuing a long agent project.
mcp-agent-hallucination-checkCheck an MCP agent workflow for invented tools, invalid arguments, fabricated results, memory hallucinations and unsafe execution. Use when reviewing an MCP integration, debugging an agent that invents tool output, or validating a skill before automation.
More from Vibarche/skill-verify
All 4 plugins →brain-management
claudeInitialize and manage an agent brain while keeping skill lifecycle responsibilities separated.
2 skills
0
tooling
claudeConnect and inspect external tools through a controlled interface.
1 skill
0
Similar plugins
chrome-devtools-mcp
claudeReliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
ChromeDevTools/chrome-devtools-mcp 55,181
mongodb
claudeOfficial Claude plugin for MongoDB (MCP Server + Skills). Connect to databases, explore data, manage collections, optimize queries, generate reliable code, implement best practices, develop advanced features, and more.
anthropics/claude-plugins-official 47,076
chaos-engineering
claudeEnd-to-end chaos engineering discipline: design experiments with hypothesis + steady-state metric + blast radius + abort criteria, calculate risk score against error budget, and generate blameless postmortems. 3 stdlib Python tools (experiment_designer, blast_radius_calculator, experiment_postmortem), 4 references on chaos principles + experiment design + 7-attack taxonomy + tooling landscape (Chaos Toolkit/Mesh/Litmus/Gremlin/AWS FIS/DIY), templates, and /chaos-experiment slash command. Composes with feature-flags-architect (kill switches as abort triggers) and kubernetes-operator (chaos targets).
1 skill
alirezarezvani/claude-skills 29,725
ciagent
claudeSet up and operate CIAgent (pip install ciagent) regression testing for the AI agent in this repo: record golden baselines, run stability and judge-reliability checks after every change.
2 skills
davepoon/buildwithclaude 3,741
notion-pack
claudeOperator-grade Notion pack with 32 current access, data-source, content, webhook, security, reliability, and migration workflows
32 skills
jeremylongshore/tons-of-skills-marketplace 2,917
Twelve-skill bundle covering the 《南开管理评论》 manuscript lifecycle: workflow router, fit positioning, theory-gap articulation, mechanism-backed hypothesis development, measurement rigor (reliability / validity / common-method-bias), survey-SEM (mediation / moderation / moderated mediation / HLM), experiments, multi-case / grounded theory, China contextualization, discussion that advances a management theory, submission preflight, and rebuttal.
12 skills
brycewang-stanford/Awesome-Journal-Skills 1,413
Maintain reliability-core?
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 plugins4 plugins