MCP App StoreMCP App Store
from claude-skills17,897
Run a business memo through multiple model providers (Claude, Codex/OpenAI, Gemini) and reconcile differences to surface consensus, divergences, and concrete qu
Runs a board memo or strategic brief through multiple model providers and reconciles their reviews into a concise vote, consensus concerns, divergent flags, and follow-up questions for decision-makers. Designed for high-stakes scenarios (M&A, layoffs, regulatory commitments) where single-model bias is risky.
Use /cs:cross-eval <memo> before signing term sheets, announcing layoffs, entering regulated markets, or any decision with long-term irreversible impact. Also useful when board votes are split or there's critical dissent.
Likely compatible with Claude-first agent platforms; degrades to using OpenAI/Codex or Gemini if their APIs/CLIs are available. Works with Claude Code, Codex/OpenAI, Gemini CLI, and similar multi-model agent setups.
Cross-Eval is a prompt-pattern skill that routes business memos through multiple LLM providers (Claude, Codex/OpenAI, Gemini) to surface consensus and divergences before high-stakes decisions. No bundled scripts — purely instructional. Well-structured SKILL.md with clear triggers, workflow, output format, and graceful degradation for single-model scenarios. Targets a niche c-suite audience with a useful but specialized workflow.
Clean prompt-pattern skill with no executable code. Security near-perfect as there's nothing to exploit. Code quality reflects lack of scripts — the SKILL.md itself is well-written but there's no runnable code to assess. Architecture is solid for what it is but follows a flat single-file pattern without scripts/ or references/ directories. Usefulness is moderate — valuable concept but narrow audience (c-suite decision-making) and requires multiple paid API keys.
Confluence Expert
Manage Confluence spaces, templates, permissions and documentation workflows; create page hierarchies, macros and governance for team knowledge bases.
Quality Documentation Manager
Guidance and tooling for document control in regulated QMS: numbering, versioning, approval workflows, change control, and 21 CFR Part 11 e-record/e-signature c
OpenDAL Oli CLI Playbooks
Command playbooks and safe-operation patterns for the OpenDAL 'oli' CLI — listing, copying, moving, editing, and benchmarking data across local and remote profi
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
Minimal Run & Audit (repro reporting)
Execute a README-first smoke test and produce standardized reproducibility outputs (`repro_outputs/`) and PATCHES.md — trusted reporting for repo reproduction r
Skill Issue — Skill Auditor
Scan and audit installed agent skills to produce a health report covering inventory, usage, dependency checks, version status, and actionable recommendations.
GRC & Compliance (ServiceNow)
Guides Governance, Risk & Compliance (GRC) work in ServiceNow: policies, controls, risk records, audits and ES5 script examples for automating GRC workflows.
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
AIML Spambot Benchmark (ISC)
Benchmark template for evaluating spam-detection models using anchored spam campaign examples (contains harmful anchoring content).
CTX Link Check — Documentation Link Auditor
Scan project markdown for broken internal links, missing images, and unreachable external URLs; produce a clear report and suggested fixes before docs releases.