MCP App StoreMCP App Store
from cv-train-stack13
Review, run, validate and audit computer vision model training with checks for dataset quality, preprocessing consistency, augmentation, and deployment validati
Structured CV model training and review workflow that helps teams catch mistakes that break production accuracy. It scans a project for training scripts, datasets and preprocessing steps, runs a preflight review, executes controlled training runs (local or remote), validates exported models, and audits training/inference consistency.
Use this skill before starting a new training run, when retraining models, or right after a run finishes. Triggers include: preparing training, reviewing training config, validating an export, or auditing preprocessing for production deployment.
Most general-purpose code-capable assistants (Copilot/Codex/Gemini CLI/Claude Code) can use this skill to orchestrate training and checks.
CV model training review and execution skill with subcommands for review, run, validate, and audit. No bundled scripts — all logic is guidance in SKILL.md with reference docs loaded on demand. Clean, well-structured content covering real production pitfalls (preprocessing mismatches, quantization drift, training-serving skew). No security concerns whatsoever.
Well-written skill for CV practitioners. Common mistakes section is genuinely useful. Architecture follows progressive disclosure pattern well. Would benefit from having scripts/ for automated checks (dataset balance, preprocessing consistency) but works fine as guidance-only.
GraphQL Inspector — Validate
Validate GraphQL operations against a schema with configurable depth, complexity, alias and directive limits to catch errors before runtime.
Alpha Forge Pre-Ship Quality Gates
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.
Evolve — Goal-Driven Improvement Loop
Autonomous improvement loop that selects high-value work, runs a full research-plan-implement (/rpi) cycle, validates changes, and repeats to compound repo impr
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
Build Unplanned Feature
Orchestrates ad-hoc feature development: requirement gathering, planning, implementation and validation across task-planning, implementation, and validation loo
DSPy — Declarative LM Programming
Use DSPy to build declarative, modular LM pipelines, optimize prompts automatically, and assemble reliable RAG/agent systems with structured signatures and opti
WeChat MP Article Writer & Publisher
End-to-end toolchain for drafting, rendering, validating and publishing WeChat Official Account articles using templates, image planning and pipeline scripts.
API and Interface Design
Guides design of stable, predictable APIs and interfaces — contract-first patterns, error semantics, pagination, and naming conventions for robust integrations.