Browse The Skill Store

ML Serving Architecture Selector

by monna

$19

Choose and justify batch, real-time, streaming, edge, managed, Kubernetes, or serverless model serving with an evidence-tagged ADR.

Repo Context Architecture — AI Native Enterprise Engine

by Lorky Rongai

$129

Transform standard repositories into AI-native environments with machine-readable documentation and contribution protocols.

MLOps Maturity Scorecard

by monna

$9.99

Score eight MLOps lifecycle dimensions with evidence tags, coverage controls, and a prioritized gap report.

Align end-to-end request deadlines, retries, cancellation, database work, and side-effect ownership so server work stops when its budget is gone.

ChatGPT Skill Trigger Test Harness

by monna

$15

Test ChatGPT workspace skill routing across direct triggers, exclusions, collisions, Memory conditions, and conversation carryover.

AI Agent Red Team & Production Readiness

by Shivangi Singh

$19.99

Stress-test AI agents for security, reliability, tool abuse, data leakage, failure modes, and production readiness before deployment.

Training Pipeline Failure Forensics

by monna

$19.99

Rank evidence-backed causes of ML training crashes or silent degradation, then design the cheapest discriminating test and minimal reproduction.

AI Workflow Resilience Engineer

by Shivangi Singh

$19

Design and harden AI workflows against failures, duplicate actions, retries, rate limits, tool outages, and unreliable agent behavior.

Optimize agent performance and reduce costs through structured context budgeting, memory architecture, and handoff notes.

Audit and repair decaying agent instruction files to fix contradictions, stale rules, and token bloat.

Architect production-ready AI systems with deployable prompts, evidence policies, schemas, and test suites.

Generate multi-image series with locked character identity, product geometry, and style consistency.

SRE Infrastructure — Production Debugging & Recovery System

by Lorky Rongai

$9

A Principal SRE agent for production debugging, root cause analysis, and generating deployment-ready fixes.

Detect, inventory, and risk-score unofficial AI agents, custom GPTs, and MCP tools across your organization.

A systematic auditing engine that scores and rewrites agent instructions for safety, efficiency, and robustness.

Design a vendor-neutral telemetry contract for one AI agent workflow: traces, events, metrics, evaluations, redaction, dashboards, and alert hypotheses.

Turn a supplied agent incident or behavior change into a synthetic regression pack, observable assertions, release gate, and human-reviewed monitoring plan.

Systematically audits AI models, APIs, and cloud workflows to identify and eliminate automation spend leaks.

Converts finished AI projects and incident logs into reusable playbooks, patterns, and operational checklists.

Repair ignored DNS TTLs, startup-only resolution, stale endpoint reuse, retry-to-same-address loops, discovery refresh stampedes, and DNS/pool confusion.

Detects, classifies, and prioritizes web performance regressions by correlating metrics with deployment changes.

Map agent cost drivers and design measurable task budgets, stop conditions, routing hypotheses, and quality-latency-cost experiments.

Review a supplied Agent Skill before installation and produce a documented adopt, sandbox, revise, or decline decision with provenance, permissions, update, and approval controls.

Transforms high-level AI concepts into production-ready operating plans with risk mitigation and agent architectures.