MCP App StoreMCP App Store
from onchainos-skills283
Explains where OnchainOS writes audit logs, the JSONL format, entry fields, and rotation rules to help developers troubleshoot CLI/agent issues offline.
What it does: Provides a concise reference for locating and interpreting OnchainOS audit logs. The skill explains exact file paths (~/.onchainos/audit.jsonl or $ONCHAINOS_HOME/audit.jsonl), the JSON Lines format, the device header and per-entry fields (timestamp, source, command, ok, duration_ms, args redacted, error), and rotation behaviour. When to use it: Use when a developer asks where audit logs are stored, how to export or read them, or what fields to expect in entries. It explicitly excludes on-chain operations like balance checks or swaps. What's included: - Scripts: none - References: in-SKILL.md format notes - Instructions: direct wording to report the path/format and rotation notes. Compatible agents: developer-focused assistants and CLI-oriented agents (Copilot/Codex-style, CLI helpers).
The okx-audit-log skill is a small reference document (12 lines) explaining where OnchainOS writes audit logs, the JSONL format, entry fields, and rotation rules. It has no scripts and its SKILL.md body was null in the DB — the content had to be fetched from a different skill directory (okx-agentic-wallet) on GitHub. The standalone audit-log reference is thin: just a file path, format description, and rotation rule. Useful as a quick reference but not a standalone skill.
The skill_md_body was null in the fetch output and the GitHub URL (okx/onchainos-skills/skills/okx-audit-log/SKILL.md) returns 404. The audit-log content exists only as a reference file inside okx-agentic-wallet. This appears to be a DB discovery error — the skill was likely indexed as a standalone skill when it's actually just a reference doc within a larger skill. Security score is high (no scripts, no executable content, no credential exposure), but architecture is poor (not a proper standalone skill) and usefulness is limited (thin content, niche audience).
Monad Development
Practical developer skill for deploying and verifying smart contracts, configuring Foundry projects, and integrating frontends (viem/wagmi) on the Monad blockch
Uloop: Execute Dynamic Code
Run small C# snippets in the Unity Editor via the uloop CLI for editor automation tasks like prefab wiring, AddComponent flows, and scene edits—without writing
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.
Prompt Engineering Patterns
A practical collection of prompt engineering techniques and patterns for building reliable, controllable LLM prompts: CoT, few-shot, structured outputs, templat