LLM Mart Basic

Use this skill for Azure Cosmos DB platform operations and design review, especially accounts, databases, containers, partition-key design, throughput and RU posture, consistency choices, indexing, throttling, multi-region replication, private connectivity, and Cosmos DB evidence

Review Azure cost estimates, pricing calculator assumptions, SKU and region choices, environment sizing realism, and uncertainty handling using official Microsoft cost-management and pricing documentation only.

Review Azure spend governance, budgets, alerts, cost analysis visibility, reservation and savings-plan awareness, tagging for cost allocation, exports, and FinOps ownership with official Microsoft documentation and sampled read-only Azure evidence where available.

Use this skill for Microsoft Entra ID specialist work, especially Conditional Access, authentication methods, MFA and SSPR registration, identity protection, workload identities, app registrations, external identities, agent identities, break-glass posture, and tenant identity co

Use this skill for Azure Policy guardrails, initiatives, assignment scope, management-group inheritance, exclusions, remediation risk, tag governance, allowed regions or SKUs, and staged governance rollout reviews.

Review Microsoft Entra identity governance posture for Azure operators, with focus on standing versus eligible access, Privileged Identity Management, access reviews, entitlement management, ownership gaps, and least-privilege control patterns.

Audit Azure Key Vault secret lifecycle posture across RBAC, soft delete, purge protection, rotation, expiration, metadata hygiene, Event Grid notifications, and recovery readiness. Use when the question is whether secret management is actually safe, not just present.

Use this skill when reviewing Azure Key Vault certificate issuer configurations for cert-manager on AKS. Trigger on any request to audit Key Vault certificate policies, Managed Identity role assignments, exportability settings, private endpoint connectivity, integrated CA credent

Use this skill for Azure landing-zone design, management-group and subscription hierarchy reviews, platform-versus-application boundary decisions, or multi-subscription Azure platform architecture critiques that span governance, identity, networking, security, and operations.

Guard live AKS deployment rollouts with PDB audit, maxUnavailable/surge validation, rollout pause/undo gates, and post-rollout health verification.

Guard live App Service slot swaps with sticky-settings audit, warmup probe verification, swap-with-preview staging, and instant rollback posture.

Guard live ARM, Bicep, and Deployment Stack changes with what-if evidence, denySettings review, changeset diff, rollback posture, and approval gates.

Gate Azure budget action changes and GPU/HPC SKU provisioning against approved spend limits, with quota audits and emergency spend-stop playbooks.

Guard live permanent Microsoft Entra ID and Azure RBAC role assignments with scope audit, principal-type risk classification, dangerous-role detection, and explicit approval gates before write. Use only when a direct (non-PIM) role assignment is intentionally requested against a

Guard Key Vault key rotation, rotation policy changes, soft-delete enforcement, and purge-protection enablement with irreversibility warnings and rollback evidence.

Gate Entra ID PIM eligible role activations with justification, MFA, ticket binding, time-bound scope, and approval workflow gates before any privileged Azure role becomes active.

Use this skill to classify a user task, select the right Azure specialist agent or team of specialists from the catalog, and dispatch them. Single specialist for focused single-domain tasks; parallel team (max 4) for tasks that span multiple domains. Never auto-dispatches live-gu

Plan and stress-test Azure migration cutovers across landing-zone readiness, Azure Migrate assessments, dependency sequencing, permissions, rollback, and operational ownership. Use when a migration plan needs a go/no-go verdict instead of vague optimism.

Use this skill for Azure network architecture review, hub-spoke critique, routing and DNS dependency analysis, shared-services boundary decisions, firewall placement review, and landing-zone connectivity guidance.

Use this skill for Azure Monitor, Log Analytics, Application Insights, alerting, KQL triage, telemetry-gap analysis, workbooks, or operator-grade incident and posture investigations.

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

Lightweight Q&A about the project — answer from context and return, no routing, no state change.

Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

Clean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.

Show the codeArbiter command catalog — the public command list and what each routes to.

Create a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.

Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.

Audit stale provenance-tracked docs on request. Report first; re-scout or re-baseline only for selected docs.

Build project context from an existing codebase through isolated scouts, resolve gaps, and preserve initialization gates.

Investigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff. A no-action close records a board note. Not for implementing a known fix, new features, or explanation-only questions.

Develop greenfield project context through a layered interview, preserve decisions, and initialize only after the required gates.

Verify the active host install, package, command ownership, enforcement, and harmless live-fire probe. Read-only.

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.

Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.

Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.

Open a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. Merge and discard need explicit authority.

Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.

AI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face recognition, and get proactive anomaly alerts.…

A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for ma…

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Web & desktop (Electron) client for the OCTO open workplace — one React + TypeScript codebase shipping browser and PC surfaces, with first-class AI agent UX.

同花顺官方 A股金融数据服务，提供股票实时行情、历史行情、财务报表、指数、板块、涨停等数据，适用于 AI Agent、量化研究和应用开发，支持 API、MCP、CLI 和 Python。Official Tonghuashun (HiThink) A-share financial data service provi…

Open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, SQLite and 15+ more databases like DuckDB, ClickHouse, Redis and Firestore. Built-in MCP server…

🤖 Local-assist BOSS Zhipin CLI for AI agents — search, welfare filtering, shortlist, JSON-envelope output; low-risk & compliant by default.

The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, no extra LLM costs). Drives your live graph: edits,…

Persistent memory for Claude Code — identity, context, and continuity across sessions

🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI…

A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Visualization · PPT · Coding · Agents · Lo…

World Memory Protocol.

Run your own organization of agents.

The most RAM efficient harness

AI-native, free, open-source alternative to Jira, Trello, ClickUp & Monday. Built for Scrum teams where humans and AI agents collaborate as equals — on the same…

Free open-source desktop app that scrapes JAV metadata and generates NFO + cover art for Jellyfin, Emby & Kodi. No Docker, no CLI — one-click install on Windows…

A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skills directories — “Install once, sync ever…

天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（Tui X Gui），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 97–99%）和深度适配。它跳出了传统 AI 编程助手把大模型仅当成“工具”的局限，基于认知虚拟机 (CVM)、自感知层和信息素（Stigmergy…