LLM Mart Basic

Keep a clear audit trail of actions, tools used, actors, outcomes, and errors for sensitive work. Use for compliance-sensitive tasks, incidents, or when the user asks what changed.

Identify realistic link opportunities - partners, guest posts, directories, digital PR, and linkable assets. Use to build authority for a domain.

Snapshot configs, memory, and skills before risky edits, and define a rollback path. Use before bulk refactors, migrations, or skill/config changes.

Produce structured, documented, readable long-form articles - tutorials, opinion pieces, industry analyses. Use for editorial content beyond pure SEO pieces.

Define, store, and enforce brand voice across all content - vocabulary, tone, do/don't lists per brand. Use to keep multi-brand output consistent.

Detect and score buying signals - funding, hiring, tech changes, leadership moves, expansion, regulation. Use to prioritize which accounts to contact now and with what angle.

Plan and run multichannel campaigns with an editorial calendar, asset tracking, and post-mortems. Use for any coordinated marketing push across channels.

Recommend career moves, skill investments, and trajectory options based on profile, market demand, and goals. Use for career decisions and development plans.

Run the Navin Career desk for freelance missions and permanent jobs. Search authorized sources, score matches, tailor a CV from the Master CV, import pasted LinkedIn offers, track inbox and follow-ups. Use for /career, Freelance, Jobs, TJM, candidatures.

Turn client projects into commercial case studies - problem, solution, results, and metrics. Use to build sales proof from delivered work.

Work with GitHub Actions, GitLab CI, and deployment pipelines - inspect runs, fix workflows, and gate releases. Use gh when available for Actions.

Search and install agent skills from ClawHub, the public skill registry.

Operate AWS with the aws CLI - EC2, EKS, S3, IAM, VPC, RDS, Lambda, costs. Read-first; mutations gated by approval.

Operate Microsoft Azure with the az CLI - VMs, AKS, storage, networking, ARM resources, costs. Read-first; mutations gated by approval.

Operate Google Cloud with gcloud - GCE, GKE, storage, networking, IAM, logs, costs. Read-first; mutations gated by approval.

Review code changes for bugs, security issues, regressions, and maintainability. Use on diffs, PRs, or before merge - pairs with gh CLI and code_review tool when available.

Write personalized cold emails that earn replies - research-based hooks, clear relevance, low-friction asks. Use for outbound prospecting messages.

Monitor competitors' offers, pricing, campaigns, hiring, and positioning changes over time. Use for ongoing competitive awareness, not one-shot analysis.

Analyze competitors' keywords, top pages, content structure, and backlink signals to find gaps. Use before content planning or when a competitor outranks the user.

Map the codebase and controls against security standards - OWASP ASVS, CIS Benchmarks, SOC 2, ISO 27001, PCI-DSS - producing a gap analysis with evidence and remediation. Use for /comply, audit prep, or "are we compliant with X?" questions.

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.

Intelligent issue resolution with multi-agent debugging, root cause analysis, and verified fix implementation

Scaffold a TypeScript project (Next.js, React with Vite, Node.js API, or library) with pnpm, testing, and dev tooling

Build AI assistant application with NLU, dialog management, and integrations

Create LangGraph-based agent with modern patterns

Optimize prompts for production with CoT, few-shot, and constitutional AI patterns

Run the eval-gated fine-tuning lifecycle end to end — eval harness, method selection, data, environment, training, checkpoint gate, export

Re-gate an existing fine-tuned checkpoint against the current eval harness and export it on PROMOTE

Orchestrate specialized agents to build a production ML pipeline from data analysis through training, deployment, and monitoring

Quick gallery search. Use when user runs /meigen-ai-design:find with keywords to browse inspiration.

Quick image generation. Use when user runs /meigen-ai-design:gen with a prompt. Skips intent assessment, generates directly.

Orchestrate cross-platform feature development across web, mobile, and desktop with API-first architecture

Set up monitoring and observability with Prometheus metrics, Grafana dashboards, distributed tracing, log aggregation, and alerting

Implement SLOs with SLI selection, error budgets, burn-rate alerting, dashboards, and reporting

Run an AI-assisted code review that combines static analysis tools with AI review of security, performance, and architecture

Coordinate specialized review agents in parallel or in sequence and synthesize their findings into one code review

Full quality certification with badge

Compare two skills head-to-head

Evaluate a plugin or skill for quality

Verify every receipt in ./receipts/receipts.jsonl against the signer's public key. Detects tampered or malformed receipts across the audit trail.

Verify a single Ed25519-signed receipt file against the signer's public key. Returns exit 0 if valid, 1 if tampered, 2 if malformed or the key is missing.

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding