LLM Mart Basic

When the user wants to research keywords, find target keywords, or analyze search intent. Also use when the user mentions "keyword research," "keyword tool," "target keywords," "search volume," "search intent," "keyword difficulty," "topical map," "keyword clustering," "People Al

When the user wants to analyze backlinks, audit link profile, or identify link issues. Also use when the user mentions "backlink analysis," "backlink audit," "referring domains," "toxic links," "link profile," or "disavow file." For acquisition, use link-building.

When the user wants to build backlinks, acquire links, or improve off-page SEO. Also use when the user mentions "link building," "backlinks," "off-page SEO," "link acquisition," "outreach," "guest posting," "broken link building," "link outreach," "acquire backlinks," "how to bui

When the user wants to optimize the meta description or meta tag description. Also use when the user mentions "meta description," "meta desc," "page description," "SEO description," "search snippet," "SERP description," "description tag," "snippet for search," "meta description l

When the user wants to optimize for Featured Snippets, Position Zero, or snippet extraction. Also use when the user mentions "featured snippet," "position zero," "snippet optimization," "answer box," "definition box," "list snippet," "table snippet," "paragraph snippet," "PAA opt

When the user wants to optimize heading structure (H1-H6), fix heading hierarchy, or improve content structure. Also use when the user mentions "H1," "heading," "heading hierarchy," "content structure," "H2," "H3," "heading tags," "heading SEO," "multiple H1," or "heading structu

When the user wants to optimize images for search engines and performance. Also use when the user mentions "image SEO," "alt text," "image captions," "figcaption," "image optimization," "WebP," "lazy loading," "LCP," "image sitemap," "responsive images," "srcset," "image format,"

When the user wants to optimize internal linking, fix orphan pages, or improve link structure. Also use when the user mentions "internal links," "internal linking," "anchor text," "link equity," "internal linking strategy," or "orphan pages." For IA, use website-structure.

When the user wants to optimize meta tags other than title, description, Open Graph, or Twitter Cards. Also use when the user mentions "hreflang," "meta robots," "viewport," "charset," "canonical meta," "other meta tags," "meta robots noindex," "meta robots nofollow," "hreflang t

When the user wants to add or optimize Open Graph metadata for social sharing. Also use when the user mentions "Open Graph," "og:tags," "og:title," "og:image," "og:description," "Facebook preview," "LinkedIn preview," or "social share preview." For X (Twitter) link previews, use

When the user wants to add or optimize structured data (Schema.org, JSON-LD). Also use when the user mentions "schema," "structured data," "JSON-LD," "rich results," "rich snippets," "Google rich snippets," "featured snippet schema," "add schema to page," "missing structured data

When the user wants to understand or optimize for SERP feature types (PAA, sitelinks, rich results, AI Overviews). Also use when the user mentions "SERP," "SERP features," "search result features," "People Also Ask," "PAA," "sitelinks," "knowledge panel," "local pack," "rich resu

When the user wants to optimize the title tag, page title, or SERP title. Also use when the user mentions "title tag," "meta title," "page title," "SEO title," "SERP title," "browser tab title," "title optimization," "headline for search," "title too long," "title tag length," "d

When the user wants to add or optimize Twitter Card metadata for X (Twitter) link previews. Also use when the user mentions "Twitter Card," "twitter:card," "twitter:image," "twitter:title," "X preview," or "tweet preview." For Facebook/LinkedIn previews, use open-graph.

When the user wants to optimize URL structure, fix URL issues, or plan URL hierarchy. Also use when the user mentions "URL structure," "URL optimization," "slug," "clean URLs," "URL hierarchy," "URL path," "permalink structure," "URL best practices," "dynamic URLs," or "URL param

When the user wants to optimize videos for Google Search, video sitemap, VideoObject schema, or video SEO on websites. Also use when the user mentions "video SEO," "video sitemap," "VideoObject," "video thumbnail," "video indexing," "video preview," "key moments," "Clip schema,"

When the user wants to configure canonical URLs, fix duplicate content, or consolidate URL signals. Also use when the user mentions "canonical," "canonical URL," "duplicate content," "duplicate content fix," "preferred URL," or "URL consolidation." For GSC duplicates, use google-

When the user wants to optimize Core Web Vitals, fix LCP, INP, or CLS issues. Also use when the user mentions "Core Web Vitals," "CWV," "LCP," "INP," "CLS," "FID," "page speed," "page performance," "Largest Contentful Paint," "Interaction to Next Paint," "Cumulative Layout Shift,

When the user wants to improve crawlability, fix orphan pages, or optimize site structure for search engines. Also use when the user mentions "crawlability," "crawl budget," "orphan pages," "internal links," "site structure," "site crawlability," "infinite scroll," "pagination,"

When the user wants to fix indexing issues from Search Console, use noindex, or implement Google Indexing API. Also use when the user mentions "fix indexing," "not indexed," "Crawled - currently not indexed," "discovered - currently not indexed," "index coverage," "noindex," "noi

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.

{{SKILL_ENTRY:refactor}}

{{SKILL_ENTRY:release}}

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or {{CMD:feature}}.

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

{{SKILL_ENTRY:security-architecture}}

{{SKILL_ENTRY:tribunal}}

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

Copy a file OUT of a running sandbox box to the host — host-initiated egress only (docker cp). The reverse, a host→container bind, is impossible by construction.

Tear down a sandbox box — remove its container and named volume. --keep-volume leaves the volume; with no id, prune reclaims any leaked ca.sandbox=1-labeled object. Cached images are retained.

Run a single command inside a running sandbox box and capture a JSON result — exitCode, separate stdout/stderr, and a truncated flag past the byte cap. The scriptable exec seam.

Open an interactive shell inside a running sandbox box at /work/repo. Read-only root, non-root user, no host-FS access — explore the untrusted code interactively, then exit.

Pull an untrusted repo into an ephemeral, host-FS-isolated Docker container — clone into a named volume, build a dep-cached image, run under structural isolation. Network defaults to offline. Requires Docker and nixpacks.

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Inspect ADR health read-only; optionally select one ADR with --adr N.

Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.

Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.

An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

A governance harness for AI coding.

DeepSeek Harness 手机版：可直接安装的 Android APK，AI 免 Root 操作手机（Shizuku/root 可选），文件编辑只需所有文件访问权限，前台保活 + AI 通知

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

Orbi — the factory that builds and operates AI software factories. GitHub Issues in, releases and runnable system out

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

The SDK for browser agents. Interact, search, extract, and fetch any site reliably across the web

Agent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.

The extensible power-user platform for Google Antigravity. Adds a native In-App Browser, animated Desktop Pets, revamped Gemini UI, and custom BYOK Gemini Pro k…

Open-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a personal assistant li…

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Code…

Bridge between QQ (SnowLuma OneBot v11) and DeepSeek Harness agents: social simulation, safe MCP tools, slang learning and more.

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider,…

针对 AI 自动化渗透 Agent 的新一代反制蜜罐，通过反向代理将API密饵载入真实业务、反向提示词注入等方式反制自动化渗透 Agent，实现多款主流通用Agent的反制上线控制。

Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.

A free AI-agent toolbox for Android, 一站式安卓AI Agent工具箱

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. I…

Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, rea…