LLM Mart Basic

Triage a fetched PR review with the user, comment by comment, drafting each reply and producing a REQUIREMENTS file for the accepted code changes. Takes the PR-REVIEW file produced by fetch-pr-review. Invoke manually only.

Refine a development ticket — or brainstorm a raw idea — into a validated, self-contained REQUIREMENTS document — the "what", verified against the codebase. Invoke manually only.

Assist a human reviewing a pull request or branch locally — diff a source branch against its target (auto-detected or from a PR link) and return concise, human-voice review comments with file and line locations. Read-only, never posts.

Triage a ticket or ticket set before work starts — compare it against the codebase and save a review covering verdict, feature walkthrough, and only the high-cost questions worth raising.

Run nx format, lint, test, and build on affected or specified projects, then fix unambiguous failures

Capture durable user feedback into the governing skill/doc, or propose creating a new skill when no suitable one exists, so future sessions don't repeat the mistake. Use when the user rejects, reverts, or overrides the agent's output or approach on something a skill/doc covers or

Self-review a changeset until merge-ready — a fresh-context reviewer checks it as a maintainer would, the author answers every finding, and a compact report for the PR proves the review happened.

Split a plan into small, individually reviewable tasks grouped into PR-sized batches, appended as a task section at the end of the plan file.

Voice rules for text published under a person's name and read as if a person typed it, such as chat replies, PR comments and descriptions, commit messages, review replies, and code comments. Defines the wording only, never the content.

Verify the engineer is ready to implement a feature — a teach-back conversation over a .TICKET-REVIEW.md where they explain the feature in their own words and the agent probes and corrects.

1:1 rebuild of award-winning creative websites (WebGL / scroll-animation / portfolio sites). Evidence-driven pipeline - mirror-first forensics, line-number-traceable reverse engineering of minified bundles, verbatim porting, quantitative verification gates. Use when user asks to

Use when auditing a specific page's SEO performance, content quality, and competitive position. The agent fetches the URL, Googles the primary keyword, reads the top 3 competitors, and produces a full 7-dimension audit — no exports, no analytics access required.

Use when planning a new article. The agent Googles the keyword, reads the top 10 results, classifies intent, maps the content gap, and produces a writer-ready brief with structure, outline, and on-page artifacts. No keyword tool required.

Use when writing a complete SEO article. Includes the full anti-AI-slop ruleset (banned vocabulary, banned phrases, banned structural patterns) and voice rules. The agent researches the SERP itself if needed — no keyword data exports required.

Use when rewriting or refreshing an existing page that's underperforming. The agent fetches the URL, analyzes the current content, researches the SERP, and rewrites using the full anti-AI-slop ruleset — no data exports needed.

Use when planning to rank for a specific keyword. The agent Googles it, reads the top 10, classifies intent, reads the top 3 competitor pages, and produces a 90-day ranking plan with intent, SERP analysis, and content recommendations.

Use when a page ranks for a keyword but isn't in the top 3 and you want to know exactly what's missing. The agent compares the page to the top-ranking competitors and produces a specific list of entities, subtopics, and relationships to add.

Use when auditing a page for E-E-A-T signals. The agent reads the page and scores Experience, Expertise, Authoritativeness, and Trustworthiness — then tells you exactly what to add to each dimension.

Use when planning a topic cluster (hub + spokes) for a new content area. The agent researches the space, identifies the hub topic, maps the spokes, and produces a specific content plan with internal linking strategy.

Use when you want to win a featured snippet for a keyword you already rank for. The agent checks the current snippet format, analyzes your content, and rewrites the relevant section to match what Google wants.

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.

hydra - Show detailed status of one or all worktrees

hydra - Live monitoring of background agents with status table

import - List all cached documentation

import - Search within cached documentation

import - Update cached documentation

import - Fetch URL (via Playwright if blocked) or copy local path to docs/

limit - Display all highscores for all plans

marketplace - Restore original plugin version from backup

marketplace - Install local plugin version for testing (backup original)

<claude-mem-context>

Aggregate SKMTC friction log entries into a review — cluster patterns, classify interventions, calculate convergence metrics, produce an action plan

<claude-mem-context>

Run a SKMTC retrospective on the current session — capture friction and wins to the friction log

CoalMine measurement dashboard — canary activity this session + rule-freshness status across the project's rules home

CoalMine self-update — check for a newer CoalMine version and offer to apply it, or set how updates are handled

CoalMine measurement dashboard — canary activity this session + rule-freshness status across the project's rules home

CoalMine self-update — check for a newer CoalMine version and offer to apply it, or set how updates are handled

CoalWash stats — current band, certain-fat reading, both break-evens, Memory-BMI (informational), pending-ask state, and the last run's trace for this project

CoalWash self-update — check for a newer version and offer to apply it, or set how updates are handled.

CoalWash stats — current band, certain-fat reading, both break-evens, Memory-BMI (informational), pending-ask state, and the last run's trace for this project

AI coding platform for teams

AI Multi-Agent Framework in .NET

Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs

UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight & extensible, works with any harnesses, any models,…

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support. Built with Tauri + React.

OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs locally on your machine. Scheduled tasks support.

Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

Exposes internet search tools for use by LLM-backed Assist in Home Assistant

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

Versus Incident is the self-hosted AI SRE agent. It learns what your system normally look like and escalates only what is new or unexpected issues — routing to…

Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.

Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary CLIs with catalogs and generated Skills.

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

An agent small enough to run anywhere. A minimal agentic runtime in C — ~380 lines, 54KB binary, ~2MB RAM. A skill file + an LLM + a shell loop, no framework.

AgentiLoop Agent! An Autonomous Agentic Agent for Mac, and exclusive Apple only harnesss. Suppprtd automation, scripting, coding, build anything and more. Power…

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex