LLM Mart Basic

Cowork-style sweep of a folder of receipts, statements, and expense exports -- categorizes every transaction, matches receipts to statement lines, flags policy violations and anomalies, and outputs a clean expense report plus a findings memo.

Cowork-style cleanup of a messy folder or shared drive -- classifies every file, proposes a target structure, renames to a consistent convention, deduplicates, and writes an index. Use on Downloads, Desktop, client folders, or team shared drives.

Point Cowork at a folder of resumes plus a job description -- screens every candidate against the actual requirements, produces a ranked shortlist with evidence, drafts advance/decline emails, and builds interview kits for the top picks. Pairs with hiring-scorecard for the interv

Build an insurance-grade home inventory from a folder of photos and receipts -- identifies items, pulls values from receipts, estimates replacement costs, organizes by room, and outputs the documentation an insurance claim actually requires. Update mode keeps it current after new

Daily inbox triage using Cowork's email write tools (Microsoft 365 or Gmail) -- classifies unread mail, drafts replies in your voice, flags what needs a decision, and schedules follow-ups. Built to run as a recurring Cowork scheduled task.

Point Cowork at your invoices and payments records -- builds an AR aging report, drafts escalating follow-up emails matched to each invoice's age and the client relationship, and runs as a weekly scheduled task so nothing slips past 30 days unnoticed.

Point Cowork at a folder of medical bills and insurance EOBs -- matches every bill to its explanation of benefits, catches duplicate charges, balance-billing, and bills that ignore your insurance, then drafts the dispute letters and phone scripts. Most medical bills contain error

Build a quarterly business review from a client folder -- reports, usage exports, support tickets, meeting notes, emails. Extracts delivered value with receipts, surfaces risks before the client does, and drafts the QBR narrative plus expansion asks. For agencies, consultancies,

Turn an RFP and a folder of your past proposals, case studies, and capability docs into a requirement-by-requirement compliance matrix and a drafted response. Flags disqualifiers and unanswerable requirements before you burn a week writing.

Turn a process walkthrough -- meeting transcript, screen-recording transcript, rough notes, or a folder of scattered how-to docs -- into a clean standard operating procedure: numbered steps, roles, decision points, exceptions, and a consistent template across your whole SOP libra

Sweep your folders and downloads for tax documents and build a CPA-ready package -- checklist by form type, everything renamed and organized, a missing-document chase list, and flagged items worth asking your accountant about. Organization, not tax advice.

Drop a folder of vendor quotes, proposals, and SOWs on Cowork -- normalizes them into one comparison matrix, computes true total cost of ownership, surfaces the terms each vendor buried, and arms you with negotiation leverage points and reference-check questions.

Create professional CSS animations, transitions, micro-interactions, and complex motion design. Use when adding animations, hover effects, loading states, page transitions, scroll animations, or any motion design work.

Merge multiple CSV/Excel files with intelligent column matching, data deduplication, and conflict resolution. Handles different schemas, formats, and combines data sources. Use when users need to merge spreadsheets, combine data exports, or consolidate multiple files into one.

Maps the full customer journey from first touch to advocacy. Generates a comprehensive customer-journey.md with all stages, touchpoints, emotions, pain points, opportunities, Mermaid diagrams, and metrics. Use when mapping customer experience, designing onboarding flows, identify

Build a panel of your real buyer personas (from a deep scan of any tools you allow it to connect to) and have them debate any decision you bring — a marketing launch, a price increase, a new product, a positioning change, a feature cut. Returns a structured debate, the strongest

Aggregate and analyze customer reviews from G2, Capterra, Trustpilot, App Store, and other platforms. Performs sentiment analysis, identifies pain points, extracts feature feedback, generates marketing claims, and compares competitor reviews. Use when users need review analysis,

Convert a light-only site or app to a real dark mode -- semantic token mapping, elevation-based surfaces, recalibrated shadows and imagery -- not a naive inversion. Handles Tailwind, CSS variables, and styled-components, plus the toggle, persistence, and no-flash boot.

Designs and builds ETL/ELT data pipelines. Takes data sources, destination, transformation requirements. Generates pipeline code (Python/SQL), scheduling config, error handling, monitoring setup, and data quality checks. Outputs data-pipeline-spec.md + implementation files.

Migrates databases between providers (Postgres, MySQL, Supabase, PlanetScale, MongoDB). Reads source schema, generates migration scripts, handles data type mapping, foreign keys, indexes, triggers, stored procedures. Validates migration with row counts and checksums. Generates mi

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.

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with NVIDIA Nemotron, pays…

DSH 插件 · 注入式优化器 0.8（主线）：你照常说话，它在你发送后,AI接收前把"这一轮到底要什么"理清楚，再把这份理解交给工作 AI(上下文注入) —— 原话不改写，条条带逐字依据。含控制界面（档位/权限/模型/上下文/只读工具）、拦截浮层（思维层+产出层）与真实 token 用量。可明显提升大多数模型的发挥稳…

Reliable AI Skill + MCP toolkit for agent-driven desktop CAD automation.

Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

从 0 复刻 WorkBuddy-style 桌面 AI 助手 Harness：24 章 Python 教程，覆盖 Agent Loop、工具调用、记忆系统、Sidecar、沙盒审计、DeepSeek/OpenAI 评测轨迹

MCP server and CLI tools for web search and crawling, built on SearXNG and Crawl4AI

Delta MCP is a free app that sits between your AI apps and their MCP servers: one program per task instead of one tool call per step, up to 24.1× fewer tokens i…

Ava turns any Android 5+ device into a voice-first Home Assistant kiosk. Native C++ under the hood, so a 10-year-old tablet still listens, talks, and runs the h…

Roblox Studio macOS Window Capture Fix 2026: Real Screenshot Tool Instead of Magenta Playtest Glitch

LabTether