LLM Mart Basic

Wire SwiftUI navigation as data on the iOS 26 / macOS 26, Swift 6 baseline: one `@Observable @MainActor` Router in `.environment`, `NavigationStack(path:)` over a typed `Route` enum, `navigationDestination(for:)` at the stack root, `item:`-driven sheets and covers, `.onOpenURL` d

Design the app-side event pipeline that fans one `telemetry.observe(event)` call out to logging, tracking, MetricKit and Game Center sinks. Use when deciding whether Logger and analytics tracking share one interface; when adding a `TelemetrySink` / `MetricKitSink` / `GameCenterSi

Use when setting up or changing CI for an Apple-platform project on Xcode Cloud — choosing Xcode Cloud vs GitHub Actions, splitting PR / Main / Release / scheduled workflows, writing `ci_scripts/ci_post_clone.sh` / `ci_pre_xcodebuild.sh` / `ci_post_xcodebuild.sh`, or wiring `CI_B

Keep a running impl-notes file next to the phase meeting log while a subagent executes a task, recording design decisions, intentional deviations from spec, tradeoffs, and open questions as they happen rather than after the fact. Use at the start of any non-trivial subagent dispa

Route a stray idea that surfaces mid-task to the §Backlog of the right living doc in a spec-phase-orchestration repo (design.md, foundations.md, plan.md, methodology.md, or today's meeting log) as a single line, without derailing the current work. Use when a not-now-but-don't-for

Package Claude Code skills as a plugin plus marketplace and install them into other repos — globally, pinned per project via committed settings, or as a skills-dir plugin. Use when sharing skills across repos, wiring an existing skill plugin into a project, choosing flat project

Drive GitHub contributions through the gh CLI — pull requests, issues, GitHub-side file edits, repo secrets, contribution-flow repo settings, submodule pin bumps. Use when about to run `gh pr create` / `gh pr merge` / `gh pr checks` / `gh issue create` / `gh secret set` / `gh api

Shape the prompt a Leader sends when dispatching a sub-agent (Developer, Designer, Code Reviewer, drafting agent) so the result comes back verifiable and integrable. Use when about to call the Agent tool, writing or reviewing a dispatch prompt, deciding what a sub-agent must read

Extract recurring collaboration patterns from accumulated meeting logs (optionally session JSONL) and record them in docs/methodology.md with evidence of where each was sighted. Use when the user asks to update methodology, extract recurring patterns across the meeting logs, or c

Check that a branch's actual diff matches what its commit messages and any subagent report claim, before the commits leave the machine. Use before `git push` of a feature branch, before `gh pr create` or `gh pr merge`, after a subagent reports "committed N files", after an amend

Consolidate a Claude Code session JSONL log into a summary-only meeting record under meetings/ (decisions, rejected alternatives, hand-offs, open questions). Use when the user asks to turn a session into a meeting log, archive today's discussion, or extract a record from a .jsonl

The Apple/Swift-and-this-catalog layer for authoring or reviewing a SKILL.md, on top of superpowers:writing-skills. Use when writing or CR-ing a skill for this repo, wording a description so it routes precisely, splitting a skill into references/, or choosing granularity and nami

Run the spec-first document phase of a project and gate implementation on it. Use when starting a project that needs a spec before code, deciding which documents the spec phase produces and in what order, choosing whether a section may advance while a prerequisite is unconfirmed,

Use before dispatching a subagent with `isolation:"worktree"`, or while another subagent is in flight, to avoid three dispatch hazards — file-scope overlap with an in-flight subagent, a stale dispatch base, and collisions with another live agent/session editing the same checkout

Structure a multi-round Leader / Developer / Code-Reviewer review of a document or code change. Use when planning how many review rounds to run, dispatching a Code Reviewer subagent and deciding which tools and review criteria it carries, adjudicating a reviewer's BLOCKER / MAJOR

OKF (Open Knowledge Format) — curated catalog of tools, plugins, skills, proposals, and docs for agent-friendly knowledge. YAML-driven, agent-searchable, MCP-re…

Navigate a camp with `cgo` and `camp go`. Use when you need to move between projects/festivals/workflow directories, switch context quickly, or resolve script-safe paths with `camp go --print`.

Manage a camp's projects. Use when committing inside `projects/*`, deciding status/pull/push scope (root vs submodule vs all), or creating/removing project worktrees.

Find, filter, choose, create, or adopt camp work items with `camp workitem`, `camp wi`, or `camp workitems`. Use when a user wants current active work across intents, designs, explore notes, festivals, or tracked workflow directories; when agents need safe `camp workitem --json`

Choose the correct commit command in a camp, also called a campaign. Use when you are about to commit and need to select `camp commit`, `camp p commit`, `fest commit`, or intentional root pointer sync via `camp refs-sync`.

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.

Portfolio-wide Inforcer baseline drift report — every managed tenant's alignment vs its assigned baseline, classified aligned / semi-aligned / drifted and sorted drifted-first, with secure score

Single-tenant Microsoft 365 posture snapshot from Inforcer — secure score plus alignment score, band, and the per-policy drift detail against the tenant's assigned baseline

Get an Ironscales AI verdict on a raw email, then act on it with a remediation action

Triage open Ironscales phishing incidents — list by status and severity, investigate, and remediate

Get a Kaseya Quote Manager quote with its sections and line items

Get a Kaseya Quote Manager sales order with its lines and payments

List Kaseya Quote Manager quotes, optionally scoped to a recent window

Add a note or comment to an existing Autotask ticket

View contract status, entitlements, and remaining hours for a company or specific contract

Check pricing details for an Autotask product or service from price lists

Create a new Autotask quote with line items for products, services, and service bundles

Create a new service ticket in Autotask PSA

Use this skill when working with Autotask expense reports - creating reports, adding expense items, searching by status or submitter, and tracking reimbursable and billable expenses

Search for Autotask configuration items/assets by name, serial number, or company

Search for Autotask companies by name, ID, or other attributes

Search for Autotask contacts by name, email, phone, or company

List tickets currently assigned to you with optional filtering

Reassign a ticket to a different resource or queue

Search the Autotask product catalog for products, services, or inventory items

Search for tickets in Autotask PSA by various criteria

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