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.

{{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.

VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。

The open source Unity Dev Agent

Context is yours. Agents are replaceable. Orbital — a project agent that turns your context into assets.

Self-hosted search API + MCP server for AI agents. Bundles SearXNG. Zero API keys, one-command deploy. Open-source alternative to Tavily, Exa, and Serper.

🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomous AI agents (DeepS…

Watch, approve and steer your coding agents from your phone.

MARVIS-Agent: all-purpose credit risk agent for model development, validation, data processing, feature engineering, and strategy workflows.

TikTok e-commerce video generation, replication, and analysis SKILL

小红书/抖音/快手/视频号/B站 自媒体账号体检+爆款拆解工具。扫同赛道找对标、拆爆款为什么爆、诊断为什么没人看，顺手出可粘贴仿写初稿。支持带货电商模式。支持codex, claude code, workbuddy

Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.

A power user focused interface for LLM base models.

Outsource your understanding. Capture every human-AI decision as a step in a trajectory; grade trajectories retroactively when outcomes land (deal closed, sprin…

The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and…

🤖 Taskade MCP · Official MCP server and OpenAPI to MCP codegen. Build AI agent tools from any OpenAPI API and connect to Claude, Cursor, and more.

A block-based content engine and bilingual blog backend for Laravel Gutenberg-style editor, media library, post templates, roles, and an AI writing assistant,…

ACRYL - Agent Context Relay Yielding Lifecycles. One persistent workspace, one canonical context, any coding agent.

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

Open-source agent-native visual production workspace where humans and coding agents edit the same live canvas — local-first, BYOK image/video models.

Persistent memory extension for pi with daily logs, scratchpad, and optional qmd‑powered semantic search.

Hermes Agent CN desktop app, Windows-First, built with Tauri, Typescript and Rust. Isolated Hermes Agent core insides.