Graph memory for AI agents — decisions, context, and session history that survive across every conversation. Works with any LLM.

Delimit

One workspace for every AI coding assistant. Shared tasks, memory, and governance.

Invest IBKR Skill (BETA)

> ⚠️ **BETA — do not use.** This drives **real money in a real brokerage account** with no per-trade human > confirmation. It exists for one operator's own experiment. There is no support and no guarantee, it can lose > money, and every switch defaults to off. If you are not that operator, sto

resolve-agent-reviews

Resolve PR review bot findings on current PR. Fetches unanswered bot comments, evaluates each finding, fixes real bugs, dismisses false positives, replies to every comment, and watches for new findings until bots go quiet.

Animated Sticker Studio · 动态表情包工坊

Pipeline: **plan → reference → atlases → cut → build → look → fix → deliver**. Scripts live in `scripts/` (Python 3 + Pillow; ffmpeg for Telegram/MP4). Run every script with `--help` before first use.

Playwright CI/CD

> Ship reliable tests in every pipeline — CI-specific patterns for speed, stability, and actionable reports.

Orca Account Health Skill

Answers the question: **"Is every account connected, recently synced, and fully scanned — so we can trust the data we're about to act on?"**

audit-licenses

Use to list the open-source licenses of every dependency in this project, grouped by license family. Flags GPL or AGPL dependencies that may force the project itself to be open-source. Triggers on /audit-licenses.

Debugging

Read [[principles/fix-root-causes]] before starting. Every debugging session follows that principle: trace to root cause, never paper over symptoms.

Epitome

Personal AI memory — gives every AI agent shared, persistent memory of you

transform

Use this to author and change a dbt project: bootstrap a new dbt project in a repo that has none (`transform init`), write or refactor dbt model SQL from staging to marts, add tests and docs in schema.yml, manage dependencies, and define or update the semantic layer (dbt semantic models / MetricFlow: entities, dimensions, measures, metrics). Trigger it for requests like "set up a dbt project in this repo", "build a staging model for this table", "refactor this model", "add tests to this model", "create a mart for X", "define a revenue metric", or "add a dimension to this entity". Every change is a reviewable diff to the dbt project; any warehouse build is dev-target only, gated, and cost-surfaced first. Do not use it to explore or profile a warehouse (use explore) or to detect drift and reconcile a project that has fallen out of sync (use maintain).

/ai-llm-safety — AI/LLM Safety Design Enforcement

Every system that involves LLM agents, tool use, or prompt construction MUST treat AI safety as a first-class constraint. Prompt injection is the SQL injection of the AI era — and it's harder to fix after deployment.

Obris

Stop re-explaining yourself to AI. Save knowledge once, use it in every conversation.

Audience-First Checklist

Complete every question below before finalizing any public-facing work. Do not skip items because they seem obvious — the obvious answers are usually wrong.

schedx — Scheduler CLI

schedx is a local-first scheduler that runs shell commands, AI agent prompts, and HTTP webhooks on a schedule. All state lives as plain files under `~/.schedx/`. Every command supports `--json` for structured output.

Io.Github.Iris Eval/Mcp Server

The agent eval standard for MCP. Score every agent output for quality, safety, and cost.

CLEO Skill Validator

Full 3-phase validation loop for CLEO skills. Every phase must reach PASS before the skill is considered ecosystem-ready. Run the phases in order and iterate on failures.

clawhub-skill-lint

Use this skill before publishing any ClawHub skill from this repo, or after editing a SKILL.md, to verify the skill won't be flagged or rejected by ClawHub's server-side moderation pipeline. The skill re-implements every static-scanner rule from openclaw/clawhub's `convex/lib/moderationEngine.ts` plus the frontmatter spec from `docs/skill-format.md` and runs them locally. Triggers: "lint the claws skills", "check the claws/openclaw skills", "scan before publish", "is the skill clean", "any scanner findings", /clawhub-skill-lint, before any `clawhub sync` or `clawhub skill publish`.

every-style-editor-2

Reviews and edits text content to conform to Every's editorial style guide. Use when written content needs style compliance checks for headlines, punctuation, voice, and formatting.

drain

Run the on-demand drain pass over every spec bundle's Gate deferral entries: evaluate structured GATE(when:) conditions, surface date and free-text gates, report malformed ones, inventory each live bundle's [manual] test-spec entries, and surface the observations log's unmined state. Read-only; nothing is auto-resolved or auto-dropped.

ironclaw-workflow-orchestrator

Install and operate a full GitHub issue-to-merge workflow in IronClaw using event-driven and cron routines. Use when setting up or tuning autonomous project orchestration: issue intake, planning, maintainer feedback handling, branch/PR execution, CI/comment follow-up, batched staging review every 8 hours, and memory updates from merge outcomes.

Perseus — Live Context Engine for AI Assistants

Perseus pre-resolves your entire workspace state — git, services, memory, team coordination — into a single markdown document every assistant reads at session start. Deterministic. Cacheable. Assistant-agnostic.

Desktop control

`kaizen computer <verb>` reads the accessibility tree of a running app and acts on it. No screenshots, no pixel clicks, no keyboard shortcuts. Linux only (AT-SPI). It refuses every verb until the user turns this skill on.

app-ai-guardrails

Scaffold a greenfield app so the **full guardrail canon** is live in **commit #1** and every one of the 7 **gates** is **verified green** before that commit exists. The canon is stack-agnostic; each stack's mechanics live in one adapter file. The differentiator is **teeth**: gates that *fail* on vio

Automated TikTok-style video review of every PR.

Scaffold a tiktest.md config file in the current project by inferring dev-server URL, start command, and auth flow from README, package.json, and framework configs. Use when the user wants to set up tik-test for a new project, or when /tiktest:run / /tiktest:quick says "no tiktest.md found".

gh-batch-runner

Run several planned GitHub Issues as one unit: collect them under an Epic Issue with sub-issues, implement each on a shared epic/ branch in dependency order, verify the branch as a whole, and open a single Pull Request into the integration branch. Use when the user wants several Issues fixed, verified and released together. Triggers include requests such as Issue1,2,3をまとめて対応して / まとめて修正してリリースしたい / この3件を一緒に出して, 'batch these issues', 'do issues 1 2 3 together', 'ship these issues as one release'. Prerequisite: every member Issue needs an agreed plan comment from gh-issue-planner. For a single Issue, or for Issues that ship separately, use gh-issue-resolver instead.

Advance a card

Every status transition is a documented agreement, not a silent flag flip — the reason lives on disk: in the body for terminal transitions, in the commit message for mid-flight ones. Mutate a card's status — everything except `done`, which is `Skill(finish-card)`'s DoD-gated contract. Read the c

Obsidian Second Brain

> Claude operates your Obsidian vault as a living OS — not a note-taking app. > Everything worth remembering gets saved. Every update propagates everywhere it belongs.

Commit with auto version bump

This project follows semver. **Every commit must include a version bump** in: - `plugins/corezoid/.claude-plugin/plugin.json` - `.claude-plugin/marketplace.json`

Canonical NotFair workflow

Read [`../../seo/geo-optimizer/WORKFLOW.md`](../../seo/geo-optimizer/WORKFLOW.md) completely, then follow it as the active workflow. Resolve every relative reference from that file against `../../seo/geo-optimizer/`.

api-fetch-wrapper

The case that breaks first in production — a skill that hits an external service. This example covers the four things every such skill needs: secret handling, retry policy, error normalisation, and no-leak-on-failure logging.

Io.Github.MagneticDogSon/Fixflow

Collective memory for AI agents. One agent solves a bug — every agent gets the fix instantly.

CodeScope Q&A

CodeScope indexes source code into a two-layer knowledge graph — **structure** (functions, calls, imports, classes, modules) and **evolution** (commits, file changes, function modifications) — plus **semantic embeddings** for every function. Supports **Python, JavaScript/TypeScript, C, and Java*

analyze-session

Query a Claude Code transcript without reading it into context, then write the retrospective to disk so it remains available after the session ends. The tool reads the file line by line and reports every failure and repeated tool call by line number. Use this skill when the user asks for a retrospective on a past session, or hands over a transcript path with a question about it.

opc

OPC — One Person Company. Digraph-based task pipeline with independent multi-role evaluation. Builds, reviews, analyzes, and brainstorms with specialist agents. Every path ends with evaluation. /opc <task>, /opc -i <task>, /opc <role> [role...]

ComOS Federation Gateway

Multi-tenant MCP gateway for AI commerce. One connection, every store on the network.

cnpg

Provision and run CloudNativePG (CNPG) Postgres on Kubernetes as GitOps. Every concrete identifier below is a placeholder - substitute your own: `<project>`, `<gcp-sa>`, `<backups-bucket>`, `<cluster>`, `<ns>`, `<svc>`, `<db>`, `<owner>`, `<env>`, `<s3-endpoint>`, `<objstore-secret>`, `<app-ns>`.

Founder-Led Social: Listen, Reply, Then Post

> **Default lens: a SaaS / AI software startup.** Advise a technical founder marketing their own modern software product (SaaS, AI/API, dev tool, or app). Tailor every recommendation to that reader. > > Stage-fit (`social`): Tier 1 Too early · Tier 2 Useful · Tier 3 Useful. If the founder's tier >

task-execute-blueprint

Drive the end-to-end execution of an existing AI Task Manager plan blueprint. The skill is assistant-agnostic and self-contained: every script it invokes lives under this skill's `scripts/` directory and is referenced by relative path.

game-art-direction

Direct game art and creative vision. Turn GAME_DESIGN into a production-level ART_DIRECTION defining a recognizable visual style, camera and composition, world and character grammar, functional colour/light/material, HUD feedback, motion and transition specs, audio direction, and a signature moment for every screen and mode. Use for what should the game look like, set the art direction, define the visual style. 游戏美术与创意方向。把 GAME_DESIGN 转成策划级 ART_DIRECTION，定义可辨识视觉风格、镜头构图、世界与角色语法、功能性色光材质、界面反馈、运动与转场规格、声音方向和每个界面/模式的签名游戏时刻。用于判断游戏应该长什么样、制定游戏美术方向等需求。

Context management plugin for Claude Code. Your AI remembers your projects, people, and decisions across every session. Plain files on your machine.

Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03_Inputs/ for unrouted files and enters inbox scan mode. Stores raw content, routes to capsules, extracts tasks and insights into the stash.

nerv-ui

NERV Operations Console v2 — Evangelion-inspired UI component library. Data-driven Three.js MAGI visualization (yield surface mesh + organic flow curves + bar columns), blockchain event log terminal, dense metrics grid, vault cards, oracle consensus display, CRT effects, emergency mode. Noto Serif Display (weight 900) + Shippori Mincho B1 + JetBrains Mono. NO HELVETICA. Every pixel conveys information.

sdlc-align

The **window** check. Every other alignment gate in LoopSmith looks at one unit of work: `sdlc-plan-review` §4 holds a single plan to the north-star, and `sdlc-retro` asks what a single goal taught. Neither can see the shape of *twenty* goals, and that is where strategy actually drifts — no singl

Odoo agency fleet review

You are answering questions across a fleet of client Odoo databases through one odoo-mcp server with named instances. Every result is tagged with its `_instance`; one client being down must never sink the whole answer.

One hub for every AI coding agent. Unified configuration management for 22+ assistants.

Agent Prompt Audit

An Agent's behavior comes from every piece of text that reaches it over its lifecycle, not just its system prompt. The audit's job is to find which text causes the behavior the user sees, on the backend and model that actually ran it, and to propose the smallest change that fixes it. Judge each inst

team-style-guide

Team coding style baseline shared across every AI agent.

agent-smoke-e2e

End-to-end smoke check of the moraine MCP server. Exercises every MCP tool against a live moraine stack and prints a per-tool PASS/FAIL matrix. Use inside the dev sandbox after a fresh build to confirm the MCP binary actually serves its tools and returns shaped responses.

add-binding-feature

Add or change a public NeMo Relay API surface across the core runtime and every affected binding

LiveComponent

TwigComponents that re-render dynamically via AJAX. Build reactive UIs in PHP + Twig with zero JavaScript. Every user interaction triggers a server round-trip that re-renders the component and morphs the DOM.