An intelligent graduate entrance exam study system built with Claude Code, integrating the MemOS memory system and supporting cross-device synchronization and cross-disciplinary knowledge connections.
This repository also configures its own agents. See what kaoyan tells them →
Skill Claude CodeCodex
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
Skill Codex
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
Skill Claude CodeCodex
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Skill Claude CodeCodex
An automated tool for restructuring agent skill files. It can extract code into code.md, split overly long files, and improve their organization.
Skill Claude CodeCodex
A search router that chooses an opencli command for different kinds of information searches. It covers websites, social media, technical material, news, shopping, travel, jobs, finance, and Chinese-language content.
Skill Claude CodeCodex
A generator for sortspec.md files, which tell Obsidian how to order files in a folder. Obsidian is a note-taking app that stores notes as files.
Skill Claude CodeCodex
A registry synchronization tool for agent skills. It scans SKILL.md files and updates the skill list in skill-invocation.md.
Skill Claude CodeCodex
A synchronization tool for study progress stored in MemOS. It can pull the latest learning context across devices or save the day’s learning state from local notes.
Skill Codex
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Skill Claude CodeCodex
Teach the user a new skill or concept, within this workspace.
Skill Claude CodeCodex
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
Skill Claude CodeCodex
Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
Skill Claude CodeCodex
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.
Skill Claude CodeCodex
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
Skill Claude CodeCodex
This skill should be used when the user wants to verify whether their understanding of a concept, derivation, note, screenshot, or worked problem is correct, and expects a structured [!personal] understanding record with logic-chain checking.
Skill Claude CodeCodex
Stop. That last message did not land — re-pitch it.
Skill Claude CodeCodex
Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
Skill Codex
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
Skill Claude CodeCodex
This skill should be used when the user wants to process Word document templates, extract placeholders, or generate Word documents based on templates.
Skill Claude CodeCodex
Writing, exploit — assemble raw material into a journey of beats, grounding each term before a beat leans on it.
Skill Codex
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
Skill Claude CodeCodex
Writing, explore — mine raw fragments, no structure yet.
Skill Claude CodeCodex
Writing, exploit — shape raw material into an article, paragraph by paragraph.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: