Cxc Recall

Community

lidge-jun

cxc-recall

Use for past-session context recovery. Triggers: recall, last time, previous session, chat search, memory search, 그때, 지난번, 저번 세션, 예전에 했던, 기억나?, 리콜, 지난 세션, 이전 작업, 뭐였지, 어떻게 했었지.

Overview

Publisher	lidge-jun
Repository	`codexclaw`
Skill name	`cxc-recall`
Stars	51
Forks	10
Bundled files	6
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
6 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by lidge-jun on GitHub. Read the source before you install it.

Installation

Install the Cxc Recall AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/lidge-jun/codexclaw/tree/main/plugins/codexclaw/skills/recall
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/lidge-jun/codexclaw.git /tmp/codexclaw
mkdir -p .claude/skills
cp -r /tmp/codexclaw/plugins/codexclaw/skills/recall .claude/skills/cxc-recall

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cxc Recall in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cxc Recall on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cxc Recall is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

recall — Past-Session Recall Search

Codex already persists every session (~/.codex/sessions/**/rollout-*.jsonl) and a per-thread memory store (~/.codex/memories/). This skill is the discipline for SEARCHING that history instead of asking the user to repeat themselves.

Injected memory_summary.md and SessionStart snippets are locators, never proof. Search, then open the winning file, before answering a past-work question.

Recall Lookup Scope (read first)

When ANY of these happen, search BEFORE asking the user:

A term, file, decision, or codename from prior work is unfamiliar.
Context seems lost after a compact, restart, or session handoff.
The user references earlier work: "그때 그거", "지난번에 하던 거", "저번 세션에서", "예전에 만든", "last time", "the thing we did earlier", "as discussed previously".
You are about to write "I don't have context about X" — search X first.

Never call memories.add_ad_hoc_note from this skill.

Natural-language → keyword ladder

Do not start with the user's sentence. Rewrite, then search. Each rewrite is its own query (--days 0, chat then memory unless the noun is known to live in notes):

Proper nouns / versions / hostnames / filenames as a single token (BundledPluginsMarketplace, 2.49.0, a thread id).
Korean/English synonym pair of that noun (도그푸딩 and dogfooding, 플러그인 and plugin restart, 배포 and provenance / SLSA).
Short 2–3 word keyword query (로컬 소스 서비스, 2.49.0 배포 npm).
cxc chat search "<keywords>" --days 0 --no-tools — find the conversation. Add --context 2. Add --source all if the work was delegated.
cxc memory search "<keywords>" — durable summary. Omit --no-chat so empty memory can backfill up to 5 raw messages labelled (chat/chat).
Open the winning rollout / memory file (rollout_path is on the hit). Do not answer from the excerpt.
Only if the rewritten queries miss, ask the user and list what you searched.

Result checks (before treating a hit as the answer)

Request vs completion: a user line or "진행할게" is a locator, not proof. Prefer assistant text that names the outcome (healthz, npm latest, recovered).
Correction history: later ad-hoc notes and MEMORY.md entries override older summaries. If two hits disagree, read the newer file, then the rollout.
--any hits are not evidence by mere existence.

Conditional References

Condition	Reference
Selecting a version match	Result checks
Running chat/memory commands, selecting flags, scoring results, diagnosing or requeuing extraction	Commands and engines
Delegated work, managed worktree, project/home scope, native memory tools, empty results or JSON output	Scope and results
Aside or kim_wiki is installed and extra memory evidence is needed	Optional memory lanes
Index maintenance or understanding SessionStart/compaction injection	Index and injection

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cxc Recall AI skill do?

Why use Cxc Recall on TypingMind?

Because you install it once and use it with any model. Cxc Recall is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cxc Recall in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lidge-jun/codexclaw/tree/main/plugins/codexclaw/skills/recall. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cxc Recall?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cxc Recall?

As many as you like. As long as a model supports skills, you can use Cxc Recall with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cxc Recall AI skill free?

Yes. It is published on GitHub by lidge-jun under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Issue Reporter

CherryHQ

OrganizationPopular

只在用户明确要求提交 GitHub Issue、GitHub Bug Report 或 GitHub Feature Request 时使用。用户只说“提交问题”“提交反馈”“上报 bug”“这是个 bug”或描述功能建议但未点名 GitHub 时不得触发，必须改用 cherry-studio-feedback 并默认提交飞书。

Skills Manager

搜索、安装和协调创建 Claude Code Agent Skills。当用户想要搜索技能、安装工具、创建自定义 Skill，或者说"find a skill"、"搜索技能"、"帮我做个 skill"、"create a skill"时触发。也适用于用户说"有没有做 X 的工具"、"我想扩展 Agent 能力"，或当前能力不足需要先查找可复用方案的场景。

Cli Anything 3mf

3MF mesh geometry editor — detect and resize cylindrical holes, repair meshes, compare 3D printing files. Works with BambuStudio and PrusaSlicer 3MF files.

Cli Anything Godot

Agent-native CLI for Godot project management, scenes, exports, and script execution.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

recall — Past-Session Recall Search

Recall Lookup Scope (read first)

Natural-language → keyword ladder

Result checks (before treating a hit as the answer)

Conditional References

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now