New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Memory Recall

by zilliztech in zilliztech/memsearch

Search and recall relevant memories from past sessions via memsearch.

MITAuto-check passedAI & LLM Engineering

Install Memory Recall

skills CLI
$ npx skills add zilliztech/memsearch --skill memory-recall -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zilliztech/memsearch memory-recall --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zilliztech/memsearch.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/codex/skills/memory-recall .claude/skills/memory-recall && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
memory-recall
GitHub stars
2.7k
Token cost
~1k tokens
SKILL.md length
402 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Search and recall relevant memories from past sessions via memsearch.

  • Works in 5 steps: Search: Run memsearch search "" --top-k… → Evaluate: Look at the search results.… → Expand: For each relevant result, get… → …
  • The users question could benefit from historical context
  • SKILL.md covers Project Collection, Steps, When unsure what to search and Output Format
  • Calls git, uvx and bash

What it does

Memory Recall is an agent skill from zilliztech/memsearch. Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this before'. Also use when you see [memsearch] Recall available if needed capability hints injected via SessionStart or UserPromptSubmit. Typical flow: search for 3-5 chunks, expand the most relevant…

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering. It works with Milvus and DeepSeek. The repository describes itself as: A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus. The licence is MIT.

When your agent uses it

  • The users question could benefit from historical context
  • Debugging notes
  • Previous conversations
  • Project knowledge -- especially questions like what did I decide about X

Example prompts

  • “what did I decide about X”
  • “why did we do Y”
  • “have I seen this before”
  • “/memory-recall”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Search: Run memsearch search "" --top-k 5 --json-output --default-collection to find relevant chunks.
  2. Evaluate: Look at the search results. Skip chunks that are clearly irrelevant or too generic.
  3. Expand: For each relevant result, get the full context using one of these methods
  4. Deep drill (optional): If an expanded chunk contains transcript anchors (HTML comments with session/rollout info), and the original…
  5. Return results: Output a curated summary of the most relevant memories. Be concise — only include information that is genuinely useful for…

What it can do on your machine

Read from SKILL.md and the folder at commit 2a4652f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • uvx
    • bash

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git and uvx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Memory Recall loads about 1k tokens when it runs. Until then it costs about 189 tokens; SKILL.md has 402 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~189
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zilliztech/memsearch at commit 2a4652f, republished under its MIT licence (© zilliztech). 402 words, ~1,033 tokens.

Download SKILL.mdSave it as .claude/skills/memory-recall/SKILL.md (or your agent's skills folder).
name
memory-recall
description
Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this before'. Also use when you see `[memsearch] Recall available if needed` capability hints injected via SessionStart or UserPromptSubmit. Typical flow: search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format. Skip when the question is purely about current code state (use Read/Grep), ephemeral (today's task only), or the user has explicitly asked to ignore memory.

You are performing memory retrieval for memsearch. Search past memories and return the most relevant context to the current conversation.

Project Collection

Determine the collection name by running:

bash -c 'if [ -n "${MEMSEARCH_DIR:-}" ]; then bash __INSTALL_DIR__/scripts/derive-collection.sh "$MEMSEARCH_DIR"; else root=$(git rev-parse --show-toplevel 2>/dev/null || true); if [ -n "$root" ]; then bash __INSTALL_DIR__/scripts/derive-collection.sh "$root"; else bash __INSTALL_DIR__/scripts/derive-collection.sh; fi; fi'

Steps

  1. Search: Run memsearch search "<query>" --top-k 5 --json-output --default-collection <collection name from above> to find relevant chunks.

    • If memsearch is not found, try uvx memsearch instead.
    • Choose a search query that captures the core intent of the user's question.

  2. Evaluate: Look at the search results. Skip chunks that are clearly irrelevant or too generic.

  3. Expand: For each relevant result, get the full context using one of these methods:

    • Primary: Run memsearch expand <chunk_hash> --default-collection <collection name from above> to get the full markdown section.
    • Fallback (if expand fails with a lock/permission error due to sandbox): Read the source file directly. The search results include source (file path) and start_line/end_line — use cat <source_file> or read the relevant line range to get the full context. This avoids the Milvus lock file issue.

  4. Deep drill (optional): If an expanded chunk contains transcript anchors (HTML comments with session/rollout info), and the original conversation seems critical:

    • Run memsearch transcript <rollout_path> to retrieve the original conversation turns (auto-detects the format and includes tool calls). If memsearch is not found, use uvx memsearch instead.
    • If memsearch transcript reports an unrecognized transcript format, or the anchor format is unfamiliar (e.g. transcript: + turn:, db: instead of rollout:), read the referenced file directly to explore its structure and locate the relevant conversation by the session or turn identifiers in the anchor.

  5. Return results: Output a curated summary of the most relevant memories. Be concise — only include information that is genuinely useful for the user's current question.

Show full SKILL.md (122 more words)Show less

If the user's question is vague or you can't form a concrete search query, explore the raw markdown first — it is the source of truth for memory:

  • MDIR="${MEMSEARCH_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.memsearch}"; ls -t "$MDIR/memory/" | head -10 — recent daily logs
  • MDIR="${MEMSEARCH_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.memsearch}"; grep -h "^## " "$MDIR/memory/"*.md | sort -u | tail -40 — session headings across all days
  • MDIR="${MEMSEARCH_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.memsearch}"; cat "$MDIR/memory/<YYYY-MM-DD>.md" — read a specific day

Once a concrete topic jumps out, go back to memsearch search with a specific query.

Output Format

Organize by relevance. For each memory include:

  • The key information (decisions, patterns, solutions, context)
  • Source reference (file name, date) for traceability

If nothing relevant is found, simply say "No relevant memories found."

© zilliztech, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/codex/skills/memory-recall of zilliztech/memsearch.

Open the folder on GitHubat commit 2a4652f

Compare with similar skills

Memory Recall next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Memory Recall compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Memory Recall this skillzilliztech/memsearch2.7k—~1kAutomated safety check: PassMIT
Phx Investigateoliver-kriska/claude-elixir-phoenix565—~1kAutomated safety check: PassMIT
Evals Contextzgsm-ai/costrict4.4k1 repos~1.9kAutomated safety check: PassApache-2.0
Visionxiincs/claude-code-vision-skill170—~1.2kAutomated safety check: PassMIT
Oracle Agent Team OrchestratorBald0Wang/DeepSeek-Oracle187—~551Automated safety check: PassNone
Dsh PlaybookZSeven-W/dsh-crew156—~1.1kAutomated safety check: PassMIT

Similar skills

  • Phx Investigate

    oliver-kriska/claude-elixir-phoenix

    Investigate Elixir/Phoenix bugs root-cause first. An agent skill from oliver-kriska/claude-elixir-phoenix.

    565 GitHub stars~1k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

  • Evals Context

    zgsm-ai/costrict

    Provides context about the CoStrict evals system structure in this monorepo.

    4.4k GitHub starsUsed in 1 repo~1.9k tokens
    AI & LLM EngineeringAuto-check passed

  • Vision

    xiincs/claude-code-vision-skill

    Call vision models (Doubao, Qwen, DeepSeek, OpenAI) to analyze images.

    170 GitHub stars~1.2k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Oracle Agent Team Orchestrator

    Bald0Wang/DeepSeek-Oracle

    Orchestrate DeepSeek Oracle multi-agent workflows by routing user intents to specialist oracle skills, enforcing safety gates, and composing one unified answer with follow-up questions and action…

    187 GitHub stars~551 tokensUpdated 7 mo ago
    AI & LLM EngineeringAuto-check passed

  • Dsh Playbook

    ZSeven-W/dsh-crew

    How to dispatch well — choosing flash vs pro, writing self-contained briefs, parallelism, verifying results, and guardrails

    156 GitHub stars~1.1k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • LLM Pipeline Profiler Analysis

    BBuf/AI-Infra-Auto-Driven-SKILLS

    Breaks LLM torch profiler traces down by forward pass, layer and kernel, with timing tables and Perfetto time ranges for the layers you want to inspect.

    911 GitHub stars~3.9k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

More from zilliztech/memsearch

  • Memory Config

    zilliztech/memsearch

    Diagnose and configure MemSearch memory behavior. An agent skill from zilliztech/memsearch.

    2.7k GitHub stars~2.9k tokensUpdated 14 days ago
    Auto-check passed

  • Memory To Skill

    zilliztech/memsearch

    Turn workflows from your MemSearch memory into reusable skills.

    2.7k GitHub stars~2k tokensUpdated 14 days ago
    Auto-check passed

  • Memory Recall

    zilliztech/memsearch

    Search and recall relevant memories from past sessions via memsearch.

    2.7k GitHub stars~807 tokensUpdated 14 days ago
    Auto-check passed

Works with

Categories

Questions about Memory Recall

What does Memory Recall do?

Search and recall relevant memories from past sessions via memsearch. Memory Recall is an agent skill from zilliztech/memsearch. Search and recall relevant memories from past sessions via memsearch.

When should I use Memory Recall?

Memory Recall fits situations like: the users question could benefit from historical context; debugging notes; previous conversations; project knowledge -- especially questions like what did I decide about X.

How do I install Memory Recall in Claude Code?

Run `npx skills add zilliztech/memsearch --skill memory-recall -a claude-code`. Or copy the skill folder (plugins/codex/skills/memory-recall in zilliztech/memsearch) into .claude/skills/memory-recall in your project. Claude Code loads it when a task matches its description.

How do I install Memory Recall in Codex?

Run `npx skills add zilliztech/memsearch --skill memory-recall -a codex`. Or copy the skill folder (plugins/codex/skills/memory-recall in zilliztech/memsearch) into .agents/skills/memory-recall in your project. Codex loads it when a task matches its description.

Can I use Memory Recall in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zilliztech/memsearch --skill memory-recall -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory-recall, .gemini/skills/memory-recall, .github/skills/memory-recall and .opencode/skills/memory-recall in your project.

What does Memory Recall need to run?

Going by SKILL.md and its folder, Memory Recall needs the command-line tools its instructions call (git, uvx and bash).

Does Memory Recall access the network?

SKILL.md contains no URLs. Its commands use git and uvx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Memory Recall safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Memory Recall use?

Memory Recall is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Memory Recall use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Memory Recall?

Skills that share tags, products or a category with Memory Recall: Phx Investigate (oliver-kriska/claude-elixir-phoenix, 565 stars), Evals Context (zgsm-ai/costrict, 4.4k stars), Vision (xiincs/claude-code-vision-skill, 170 stars) and Oracle Agent Team Orchestrator (Bald0Wang/DeepSeek-Oracle, 187 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memory Recall?

zilliztech (a GitHub organization) maintains it in zilliztech/memsearch, which has 2,727 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 24, 2026.

Source: zilliztech/memsearch on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.