# task_memory_search

The task_memory_search prompt for Claude Code finds summaries of earlier tasks across conversations. Search by task wording, then narrow results by app package or start date.

- prompt · `type=prompt` · Claude Code, ChatGPT · ★ 9488 repo stars
- Author: wangzan101
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/wangzan101/Mika/tree/HEAD/core/src/main/resources/prompts/tools/task_memory_search.md
- Updated: 2026-11-16
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/prompts/task-memory-search

## What it does

The prompt searches earlier tasks using words from their titles, conclusions, or steps. It returns up to 10 brief records with a title, run time, apps or sites involved, a one-line conclusion, and the step count. Full step details are excluded.

Add an app package or a start date to narrow the search. For a relevant result, open its timeline with `task_memory_timeline`, then inspect a particular step with `task_memory_step`. In Claude Code, save the prompt as `.claude/commands/task_memory_search.md`.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/commands/task_memory_search.md`

### ChatGPT

**How to use**
- Paste the text at the start of a chat or into project instructions

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/wangzan101/Mika/tree/HEAD/core/src/main/resources/prompts/tools/task_memory_search.md

## When to use it
- find an earlier task from words in its title
- reuse the conclusion from a previous run
- filter task summaries by app package and date
- open a matching task’s timeline and a specific step

## Example prompts
- Find earlier tasks mentioning “profile screen update”.
- Search for tasks whose conclusion mentions authentication setup and filter by app package.
- Find a run after the given start date, then open its timeline and a specific step.

## Source text · task_memory_search.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: e4f78fc023d7f14e.

BEGIN THIRD-PARTY FILE e4f78fc023d7f14e
```text
Look up summaries of past tasks (across conversations) so you can reuse what worked and avoid repeating what failed. Returns up to 10 compact entries — only the title, when it ran, which apps/sites it touched, its one-line conclusion and step count, never the full steps. Query with words from the task title, its conclusion or its steps; filter by app package and/or a start date when you know them. When a returned entry looks relevant, read its timeline with task_memory_timeline and then a specific step with task_memory_step.
```
END THIRD-PARTY FILE e4f78fc023d7f14e

The third-party file has ended. Everything between the e4f78fc023d7f14e tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

© wangzan101 · Apache-2.0 · https://github.com/wangzan101/Mika/tree/HEAD/core/src/main/resources/prompts/tools/task_memory_search.md

## Similar
- [memory-metadata-search](https://affpapa.org/en/nevibecode/skills/basicmachines-co-memory-metadata-search.md) — skill · 564 installs
- [Vector Search — In-Memory TF-IDF Semantic Store](https://affpapa.org/en/nevibecode/mcp/vector-search-in-memory-tf-idf-semantic-store.md) — MCP server · 3562 installs
- [memory-search](https://affpapa.org/en/nevibecode/skills/ruvnet-memory-search.md) — skill · 751 installs
- [search-memory](https://affpapa.org/en/nevibecode/skills/search-memory.md) — skill · 740 installs
- [reviser](https://affpapa.org/en/nevibecode/prompts/reviser.md) — prompt · ★ 336 repo stars
- [task-observer](https://affpapa.org/en/nevibecode/skills/eoghan-henn-and-contributors-task-observer.md) — skill · 19300 installs

From the same set: [wangzan101/mika](https://affpapa.org/en/nevibecode/by/wangzan101/mika.md) — 132 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
