Automated summary
Searches across memory files for specific content to recall past decisions, sessions, or knowledge.
Strengths
- Quickly find past information without leaving the working context.
- Supports scope filtering (sessions, decisions, knowledge) to narrow results.
- Shows surrounding context for each match to improve understanding.
Limitations
- Simple text-based search, no complex or semantic queries supported.
- Relies on the existence and proper organization of memory files.
- Only searches local memory files within the project.
Use this skill when you need to recall a specific piece of information documented in memory files.
Avoid using it for general codebase searches or for data stored outside the memory system.
Security analysis
SafeThe skill only reads local memory markdown files and displays contents; it does not execute any commands, access networks, or modify files. No security risks.
No concerns found
How this analysis is madeExamples
Search decisions for rate limitingSearch sessions from last week: API changesSearch memory for authentication patternsdescription: Search across memory files for specific content. Use to find past decisions, recall when something was discussed, or locate specific knowledge.
Memory Search
Search across memory files for specific content.
Instructions
When this skill is triggered, perform the following steps:
Step 1: Get Search Query
If the user provided a query inline, use it. Otherwise prompt:
What would you like to search for?
You can also specify a scope:
- `sessions` - Only search session summaries
- `decisions` - Only search decision records
- `knowledge` - Only search knowledge files
- `all` - Search everything (default)
Example: "search decisions for rate limiting"
Step 2: Determine Scope
Parse the user's request to determine scope:
- If they mention "sessions" or "session summaries" -> scope: sessions
- If they mention "decisions" or "ADR" -> scope: decisions
- If they mention "knowledge" -> scope: knowledge
- Otherwise -> scope: all
Step 3: Search Files
Search the appropriate directories:
| Scope | Directory |
|-------|-----------|
| sessions | .claude/memory/sessions/*.md |
| decisions | .claude/memory/decisions/*.md |
| knowledge | .claude/memory/knowledge/*.md |
| all | All of the above |
For each file, search for the query (case-insensitive) and note:
- Filename
- Line number(s) where matches occur
- Context around the match (2-3 lines before/after)
Step 4: Display Results
Present results in a formatted summary:
## Memory Search Results
**Query**: "[search term]"
**Scope**: [sessions/decisions/knowledge/all]
**Matches**: [count] results in [count] files
---
### Sessions
#### 2024-01-15_14-30_summary.md
> Line 12: "Implemented **rate limiting** middleware..."
> Line 15: "Decision: Use sliding window **rate limiting**"
---
### Decisions
#### 0003_rate_limiting_strategy.md
> Line 1: "# Decision 0003: **Rate Limiting** Strategy"
> Line 15: "Chose token bucket **rate limiting**..."
---
### Knowledge
No matches found.
---
**Tip**: Use `/memory-status` to see all available files.
Step 5: Offer Follow-up Actions
After showing results, offer:
Would you like me to:
1. Read any of these files in full?
2. Narrow the search to a specific scope?
3. Search for a different term?
File Paths
- Sessions:
.claude/memory/sessions/ - Decisions:
.claude/memory/decisions/ - Knowledge:
.claude/memory/knowledge/
Search Features
Basic Search
Simple text matching (case-insensitive):
/memory-search authentication
Scoped Search
Limit to specific file types:
/memory-search decisions: JWT
/memory-search sessions: bug fix
/memory-search knowledge: API patterns
Date Filtering
Find content from specific time periods:
/memory-search sessions from last week: deployment
/memory-search decisions in January: database
Error Handling
- If no matches found, suggest:
- Trying different search terms
- Broadening the scope
- Checking if memory system has content
- If memory directory doesn't exist, inform user to run setup
- If a directory is empty, note it and continue searching others
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/memory-search-mm78nnws/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/memory-search-mm78nnws' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/memory-search-mm78nnws/download' --output '.skill-downloads/memory-search-mm78nnws/SKILL.md.part' && mv '.skill-downloads/memory-search-mm78nnws/SKILL.md.part' '.skill-downloads/memory-search-mm78nnws/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/memory-search-mm78nnws/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.