Claude-skill-registry engram-recall

install
source · Clone the upstream repo
git clone https://github.com/majiayu000/claude-skill-registry
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/engram-recall" ~/.claude/skills/majiayu000-claude-skill-registry-engram-recall && rm -rf "$T"
manifest: skills/data/engram-recall/SKILL.md
source content

Engram Recall

Before diving into implementation, recall relevant context from past sessions.

When to Use

  • Starting work on an existing codebase
  • Asked "why was this done this way?"
  • Need to understand previous decisions
  • Continuing work from a previous session

Workflow

Step 1: Check for engram database

ls .engram/memory.db 2>/dev/null || echo "No engram database found"

If no database exists, ingest Claude Code history:

npx engram ingest-claude --days 14

Step 2: Search for relevant context

Before implementing, search for related decisions:

npx engram search "your task keywords" --json

Step 3: Review file-specific context

If working on a specific file:

npx engram context get --file path/to/file.ts --json

Step 4: Document new decisions

After making significant decisions, add context:

npx engram context add --file path/to/file.ts --note "Chose X over Y because..."

Integration with Other Skills

This skill chains well with:

SkillWhen to Combine
tddRecall past test patterns before writing tests
code-reviewCheck if similar code was reviewed before
describe-codebaseAugment description with decision history

Output Format

When recalling context, format findings as:

## Relevant Context Found

**From session [date]:**
- [Summary of decision or discussion]
- Related files: [list]

**Recommendation:** [How this affects current task]

Important

  • Don't blindly follow past decisions if they were wrong
  • Context is for understanding, not for copy-paste
  • Update context when decisions change