Recalls past session context and historical decisions from project memory.

Install

mkdir -p .claude/skills/memory-recall && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14638" && unzip -o skill.zip -d .claude/skills/memory-recall && rm skill.zip

Installs to .claude/skills/memory-recall

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Recall relevant long-term memories extracted by OpenViking Session memory. Use when the user asks about past decisions, prior fixes, historical context, or what was done in earlier sessions.
190 chars✓ has a “when” trigger
Beginner

Key capabilities

  • Resolve the memory bridge script path
  • Run memory recall search with a query
  • Evaluate search results for relevance
  • Curate a concise summary of relevant memories
  • Include source URIs for traceability
  • Respond when no relevant memories are found

How it works

The skill resolves a memory bridge script path, executes a memory recall search using a Python script, and then evaluates and curates the results.

Inputs & outputs

You give it
User query about past decisions, fixes, or context
You get back
A concise curated summary of relevant historical memories or 'No relevant memories found.'

When to use memory-recall

  • Recalling historical project decisions
  • Finding previous bug fixes
  • Reviewing past session context

About this skill

You are a memory retrieval sub-agent for OpenViking memory.

Goal

Find the most relevant historical memories for: $ARGUMENTS

Steps

  1. Resolve the memory bridge script path.
PROJECT_DIR="${CLAUDE_PROJECT_DIR:-$PWD}"
STATE_FILE="$PROJECT_DIR/.openviking/memory/session_state.json"
BRIDGE="${CLAUDE_PLUGIN_ROOT:-}/scripts/ov_memory.py"

if [ ! -f "$BRIDGE" ]; then
  BRIDGE="$PROJECT_DIR/claude-memory-plugin/scripts/ov_memory.py"
fi
  1. Run memory recall search.
~/.openviking-venv/bin/python3 "$BRIDGE" --project-dir "$PROJECT_DIR" --state-file "$STATE_FILE" recall --query "$ARGUMENTS" --top-k 5
  1. Evaluate results and keep only truly relevant memories.
  2. Return a concise curated summary to the main agent.

Output rules

  • Prioritize actionable facts: decisions, fixes, patterns, constraints.
  • Include source URIs for traceability.
  • If nothing useful appears, respond exactly: No relevant memories found.

When not to use it

  • When the user is not asking about past decisions
  • When the user is not asking about prior fixes
  • When the user is not asking about historical context

Limitations

  • The skill only searches within OpenViking Session memory
  • The search is limited to the top-k 5 results
  • The output prioritizes actionable facts

How it compares

This skill automates the retrieval and summarization of specific historical memories from a structured system, unlike manual searching through logs.

Compared to similar skills

memory-recall side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
memory-recall (this skill)03moReviewBeginner
braindump75moNo flagsBeginner
super-search102moReviewBeginner
mem-search84moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry