Name: memory-recall
Author: abobreshov

Imported from abobreshov/da-hackaton (.claude/skills/memory-recall/SKILL.md). Install upstream with npx skills add abobreshov/da-hackaton --skill memory-recall. Copyright stays with the author.

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

Goal

Find the most relevant historical memories for: $ARGUMENTS

Steps

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

Run memory recall search.

~/.openviking-venv/bin/python3 "$BRIDGE" --project-dir "$PROJECT_DIR" --state-file "$STATE_FILE" recall --query "$ARGUMENTS" --top-k 5

Evaluate results and keep only truly relevant memories.
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.

{ "ocm": "1", "id": "abobreshov-da-hackaton-memory-recall", "kind": "skill", "name": "memory-recall", "description": "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.", "publisher": "abobreshov", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "github" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "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." ], "primary": false, "metadata": { "source": { "provider": "github", "repository": "https://github.com/abobreshov/da-hackaton", "path": ".claude/skills/memory-recall/SKILL.md", "ref": "ac50e1f362d933dcf1bd8a182310454256d547f6", "url": "https://github.com/abobreshov/da-hackaton/blob/ac50e1f362d933dcf1bd8a182310454256d547f6/.claude/skills/memory-recall/SKILL.md", "key": "abobreshov/da-hackaton/.claude/skills/memory-recall/SKILL.md" }, "allowed_tools": [ "Bash" ] }, "instructions": "You are a memory retrieval sub-agent for OpenViking memory.\n\n## Goal\nFind the most relevant historical memories for: $ARGUMENTS\n\n## Steps\n\n1. Resolve the memory bridge script path.\n```bash\nPROJECT_DIR=\"${CLAUDE_PROJECT_DIR:-$PWD}\"\nSTATE_FILE=\"$PROJECT_DIR/.openviking/memory/session_state.json\"\nBRIDGE=\"${CLAUDE_PLUGIN_ROOT:-}/scripts/ov_memory.py\"\n\nif [ ! -f \"$BRIDGE\" ]; then\n BRIDGE=\"$PROJECT_DIR/claude-memory-plugin/scripts/ov_memory.py\"\nfi\n```\n\n2. Run memory recall search.\n```bash\n~/.openviking-venv/bin/python3 \"$BRIDGE\" --project-dir \"$PROJECT_DIR\" --state-file \"$STATE_FILE\" recall --query", "cost": { "context_tokens": 236 } }

memory-recall

About

Goal

Steps

Output rules

Use it

Manifest

Reviews