From shared-memory
Store multiple sharedMemory entries with one MCP call using memory_bulk_set. Efficiently capture project-specific and general entries in batch.
How this skill is triggered — by the user, by Claude, or both
Slash command
/shared-memory:memory-bulk-setThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use `memory_bulk_set` for multiple entry writes in one round trip — useful for importing sessions, capturing decisions, or recording multiple learnings at once.
Use memory_bulk_set for multiple entry writes in one round trip — useful for importing sessions, capturing decisions, or recording multiple learnings at once.
entries: array of set items. Each item uses the memory_set fields: key, value, optional metadata (summary, tags, importance), expiry (ttlMs or expiresAt), and ifRevision.Example:
{
"entries": [
{ "key": "task.resume-update", "value": {...}, "summary": "...", "tags": [...], "importance": 7 },
{ "key": "learning.ripgrep-flags", "value": {...}, "summary": "...", "tags": [...], "importance": 6 }
]
}
Each item is isolated: one failure does not stop the others. Use this for independent writes, not all-or-nothing transactions. Search first when duplicate risk is high. Works with mixed project and general entries.
Success returns { ok: true, results }, where each result has per-item ok, key, revision, or error. Review error results to retry or fix failed entries.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub pruthuraj/sharedmemory --plugin shared-memory