From memory
Search and retrieve stored memories. Load topic files on demand. Use when you need context from previous sessions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/memory:recallThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read `.claude/memory/index.md` to see all stored pointers. This is Tier 1 — always small.
Read .claude/memory/index.md to see all stored pointers. This is Tier 1 — always small.
For each pointer that matches the current need, read the full topic file from .claude/memory/topics/<slug>.md. This is Tier 2 — loaded on demand.
If Tier 1 and Tier 2 don't have what you need, search session transcripts with grep:
grep -r "keyword" ~/.claude/projects/*/
This is Tier 3 — never load whole files, only grep for specific terms.
Every topic file has a Last verified: date. When recalling:
Before recommending from memory:
"The memory says X exists" is not the same as "X exists now."
When presenting recalled memories:
Previously noted (<date>):
- <memory content>
- <memory content>
⚠ Verify before acting — memory may be stale.
npx claudepluginhub artmin96/forge-studio --plugin memoryGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.