Workspace memory steward

What this skill teaches

Workflow

1. 1

   Confirm that the user wants a durable Prism memory rather than temporary task context.

2. 2

   List existing memories in the authorized Project before creating a duplicate or applying a correction.

3. 3

   Use remember_workspace_memory with the correct kind, scope, confidence, and evidence refs. A semantic fact needs at least one approved evidence ref.

4. 4

   Use correct_workspace_memory when the user supplies a correction and include the reason and supporting evidence.

5. 5

   Use forget_workspace_memory only for a specific stable memory id after explicit confirmation.

Tool routing

Safety boundaries

---
name: prism-workspace-memory-steward
description: "Use when the user explicitly asks an AI client to remember, inspect, correct, or forget durable workspace memory inside authorized Projects."
---

# Workspace memory steward

Keep durable workspace memory explicit, evidence-linked, and easy to correct or remove.

## Before you start

Copy this guidance into ChatGPT, Claude, Codex, Grok, or another client that accepts custom instructions. It changes the client's instructions only; it does not grant Prism access. Direct MCP calls require the client's current MCP support, a configured connection, and separately authorized scopes.

Scopes this workflow may need:

- `memory:read`
- `memory:write`

The installed skill does not grant these permissions. Use only the scopes and Projects authorized on the current Prism MCP connection.

## Workflow

1. Confirm that the user wants a durable Prism memory rather than temporary task context.
2. List existing memories in the authorized Project before creating a duplicate or applying a correction.
3. Use remember_workspace_memory with the correct kind, scope, confidence, and evidence refs. A semantic fact needs at least one approved evidence ref.
4. Use correct_workspace_memory when the user supplies a correction and include the reason and supporting evidence.
5. Use forget_workspace_memory only for a specific stable memory id after explicit confirmation.

## Tool routing

- `list_workspace_memories`: Inspect bounded authorized memory and obtain stable ids.
- `remember_workspace_memory`: Save only explicit durable memory with appropriate evidence and scope.
- `correct_workspace_memory`: Apply a user-supplied correction while retaining correction provenance.
- `forget_workspace_memory`: Purge one specific memory after explicit confirmation.

## Expected result

- Only durable facts, preferences, procedures, open questions, or source preferences are saved.
- Corrections preserve provenance and target a stable memory id.
- Forgetting purges the selected memory content without deleting canonical Project sources.

## Boundaries

- A skill does not grant Prism access. The connection must separately authorize every required scope and Project.
- Call only tools verified callable by the current AI host. Use discover_prism_actions for granular actions. If a default workflow tool is missing, follow the capability-handshake recovery guidance instead of inventing a substitute tool.
- Read before writing. Mutate Prism only when the user asked for a durable change and the connected tool exposes that exact action.
- Keep retrieved evidence separate from analysis. Cite Prism source ids, titles, snippets, locations, and chunk ids when available.
- Never save hidden chain-of-thought, secrets, transient task state, or an inferred personal preference without user intent.
- memory:read and memory:write are privacy-sensitive explicit scopes.
- Forgetting memory never deletes canonical Project sources and retains only a non-content audit marker.