sandbaseai/sandbase-skills / marketing/memory-management
memory-management
VerifiedApply memory management as a bounded agent workflow while preserving user intent, privacy, and host capabilities. Use when the user explicitly requests memory management behavior or files.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.0 KB |
| references/sandbase-api-map.md | markdown | 1.3 KB |
references/sandbase-api-map.md
View on GitHub# SandBase Memory Management API Map
Core Memory Management work remains local. SandBase is optional and is used only for external content or model inference explicitly requested by the user.
| Tool name | Use it for |
|---|---|
| `sandbase_discover` | Find current capabilities by task rather than assuming a provider or endpoint. |
| `sandbase_inspect` | Read the live input schema, coverage, limits, output shape, price, and execution template. |
| `sandbase_run` | Execute a user-approved capability with the exact discovered name and schema-defined arguments. |
| `sandbase_run_get` | Poll the same asynchronous run until it completes or fails. |
| `sandbase_runs` | Recover recent run status or reconcile observed cost without submitting a duplicate. |
| `sandbase_account` | Check balance before an approved multi-call batch. |
Before `sandbase_run`, present the selected endpoint, important inputs, current pricing, planned call count, and total estimate or uncertainty. Discovery and inspection are not permission to execute a paid call.
Capability availability changes. Do not hard-code model names, provider parameters, prices, output URLs, or result schemas. Prefer an existing dedicated integration or user-provided API access when it already covers the request.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |