Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →shobcoder/memory
Persistent, token-efficient project memory. When ON, maintains a `.shob/memory/` folder of structured `.md` files so the full context of the project is NEVER lost across responses, sessions, or context compaction. Uses progressive disclosure — routes through a lightweight INDEX and loads only the files a task needs, instead of dumping everything into context. Read memory at the START of every response, write it back at the END.
Passed 6 of 11 test cases with the skill, and 6 of 11 without it.
and 3 more in the full report
5 fixed6 passed either way4 still failing7 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
When opening persistent context at the start of a turn, besides `INDEX.md`, which two specific hot files in `.shob/memory/` are required to be loaded every single time?
| Checked | Without skill | With skill |
|---|---|---|
| Names `STATE.md` as one required hot file | Missed | Passed |
| Names `NEXT.md` as the second required hot file | Missed | Passed |
The instructions your model reads when the skill loads.
Give the project a durable brain. While ON, you keep a living set of markdown files under
.shob/memory/ that capture everything needed to resume the project cold — with zero prior
chat history — and keep working without re-asking the user anything.
You are a memory-first agent. This is who you are, not an optional step.
Before you do ANYTHING the user asks — answering, coding, searching, planning, running a command — your FIRST action is to read
.shob/memory/. Memory is the first thing you touch every single turn. No task starts before memory is loaded.
Rules that you NEVER break while memory is ON:
.shob/memory/ are your only trusted memory. If it is not written there, you treat it as
not remembered.If .shob/memory/ does not exist yet, your memory-first action is to BOOTSTRAP it (see below)
before doing the user's task.
ACTIVE EVERY RESPONSE while ON. The memory loop runs on every turn, not just when asked. Off only when user says "memory off" / "stop memory" / "disable memory".
State is stored on disk, so it survives across sessions. The chat can be wiped — the project
brain in .shob/memory/ must be enough to fully reconstruct context.
test cases passed, vs 6 / 11 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.