Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →syncable-dev/memtrace-episode-replay
Replay the graph diff of one episode — a single git commit or working-tree save — to inspect what it changed: added/modified/removed symbols and edges.
Passed 16 of 20 test cases with the skill, and 4 of 20 without it.
and 16 more in the full report
14 fixed4 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
What is the default record limit per bucket when replaying an episode graph diff in Memtrace if no `limit` parameter is explicitly provided?
| Checked | Without skill | With skill |
|---|---|---|
| States that the default limit is 200 | Missed | Passed |
The instructions your model reads when the skill loads.
Replay the graph diff for one episode (a single git commit or working-tree save). Shows which nodes/edges were added, modified, or removed in that episode — not a multi-episode time-range narrative.
Use get_evolution(mode: "recent") to find episode IDs and timestamps, then drill into a specific episode with this tool.
| Approach | Parameters |
|---|---|
| Known episode UUID | episode_id |
| Newest episode in repo | repo_id + episode_index: 0 |
| Nth newest | repo_id + episode_index: N |
There is no from / to / include_working_tree on this tool.
| Param | Purpose |
|---|---|
symbol | Scope to one symbol name |
file_path | Substring filter on record paths |
kind | e.g. "Function", "CALLS" |
mode | "graph_summary" for digest on huge commits |
compress | default true — collapse identical-hash modifications |
limit / cursor | Pagination per bucket (default limit 200) |
Full parameter spec for every Memtrace tool: references/mcp-parameters.md (bundled at the memtrace-skills plugin root).
From get_evolution:
{ "repo_id": "memdb", "from": "7d ago", "mode": "recent", "limit": 20 }
Each entry has episode metadata including id (use as episode_id) and reference_time.
test cases passed, vs 4 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.