diff --git a/skills/official/akashi/README.md b/skills/official/akashi/README.md
index cd24237..1333edd 100644
--- a/skills/official/akashi/README.md
+++ b/skills/official/akashi/README.md
@@ -15,7 +15,7 @@ Pasting notes into context burns tokens and trust. Akashi serves only the passag
 | Average per query | 22,530 tokens | 1,262 tokens | **94.4%** |
 | 8-query conversation | 811,085 tokens | 44,759 tokens | **94.5%** |
 
-Not a promise. A measurement you can reproduce: full table on the [Akashi page](https://apilium.com/en/products/akashi).
+Not a promise. A measurement you can reproduce: full table on the [Akashi page](https://apilium.com/en/products/akashi). Said differently: about 18x more of your knowledge per token spent.
 
 ## Connect
 
diff --git a/skills/official/akashi/SKILL.md b/skills/official/akashi/SKILL.md
index 7f31020..604548c 100644
--- a/skills/official/akashi/SKILL.md
+++ b/skills/official/akashi/SKILL.md
@@ -58,6 +58,9 @@ decisions, conventions, people, notes, plans), query the vault:
 - `aingle_vault_map`: orientation. Hubs, semantic clusters, indices.
 - `aingle_note_context {note}`: the verified neighborhood of one note.
 - `aingle_sources`: what is indexed, with content hashes.
+- To trace how two notes or topics connect: call `aingle_note_context` on each
+  and intersect their neighborhoods, or walk `aingle_backlinks` from one side;
+  report the connecting chain with citations for every hop.
 
 Prefer several small `ground` calls over one broad one. Never dump whole
 notes into context when passages answer the question.