diff --git a/deep-research/SKILL.md b/deep-research/SKILL.md
index 943451d..b4dd16b 100644
--- a/deep-research/SKILL.md
+++ b/deep-research/SKILL.md
@@ -1,7 +1,7 @@
 ---
 name: deep-research
 description: Dispatch exhaustive deep web research to the research profile. Triggered by "deep research", "ask web", or "research this". The research profile runs with the deep-web-research skill loaded — six-move flow, external ledger, mechanical saturation, disconfirmation, condensation from disk.
-version: 2.2.1
+version: 2.3.0
 author: Hermes Agent
 license: MIT
 platforms: [linux]
@@ -44,7 +44,7 @@ hermes -p research -s deep-web-research chat -q "<question>" -Q --max-turns 600
 ```
 
 - Output line 1: `session_id: <id>` — capture this
-- Output line 2+: the research agent's condensed answer
+- The research agent writes the condensed answer to `~/workspace/research/results/<YYYY-MM-DD>-<slug>.md`
 - Hold the session_id for follow-up questions
 
 **Subsequent asks (resume the session):**
@@ -52,6 +52,18 @@ hermes -p research -s deep-web-research chat -q "<question>" -Q --max-turns 600
 hermes -p research -s deep-web-research chat --resume <session_id> -q "<follow-up>" -Q --max-turns 600 --yolo
 ```
 
+## Delivery Method (MANDATORY)
+
+**File-only delivery.** The research agent writes the full condensed answer to a markdown file and reports the path. Nothing is relayed inline.
+
+- **Path:** `~/workspace/research/results/<YYYY-MM-DD>-<slug>.md`
+- **Slug:** derived from the question (e.g., `minimax-m3-temperature-support`)
+- **Format:** YAML frontmatter (question, date, sources, confidence) + markdown body with structured findings
+- **After dispatch:** report the session_id and the expected output path to the user
+- **When user asks for results:** use `session_search` on the research profile with the captured session_id, then relay the path — the user reads the file directly
+
+The file is the single source of truth. Do not inline the research answer — it's always lossy for 100+ turn sessions.
+
 ## Post-Dispatch Behavior (MANDATORY)
 
 **After dispatching, continue working with the user. Do NOT poll, wait, or check for results unless the user explicitly asks.**
@@ -61,7 +73,7 @@ hermes -p research -s deep-web-research chat --resume <session_id> -q "<follow-u
 - Do NOT call `process wait` or `process poll` on the background process.
 - Do NOT proactively surface results when the background process completes.
 - **Only check for results when the user explicitly asks** (e.g., "what did the research find?", "is it done?", "show me the results").
-- When the user asks, use `session_search` on the research profile with the captured session_id to retrieve and relay the condensed answer.
+- When the user asks, use `session_search` on the research profile with the captured session_id to confirm completion, then report the file path: `~/workspace/research/results/<date>-<slug>.md`. Do NOT inline the answer — the file is the source of truth.
 
 The session_id is captured from output line 1 and held in conversation context for follow-up questions and result retrieval. No state file needed.
 
@@ -116,7 +128,7 @@ The research agent must determine the best tools for each research type — not
 
 ## Relay Rule
 
-Relay the research agent's actual response. Do not paraphrase or summarize. If the response is long, chunk it. The research agent already condensed — don't re-condense.
+Do NOT relay the research agent's response inline. The file at `~/workspace/research/results/<date>-<slug>.md` is the single source of truth. When the user asks for results, report the file path and let them read it directly. If the user asks for a specific finding, you may extract that one section from the file — but never inline the full answer.
 
 ## Spot-check Rule