diff --git a/skills/mpi-terms-search/SKILL.md b/skills/mpi-terms-search/SKILL.md
index 1eddb12..c207d25 100644
--- a/skills/mpi-terms-search/SKILL.md
+++ b/skills/mpi-terms-search/SKILL.md
@@ -6,14 +6,14 @@ category: research
 
 # Terms Search
 
-Database: `$MPI_PROJECT_ROOT/toolkit/terms-database/termlib.duckdb`
-CLI: `$MPI_PROJECT_ROOT/toolkit/terms-database/search.py`
-Server: `$MPI_PROJECT_ROOT/toolkit/terms-database/server.py`
+Database: `toolkit/terms-database/termlib.duckdb`
+CLI: `toolkit/terms-database/search.py`
+Server: `toolkit/terms-database/server.py`
 
 ## CLI (preferred)
 
 ```
-$MPI_PROJECT_ROOT/toolkit/terms-database/search.py <query> [limit]
+toolkit/terms-database/search.py <query> [limit]
 ```
 
 Multi-word queries are ANDed. Searches both `zh` and `en` columns.
@@ -22,7 +22,7 @@ Multi-word queries are ANDed. Searches both `zh` and `en` columns.
 
 ```python
 import sys
-sys.path.insert(0, '$MPI_PROJECT_ROOT/terms-search')
+sys.path.insert(0, 'toolkit/terms-database')
 from search import search
 results = search("空性", limit=5, src="DoT定稿")
 # → list of {zh, en, loc, source} dicts
@@ -32,7 +32,7 @@ Use this inside `execute_code` scripts for batch lookups — no subprocess neede
 
 ## HTTP API (use only when CLI is insufficient)
 
-Start: `python3 $MPI_PROJECT_ROOT/toolkit/terms-database/server.py` (port 8910)
+Start: `python3 toolkit/terms-database/server.py` (port 8910)
 
 - `GET /` — plain HTML UI (form + results table, no CSS)
 - `GET /` — plain HTML UI (form + results table, no CSS)
@@ -64,14 +64,14 @@ Errors return `{"error": "..."}` with HTTP 500 (API) or shown inline (UI).
 ## Direct DuckDB
 
 ```
-duckdb $MPI_PROJECT_ROOT/toolkit/terms-database/termlib.duckdb
+duckdb toolkit/terms-database/termlib.duckdb
 ```
 
 Key tables: `unified_terms_flat` (zh, en, loc, source), individual source tables, `unified_terms` view.
 
 ## Rebuilding
 
-Terms data comes from `$MPI_PROJECT_ROOT/guide/03 术语库/`. To rebuild:
+Terms data comes from `guide/03 术语库/`. To rebuild:
 1. Convert source xlsx/ods → CSV+YAML in `_output/`
 2. Rebuild DuckDB from CSVs
 3. Materialize `unified_terms_flat` view → table for performance
diff --git a/skills/mpi-terms-search/references/translation-alignment.md b/skills/mpi-terms-search/references/translation-alignment.md
index a5180cd..7a6bb9e 100644
--- a/skills/mpi-terms-search/references/translation-alignment.md
+++ b/skills/mpi-terms-search/references/translation-alignment.md
@@ -10,7 +10,7 @@ After producing a first-pass translation, or when the user asks to check termino
 
 1. Read the full translated file. Extract all Chinese terms from `{% "TERM" (pinyin) = ENGLISH ... %}` blocks.
 
-2. Start the search server: `python3 $MPI_PROJECT_ROOT/toolkit/terms-database/server.py &` (port 8910). It may already be running — check with `curl -s http://localhost:8910/`.
+2. Start the search server: `python3 toolkit/terms-database/server.py &` (port 8910). It may already be running — check with `curl -s http://localhost:8910/`.
 
 3. Batch-search each term via the HTTP API:
    ```
diff --git a/skills/mpi-translation-review/references/terms-db-alignment.md b/skills/mpi-translation-review/references/terms-db-alignment.md
index 6f48b4f..fe7ef34 100644
--- a/skills/mpi-translation-review/references/terms-db-alignment.md
+++ b/skills/mpi-translation-review/references/terms-db-alignment.md
@@ -8,7 +8,7 @@ Import directly in `execute_code` scripts — no subprocess, no server, no text
 
 ```python
 import sys
-sys.path.insert(0, '$MPI_PROJECT_ROOT/terms-search')
+sys.path.insert(0, 'toolkit/terms-database')
 from search import search
 
 results = search("三级修学", limit=5)
@@ -20,7 +20,7 @@ results = search("空性", loc="心经", src="DoT定稿", limit=5)
 
 ```python
 import sys
-sys.path.insert(0, '$MPI_PROJECT_ROOT/terms-search')
+sys.path.insert(0, 'toolkit/terms-database')
 from search import search
 
 terms = ["三无漏学", "八步三禅", "闻思修", ...]
diff --git a/skills/readme.dj b/skills/readme.dj
index d8a4680..430b488 100644
--- a/skills/readme.dj
+++ b/skills/readme.dj
@@ -9,10 +9,10 @@ Add to `~/.hermes/config.yaml`:
 ```yaml
 skills:
   external_dirs:
-  - $MPI_PROJECT_ROOT/toolkit/skills
+  - /path/to/mpi/toolkit/skills
 ```
 
-{% Edit config.yaml directly — `hermes config set` stores list values as strings. %}
+{% Replace `/path/to/mpi` with the absolute path to this repository. Edit config.yaml directly — `hermes config set` stores list values as strings. %}
 
 ## Skills
 
diff --git a/terms-database/search.py b/terms-database/search.py
index 12e4c0f..6654257 100755
--- a/terms-database/search.py
+++ b/terms-database/search.py
@@ -1,4 +1,7 @@
-#!/usr/bin/env python3
+#!/usr/bin/env -S uv run --script
+# /// script
+# dependencies = ["duckdb"]
+# ///
 """Full-text search over MPI term database. Queries unified_terms_flat via DuckDB LIKE.
 
 Module usage: