docs(skills): update skills to reflect 0.2.8 API changes

- Rename workspace context → database context throughout; context is
  now scoped to the active database (/v1/databases/{id}/context)
- Add --database-id / -d flag to all context command examples
- Add hotdata databases set to databases section
- Add --expires-at flag to databases create
- Fix databases create flag: --name → --description
- Fix databases tables subcommand syntax: positional <database> arg
  replaced by --database <id> flag
- Add databases load dot-notation shorthand
- Fix datasets create: --label → --description, --table-name → --name
  (now required); remove --file / --url / --upload-id paths (removed in 0.2.8)
- Fix datasets update: same flag renames
- Fix analytics skill Chain examples with corrected flag names

Author: eddietejeda

skills/hotdata-analytics/SKILL.md

@@ -82,15 +82,16 @@ hotdata results <result_id> [--workspace-id <workspace_id>] [--output table|json
 2. **Materialize** (pick one)
 
    ```bash
-   hotdata datasets create --label "chain slice" --sql "SELECT ..." [--table-name chain_slice]
-   hotdata datasets create --label "from saved" --query-id <query_id> [--table-name ...]
+   hotdata datasets create --name chain_slice [--description "chain slice"] --sql "SELECT ..."
+   hotdata datasets create --name chain_from_saved [--description "from saved"] --query-id <query_id>
    ```
 
    Or managed parquet:
 
    ```bash
-   hotdata databases create --name analytics --table slice
-   hotdata databases tables load analytics slice --file ./slice.parquet
+   hotdata databases create --description "analytics" --table slice
+   hotdata databases set <returned-id>
+   hotdata databases tables load slice --file ./slice.parquet
    ```
 
 3. **Chain query** — use printed **`full_name`** or `datasets list` **FULL NAME** column: