feat: generate brain tools skill from OpenAPI; rename db-yaml to postgres (#21)

Cursor skills stay in lockstep with serve handlers. CI checks every bin/
path named in SKILL.md exists.

skills/brain/SKILL.md

@@ -45,5 +45,6 @@ are not wired yet); do not treat it as a graph walk.
 - If recall looks wrong, run `bin/brain/eval.go`; it gates control questions and
   should stay at or above 95% recall@5.
 - Agents: `GET /openapi.json` and `POST /mcp` on `bin/brain/serve.go` (same
-  handlers; tool names match paths `search`/`get`/`stats`/`audit`).
+  handlers; tool names match paths `search`/`get`/`stats`/`audit`). Generated
+  list: [tools.md](tools.md).
 - Never report an unconfirmed single-source local answer as fact.

skills/brain/tools.md

@@ -0,0 +1,11 @@
+# brain HTTP / MCP tools
+
+Generated from `internal/httpapi.Ops`. Do not edit by hand.
+
+Serve: `bin/brain/serve.go` (`GET /openapi.json`, `POST /mcp`).
+
+- `search` — deduction search (facts → info → web)
+- `get` — read one leaf by id
+- `stats` — index health
+- `audit` — facts confidence histogram
+- `ingest` — rebuild hint (write is v2)

skills/db-yaml/SKILL.md

@@ -1,39 +0,0 @@
----
-name: db-yaml
-description: >-
-  Read any Postgres as compact YAML through db/psql-yq, with a read-only guard and
-  named profiles. Use when a task needs table contents, column types or a SELECT
-  against cs_brain or another project database.
----
-
-# db-yaml
-
-`bin/db/psql-yq` (vendored in this repo) talks to Postgres and returns YAML,
-which is far cheaper than a psql ASCII table and easy to slice with `yq`.
-
-```bash
-bin/db/psql-yq --profile onlyoffice -s document_asset   # column list
-bin/db/psql-yq --profile onlyoffice -t task_result -l 20  # sample rows as YAML
-bin/db/psql-yq --profile onlyoffice -c 'SELECT ...'     # query -> YAML
-```
-
-Ad-hoc targets without a profile:
-
-```bash
-bin/db/psql-yq --container my-pg --db app -c 'SELECT 1'
-bin/db/psql-yq --dsn 'postgres://user@host:5432/db' -c 'SELECT 1'
-```
-
-## Profiles
-
-Connection details live in `~/.config/brain/db-profiles.yml` (mode 600), never in a
-project repo. A profile names either a `container` or a `host`; passwords are read
-from a separate `password_env_file` and never appear in argv.
-
-## Rules
-
-- **Read-only.** Any `insert|update|delete|drop|truncate|alter|create|grant|
-  revoke|vacuum|copy` is rejected with exit 3. Do not work around it.
-- **PII.** `cs_brain` holds client data. Aggregate and count freely; never copy
-  names or addresses into chat, issues or docs.
-- Use `-l` to keep samples small. Twenty rows answer most questions.

skills/postgres/SKILL.md

@@ -0,0 +1,39 @@
+---
+name: postgres
+description: >-
+  Read Postgres as compact YAML through bin/postgres/query.go (read-only
+  guard, named profiles). Use when a task needs table contents, column types,
+  or a SELECT against an ops database.
+---
+
+# postgres
+
+`bin/postgres/query.go` wraps vendored `bin/db/psql-yq`. Output is YAML
+(cheaper than psql ASCII, easy to slice with `yq`).
+
+```bash
+bin/postgres/query.go --profile onlyoffice -s document_asset   # column list
+bin/postgres/query.go --profile onlyoffice -t task_result -l 20  # sample rows
+bin/postgres/query.go --profile onlyoffice -c 'SELECT ...'     # query → YAML
+```
+
+Ad-hoc targets without a profile:
+
+```bash
+bin/postgres/query.go --container my-pg --db app -c 'SELECT 1'
+bin/postgres/query.go --dsn 'postgres://user@host:5432/db' -c 'SELECT 1'
+```
+
+## Profiles
+
+Connection details live in `$HOME/.config/brain/db-profiles.yml` (mode 600),
+never in a project repo. A profile names either a `container` or a `host`;
+passwords are read from a separate `password_env_file` and never appear in argv.
+
+## Rules
+
+- **Read-only.** Any `insert|update|delete|drop|truncate|alter|create|grant|
+  revoke|vacuum|copy` is rejected with exit 3. Do not work around it.
+- **PII.** Client CRM databases: aggregate and count freely; never copy names
+  or addresses into chat, issues or docs.
+- Use `-l` to keep samples small. Twenty rows answer most questions.