build(ci): uv toolchain, release-please semver; feat(skills): vendor tools self-contained (no symlinks, relative refs)

- bin/db/psql-yq + bin/web/search + tools/{yamlout,websearch} vendored as real files
- bin/db/ssh-tunnel added (OnlyOffice VM pg on 5433)
- skills reference local bin/ paths; no agent-skills/abs links in git
- pyproject.toml + uv.lock; CI installs via uv sync --frozen
- release-please auto-tags semver from conventional commits when green
- LICENSE MIT, badges/mermaid README

skills/agent-cost/SKILL.md

@@ -9,10 +9,10 @@ description: >-
 # agent-cost
 
 ```bash
-bin/agents/cost                       # every project, YAML
-bin/agents/cost --repo brain-ui   # only sessions whose cwd matches
+bin/agents/cost                        # every project, YAML
+bin/agents/cost --repo 2dph            # only sessions whose cwd matches
 bin/agents/cost --json | jq .cursor.by_tool
-bin/agents/cost --snapshot after-x --repo brain-ui   # append a row to docs/CONTEXT-BUDGET.md
+bin/agents/cost --snapshot after-x --repo 2dph   # append a row to docs/CONTEXT-BUDGET.md
 ```
 
 Reads local session storage from OpenCode and Cursor transcripts. Reports the

skills/db-yaml/SKILL.md

@@ -8,21 +8,20 @@ description: >-
 
 # db-yaml
 
-`agent-skills/bin/db/psql-yq` talks to Postgres and returns YAML, which is far
-cheaper than a psql ASCII table and easy to slice with `yq`.
+`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/offline -s kunde              # column list          (brain-ui wrapper)
-bin/db/offline -t tour -l 20         # 20 sample rows as YAML
-bin/db/offline -c 'SELECT ...'       # query -> YAML
-bin/db/live -c 'SELECT ...'          # live database instead of the snapshot
+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
-agent-skills/bin/db/psql-yq --container my-pg --db app -c 'SELECT 1'
-agent-skills/bin/db/psql-yq --dsn 'postgres://user@host:5432/db' -c 'SELECT 1'
+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

skills/diataxis-docs/SKILL.md

@@ -34,8 +34,8 @@ related:
 becomes a graph edge:
 
 ```bash
-bin/kb/search search "deploy" --type howto
-bin/kb/search search "Stecktafel" --hop 1     # follow links and related
+bin/kb/search "deploy" --type howto
+bin/kb/search "Stecktafel" --hop 1     # follow links and related
 ```
 
 ## Audit checklist

skills/web-search/SKILL.md

@@ -10,17 +10,17 @@ description: >-
 # web-search
 
 ```bash
-bin/web/search "Pflegegrad SGB XI Einstufung"
-bin/web/search "Toureffizienz" --site ticket.detective.de
-bin/web/search "sqlite-vec" --category it -n 3 --json | jq -r '.results[].url'
-bin/web/search "Pflegereform" --lang de --fresh year
+bin/web/search "LadybugDB vector index"
+bin/web/search "model2vec multilingual" --category it
+bin/web/search "hypervisor" --site ops.io --json | jq -r '.results[].url'
+bin/web/search "postgres partial index" --lang en --fresh year
 ```
 
 ## Web or knowledge base
 
-`bin/kb/search` holds our own facts: product docs, detective business logic, the
+`bin/kb/search` holds our own facts: the ops stack, portfolio, ssh hosts, the
 lexicon. Go there first. Reach for `bin/web/search` when the answer is outside
-our repos: legislation, vendor documentation, upstream library behaviour.
+our repos: upstream library behaviour, vendor documentation, public standards.
 
 Keep the two apart. A finding is stronger when the reader can see that one
 source was ours and one was not.