Every HeliosDB product ships an AGENTS.md aggregate plus a .claude/skills/ catalogue. Every CLI flag, REPL meta-command, public API, and MCP tool is indexed for LLM coding agents — no README spelunking required.
The cargo install binary embeds the skill bundle. The subcommand unpacks it into ~/.claude/skills/ and ~/.codex/skills/ (or just one, if you target).
Embedded multi-model database. Skills cover overview, install, connect, schema, query, transactions, branches, time-travel, backup, vector, code-graph, graph-rag, mcp, server, deploy, observability, migrate.
cargo install heliosdb-nano
heliosdb-nano skills installProduction self-hosted. Skills span foundation, DML/DDL, ops, advanced features, security, HA/replication, AI/agent surface — in seven phases.
cargo install heliosdb-lite
heliosdb-lite skills installDistributed enterprise. Catalogue mirrors Lite plus 14-protocol-specific skills (MongoDB, Redis, Cassandra, Oracle, MSSQL, ClickHouse, Pinecone, S3, …).
cargo install heliosdb-full
heliosdb-full skills installPostgres operator playbook. Pool tuning, failover rehearsal, time-travel replay, plugin signing, OCI distribution, PG-12→17 upgrade orchestration.
cargo install heliosdb-proxy
heliosdb-proxy install skillsSKILL.md per operational domainA skill is one Markdown file scoped to one verb or workflow. The agent reads it once and knows the exact API: which command to run, which flags matter, which failure modes to look for.
# heliosdb-nano-vector / SKILL.md
## When to use
The user wants similarity search on embeddings, hybrid retrieval,
or any operation involving the VECTOR(n) column type.
## Surface
- DDL: CREATE TABLE ... embedding VECTOR(n); CREATE INDEX ... USING hnsw
- Operators: <=> (cosine), <-> (L2), <#> (inner product)
- Function: vector_search(table, query_vec, k, metric)
- REST: POST /api/vectors/search
## Minimal example
CREATE TABLE docs (id SERIAL PRIMARY KEY, embedding VECTOR(1536));
CREATE INDEX ON docs USING hnsw (embedding vector_cosine_ops);
SELECT id, embedding <=> '[0.1, 0.2, ...]' AS dist
FROM docs ORDER BY dist LIMIT 10;
## Failure modes
- Dimension mismatch → ERROR: vector dimensionality <n> != index <m>
- No index → falls back to brute-force scan (acceptable below ~10k rows)… mediocre at exploring unfamiliar APIs. Without a skill catalogue, an agent fumbles through HeliosDB the same way a new hire does. With it, the agent reads AGENTS.md and knows the verb for the task in front of it.
Each skill names a single verb — BRANCH, WITH CONTEXT, graph_bfs. No "see also" trees. Find the verb, get the API.
Every skill ends with the failure modes most likely to confuse an agent — dimension mismatches, FK in transactions, branch-aware visibility.
_index/verb-map.md normalises every CLI flag ↔ SQL function ↔ MCP tool. _index/feature-matrix.md maps cargo features to skills.
If a feature ships without a skill, it doesn't ship. Skill counts grow with every release — treat them as part of the API.
| Flag | Effect |
|---|---|
--target claude|codex|both | Default both. Where the bundle lands. |
--symlink | Symlink instead of copy. Re-running after a binary upgrade refreshes in place. |
--force | Overwrite existing heliosdb-* skill directories. Without it, prior installs are backed up to *.bak.<ts>. |
--dry-run | Print the planned actions without writing. |
Run the skills install subcommand and your agent stack catches up to the latest verb catalogue.