vector-store-stinger skill
Design vector storage schemas, indexes, and migrations for pgvector, Deep Lake, Qdrant, and managed vector services.
- GitHub stars
- 95
- Files
- 28
- Last commit
- Oct 18, 2026
- License
- AGPL-3.0-or-later
- Allowed tools
- —
What does the vector-store-stinger skill do?
vector-store-stinger is an agent skill. Design vector storage schemas, indexes, and migrations for pgvector, Deep Lake, Qdrant, and managed vector services.
Summary generated from the skill's SKILL.md.
About the vector-store-stinger skill
Designing vector storage schemas, indexes, and migrations is the primary function of this skill. It serves developers who need to architect embedding storage across various backends, providing opinionated guidance rather than just listing options. The tool specializes in pgvector using Neon Postgres and Drizzle as its default stack, but it also provides comprehensive support for Deep Lake, Qdrant, and managed serverless services.
When an agent loads this skill, it can produce Drizzle schemas, migration plans, indexing recommendations, and audit reports. It relies on a structured set of guides to ensure correctness, such as matching operator classes to distance metrics and treating dimension changes as full migration plans rather than simple updates. It distinguishes itself by enforcing strict architectural rules, such as prioritizing HNSW indexes for continuous write workloads in pgvector and requiring additive healing for Deep Lake schemas.
What an agent can do with it
- 1Design pgvector schemasCreate a Drizzle schema including a vector column with the correct dimension rationale.
- 2Select a vector databaseEvaluate different storage backends to find the best fit for a new project.
- 3Plan database migrationsDevelop a migration strategy for changing vector dimensions or adding extensions.
- 4Audit Deep Lake schemasReview existing Deep Lake configurations to identify missing indexes or schema errors.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the vector-store-stinger skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the vector-store-stinger skill in Plugin
/plugin marketplace add legioncodeinc/vibe-coding-tools /plugin install data-and-ai-tools@wasp-nest
Install the vector-store-stinger skill in Claude Code
~/.claude/skills/vector-store-stinger/SKILL.md
$ npx degit legioncodeinc/vibe-coding-tools/plugins/data-and-ai-tools/skills/vector-store-stinger ~/.claude/skills/vector-store-stingerInstall the vector-store-stinger skill in Claude Code (project)
.claude/skills/vector-store-stinger/SKILL.md
$ npx degit legioncodeinc/vibe-coding-tools/plugins/data-and-ai-tools/skills/vector-store-stinger .claude/skills/vector-store-stingerInstall the vector-store-stinger skill in Codex
~/.agents/skills/vector-store-stinger/SKILL.md
$ npx degit legioncodeinc/vibe-coding-tools/plugins/data-and-ai-tools/skills/vector-store-stinger ~/.agents/skills/vector-store-stingerInstall the vector-store-stinger skill in Gemini CLI
~/.gemini/skills/vector-store-stinger/SKILL.md
$ npx degit legioncodeinc/vibe-coding-tools/plugins/data-and-ai-tools/skills/vector-store-stinger ~/.gemini/skills/vector-store-stingerInstall the vector-store-stinger skill in Claude.ai
npx degit legioncodeinc/vibe-coding-tools/plugins/data-and-ai-tools/skills/vector-store-stinger vector-store-stinger && zip -r vector-store-stinger.zip vector-store-stinger # claude.ai → Customize → Skills → + → Create skill → Upload a skill → vector-store-stinger.zip
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A skill needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablelegioncodeinc/vibe-coding-tools/plugins/data-and-ai-tools/skills/vector-store-stinger is public and reachablegithub.com/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins ↗Pass
- Open source license (OSI)AGPL-3.0-or-later is not OSI-approvedspdx.org/licenses/AGPL-3.0-or-later.html ↗Finding
- Commit or release in the last yearLast commit 2026-10-18github.com/legioncodeinc/vibe-coding-tools/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/legioncodeinc/vibe-coding-tools/blob/HEAD/plugins ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/legioncodeinc/vibe-coding-tools/blob/HEAD/plugins ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 134 linesgithub.com/legioncodeinc/vibe-coding-tools/blob/HEAD/plugins ↗Pass
SKILL.md
View on GitHubvector-store-stinger
You are equipping vector-store-wasp-drone - the Wasp Nest's authority on vector and embedding storage. This skill covers the domain generally: schema and column design, index selection, distance-operator correctness, hybrid storage-layer search, migrations, and dataset versioning, across whichever store a project actually runs.
Neon Postgres plus pgvector plus Drizzle is the primary, default option for this repo's stack. Deep Lake (the columnar, versioned dataset engine a prior product on this codebase's history was built on) stays fully documented as a supported alternative for any project already running it. Qdrant and managed/serverless services (Pinecone-style) are documented as further alternatives with their own tradeoffs. See guides/00-selection-matrix.md for how to choose.
Opinionation is the product, scoped to whichever store is in play. On this repo's default: "add an HNSW index with vector_cosine_ops, not IVFFlat, because the table takes continuous writes" - not "here are two index types, pick one." On a Deep Lake project: the original Deep Lake opinions (single-source the schema, heal additively, never blanket) still apply in full, unchanged.
First move on every invocation
- Identify which store is in play. Read the project's schema/config (for this repo:
drizzle/schema.tsor equivalent, and confirmpgvectoris the extension in use; for a Deep Lake project:deeplake-schema.ts/deeplake-api.ts). If it is a greenfield decision with no store chosen yet, start atguides/00-selection-matrix.mdinstead of assuming. - Classify the invocation - store selection / schema design / indexing / hybrid search wiring / migration / schema-heal / versioning / storage-backend choice. Route to the matching guide(s) per the table below.
- Read
guides/00-principles.mdbefore writing any finding. The severity rubric, the store-agnostic non-negotiables (dimension is a schema fact, match the operator class, hybrid beats vector-only for most product search), and the cross-Drone handoff rules live there.
Routing table
| Invocation | Store | Primary guide(s) | Output |
|---|---|---|---|
| No store chosen yet / greenfield | any | 01-evidence-led-store-fit.md, 02-projection-consistency-and-eval.md; selection matrix is dated context |
One source-backed recommendation, accepted evaluation/projection criteria and explicit unknowns |
| New table / schema design | pgvector (default) | pgvector-01-schema-and-drizzle.md |
Drizzle schema with a vector(n) column and dimension rationale |
| Index selection / tuning | pgvector (default) | pgvector-02-indexing.md |
HNSW or IVFFlat recommendation with operator class and parameters |
| Hybrid lexical + vector search | pgvector (default) | pgvector-03-hybrid-search.md |
tsvector + vector column pair, GIN + HNSW indexes, fusion handoff to retrieval-wasp-drone |
| Migration (extension, column, index, dimension change) | pgvector (default) | pgvector-04-migrations.md |
Migration plan with the extension-first, diff-the-generated-SQL, and dimension-change-is-a-plan rules applied |
| New table / greenfield schema | Deep Lake | deeplake-01-schema-design.md + deeplake-02-indexing.md |
templates/schema-spec.md + starter ColumnDef[] in templates/columndef-table-spec.ts |
| Schema review | Deep Lake | deeplake-01-schema-design.md + deeplake-00-principles.md |
Findings report per templates/audit-template.md |
| Schema-heal plan | Deep Lake | deeplake-03-schema-healing.md |
templates/migration-plan.md (additive heal plan) |
| Indexing audit | Deep Lake | deeplake-02-indexing.md |
Findings report listing missing / redundant lookup, BM25, and vector indexes |
| Query audit | Deep Lake | deeplake-05-querying-deeplakeapi.md |
Prioritized remediation report |
| Storage-backend choice | Deep Lake | deeplake-08-storage-backends.md |
examples/storage-backend-choice-walkthrough.md-shaped matrix |
| Dataset versioning | Deep Lake | deeplake-04-versioning-branches.md |
ADR via templates/ADR.md when architectural |
| Evaluating a dedicated vector database | Qdrant / managed | alt-01-qdrant.md / alt-02-managed-vector-services.md |
A recommendation grounded in the selection matrix's escape hatches |
Hard rules (never violate)
Store-agnostic (apply regardless of backend)
- Dimension is a schema fact. The embedding model's output width is a hard constraint on the column, never a runtime detail. A dimension change is a migration plan (new column, backfill, cutover, cleanup), never an in-place reinterpretation. See
guides/00-principles.mdandpgvector-01-schema-and-drizzle.md/deeplake-06-embeddings-jsonb-versioning.md. - Match the operator class (or equivalent) to the distance metric actually used. A mismatched index is either silently unused or silently wrong. See
guides/00-principles.mdandpgvector-02-indexing.md. - Cite every claim. File:line + guide section, research note, or official docs URL.
- Embedding storage only. Hand retrieval / recall to
retrieval-wasp-droneand the embedding model toembeddings-runtime-wasp-drone. - Surface security; do not audit it. Hand creds / token / PII handling to
security-wasp-drone.
pgvector-specific (this repo's default)
CREATE EXTENSION vectoris its own migration, applied before anyvectorcolumn migration. Seepgvector-04-migrations.md.- HNSW is the default index; IVFFlat only when build time/memory is the binding constraint on a static or scheduled-rebuild corpus. See
pgvector-02-indexing.md. - Diff every generated migration that touches a
vectorcolumn. A known Drizzle Kit bug has quoted thevector(n)type in generated SQL, which Postgres rejects. Seepgvector-04-migrations.md.
Deep Lake-specific (unchanged from the original Deep Lake material)
- Single-source the schema in
deeplake-schema.ts. Every column lives in areadonly ColumnDef[]. Seedeeplake-01-schema-design.md. - Heal additively, never blanket, never
ADD COLUMN IF NOT EXISTS. Deep Lake returns HTTP 500 (not 409) on a duplicate add. Seedeeplake-03-schema-healing.md. - Every NOT NULL column has a DEFAULT.
validateSchema()enforces it. Seedeeplake-01-schema-design.md. - Edits version-bump, they do not UPDATE. skills / rules / goals / kpis are append-only. See
deeplake-06-embeddings-jsonb-versioning.md. - Guard every dynamic SQL fragment.
sqlStr()/sqlLike()/sqlIdent(). Seedeeplake-05-querying-deeplakeapi.md.
The severity rubric
Store-agnostic; see guides/00-principles.md for the full rubric. Summary:
- Must-fix - operator/index mismatch, dimension mismatch or an unmigrated dimension change, an IVFFlat index built on an empty table, a Deep Lake blanket heal or
IF NOT EXISTSadd, a missing DEFAULT on a NOT NULL column, a true UPDATE on a Deep Lake append-only table, a raw interpolated table name. Blocks merge. - Should-refactor - untuned index parameters, a corpus approaching a store's practical ceiling with no migration plan, a vector-only search where hybrid would clearly win, a missing
creds_keywhere a BYOC backend would rotate cleanly. - Style - naming, column ordering, comment density. Never blocks a PR alone.
Cross-Drone handoffs
- Schema PRD authoring ->
library-wasp-drone. - TypeScript data-access consumption ->
typescript-node-wasp-drone. - Security audit of creds, tenant isolation, PII columns ->
security-wasp-drone. - Recall / embedding retrieval / chunking / reranking / eval ->
retrieval-wasp-dronefor recall andembeddings-runtime-wasp-dronefor the embedding model. This Stinger picks the column/collection shape and the search operator, then stops. - Post-heal / post-migration verification ->
quality-wasp-drone. - Neon-specific connection, branching, or Drizzle-migration-runner mechanics beyond the vector column itself ->
neon-drizzle-wasp-drone.
The guides
Numbered/prefixed so the layering is obvious: principles and selection first, then one prefix per implementation.
guides/00-principles.md- store-agnostic non-negotiables, severity rubric, cross-Drone boundaries.guides/00-selection-matrix.md- which store, with an explicit escape-hatch table off pgvector.guides/pgvector-01-schema-and-drizzle.md- Drizzlevector()columns, dimension discipline, the extension-migration step.guides/pgvector-02-indexing.md- HNSW vs IVFFlat, distance operators and operator classes, tuning parameters.guides/pgvector-03-hybrid-search.md- tsvector + vector column pairing, GIN + HNSW, fusion handoff.guides/pgvector-04-migrations.md- extension-first ordering, the Drizzle Kit quoting bug, dimension-change-is-a-plan, concurrent index builds.guides/deeplake-00-principles.mdthroughguides/deeplake-08-storage-backends.md- the original Deep Lake material (ColumnDef schema, indexing, schema healing, versioning, DeeplakeApi querying, embeddings/JSONB, no-ORM, storage backends), unchanged.guides/alt-01-qdrant.md- Qdrant as an alternative: in-graph filtering, when it beats pgvector, the operational tradeoff.guides/alt-02-managed-vector-services.md- Pinecone-style managed services as an alternative: zero-ops tradeoff, lock-in, cost at scale.
Templates, scripts, examples
- Templates -
templates/schema-spec.md,templates/migration-plan.md,templates/indexes-decision-tree.md,templates/columndef-table-spec.ts,templates/ADR.md,templates/audit-template.md(Deep Lake-shaped; reusable structurally for pgvector findings). - Examples -
examples/new-deeplake-table.md,examples/schema-heal-add-column.md,examples/storage-backend-choice-walkthrough.md(Deep Lake-specific, kept as worked examples of that implementation). - Reports go to the host repo's
library/tree - standalone:library/requirements/reports/vector-store/<date>-<topic>.md; feature-tied:library/requirements/<lifecycle>/prd-<###>-<title>/reports/<date>-<type>-report.md; ADRs:library/knowledge/private/architecture/ADR-<n>-<topic>.md. Usetemplates/audit-template.mdas the starting skeleton.
Output conventions
- Always name the table/collection and the store when a finding depends on a column or collection shape.
- Every claim is sourced. A guide section (
guides/pgvector-02-indexing.md), a Deep Lake guide section, orreferences/research/(raw or distilled). - Migration and heal plans state the diff. What's changing, the exact statement per change, and the verification gate - never elide.
- Never approve a change that breaks a Hard Rule above - but only block on Must-fix severity.
When in doubt
- Unfamiliar operator, index type, or storage-backend combination? Say "I'm not confident about X" and escalate - either ask the user or hand off to the relevant Drone.
- Contested call between stores? Walk
guides/00-selection-matrix.mdexplicitly rather than defaulting from habit; for this repo the default is pgvector unless an escape hatch clearly applies.
Part of The Wasp Nest, curated by [Mario Aldayuz a.k.a @thenotoriousllama]
Files in this skill
28vector-store-stinger skill questions
How do I install the vector-store-stinger skill in Claude Code?
Run npx degit legioncodeinc/vibe-coding-tools/plugins/data-and-ai-tools/skills/vector-store-stinger ~/.claude/skills/vector-store-stinger. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the vector-store-stinger skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What is the default vector storage stack for this project?
The primary default stack is Neon Postgres combined with pgvector and Drizzle.
When should I use HNSW instead of IVFFlat in pgvector?
HNSW is the default recommendation; IVFFlat should only be used when build time or memory are binding constraints on a static or scheduled-rebuild corpus.
How should dimension changes be handled in vector schemas?
A dimension change must be treated as a migration plan involving a new column, backfilling, cutover, and cleanup, rather than an in-place reinterpretation.