sqlite-vec-skilld
- Repo stars 275
- Author updated Live
- Author repo skilld
- Domain
- Writing
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @skilld-dev · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- macOS · Linux · Windows
- Runtime requirements
- Python
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: sqlite-vec-skilld
description: ALWAYS use when writing code importing \"sqlite-vec\". Consult for debugging, best practices, or…
category: writing
runtime: Python
---
# sqlite-vec-skilld output preview
## PART A: Task fit
- Use case: ALWAYS use when writing code importing \"sqlite-vec\". Consult for debugging, best practices, or modifying sqlite-vec, sqlite vec. Use skilld search instead of grepping .skilld/ directories — hybrid semantic + keyword search across all indexed docs, issues, and releases. If skilld is unavailable, use npx -y skilld search. runs entirely locally; runs on Py….
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Search / API Changes / Best Practices” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “ALWAYS use when writing code importing \"sqlite-vec\". Consult for debugging, best practices, or modifying sqlite-vec, sqlite vec. Use skilld search instead of grepping .skilld/ directories — hybrid semantic + keyword search across all indexed docs, issues, and releases. If skilld is unavailable, use npx -y skilld search. runs entirely locally; runs on Py…”.
- **02** When the source has headings, the agent prioritizes “Search / API Changes / Best Practices” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source mentions slash commands such as `/skilld`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “Search / API Changes / Best Practices”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: sqlite-vec-skilld
description: ALWAYS use when writing code importing \"sqlite-vec\". Consult for debugging, best practices, or…
category: writing
source: skilld-dev/skilld
---
# sqlite-vec-skilld
## When to use
- ALWAYS use when writing code importing \"sqlite-vec\". Consult for debugging, best practices, or modifying sqlite-vec…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Search / API Changes / Best Practices” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "sqlite-vec-skilld" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Search / API Changes / Best Practices
rules -> SKILL.md triggers / order / output contract
runtime -> Python | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}asg017/sqlite-vec sqlite-vec
Version: 0.1.7 Tags: latest: 0.1.7, alpha: 0.1.7-alpha.13
References: package.json — exports, entry points • README — setup, basic usage • Docs — API reference, guides • GitHub Issues — bugs, workarounds, edge cases • Releases — changelog, breaking changes, new APIs
Search
Use skilld search instead of grepping .skilld/ directories — hybrid semantic + keyword search across all indexed docs, issues, and releases. If skilld is unavailable, use npx -y skilld search.
skilld search "query" -p sqlite-vec
skilld search "issues:error handling" -p sqlite-vec
skilld search "releases:deprecated" -p sqlite-vecFilters: docs:, issues:, releases: prefix narrows by source type.
API Changes
This section documents version-specific API changes — prioritize recent major/minor releases.
BREAKING: DELETE operations now properly clear vector data and free space — v0.1.7 changed behavior from only setting validity bits. Code using DELETE statements may see different storage behavior source
NEW: Distance column constraints in KNN queries — v0.1.7 adds support for
>,>=,<,<=constraints on the distance column, enabling pagination-like patterns without requiring large k values sourceNEW: Metadata columns in vec0 virtual tables — v0.1.6 added ability to declare metadata columns that can be filtered in WHERE clauses of KNN queries alongside vector matching source
NEW: Partition keys for internal index sharding — v0.1.6 added
partition keysyntax to internally shard vector indexes by column values sourceNEW: Auxiliary columns with
+prefix — v0.1.6 added support for auxiliary columns (prefix with+) that are unindexed but available for fast lookups in KNN query results sourceBREAKING:
vec_npy_eachtable function removed from default entrypoint — v0.1.3 moved this experimental function out due to CVE-2024-46488 security mitigation; affected code using untrusted SQL or the rarevec_npy_eachfunction source
Also changed: Static linking support for SQLite 3.31.1+ · serialize_float32() / serialize_int8() Python functions added
Best Practices
Use two-column re-scoring pattern for binary quantization — store both quantized and full-precision vectors; query coarse index with quantized vectors, then re-score top candidates with full precision to recover quality lost from extreme dimensionality reduction source
Combine
vec_slice()withvec_normalize()for Matryoshka embeddings — truncating dimensions requires subsequent normalization to maintain embedding quality and semantic meaning sourcePrefer scalar quantization over binary quantization for moderate storage savings — trade off storage efficiency against quality loss;
vec_quantize_float16(2 bytes per value) andvec_quantize_int8(1 byte per value) offer better quality retention than binary quantization for many use cases sourceUse partition keys to shard large vector datasets — declare a
partition keycolumn inCREATE VIRTUAL TABLEto internally shard the vector index on that column, improving query performance by reducing search scope sourceCombine metadata columns (indexed) with auxiliary columns (unindexed) for efficient filtering — use regular metadata columns for dimensions you filter on in KNN WHERE clauses; prefix columns with
+to store related data without indexing overhead sourceUse distance constraints instead of oversampling for pagination — as of v0.1.7, apply
distance > thresholdordistance < thresholdconstraints in WHERE clauses to paginate through KNN results without fetching excess candidates sourceMonitor the k value limit when performing large KNN queries — the default maximum k is 4096 (configurable) to prevent memory exhaustion; be aware that kNN results are materialized in memory and internally use O(n²) complexity on k source
Rely on v0.1.7+ for automatic DELETE cleanup — vector space is now reclaimed when enough vectors are deleted to clear a chunk (~1024 vectors); previous versions only marked entries as deleted without freeing space source
Select embedding models with quantization support for better results — models like
nomic-embed-text-v1.5,mxbai-embed-large-v1, and OpenAI'stext-embedding-3are specifically trained to maintain quality after quantization and Matryoshka truncation source
Decide Fit First
Design Intent
How To Use It
Boundaries And Review