Chroma Vector Database
Orchestra-Research/AI-Research-SKILLs
Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.
A skill your agent uses for sentence-transformers CrossEncoder pair scoring, reranking, rank API usage, retrieve-and-rerank handoffs, multimodal reranker routing, and activation/softmax/numlabels…
Install Reranking Cross Encoder
$ npx skills add VectorSpaceLab/AREX-Skill --skill reranking-cross-encoder -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill reranking-cross-encoder --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder .claude/skills/reranking-cross-encoder && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "reranking-cross-encoder" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder into .claude/skills/reranking-cross-encoder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reranking-cross-encoder", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoderType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add VectorSpaceLab/AREX-Skill --skill reranking-cross-encoder -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill reranking-cross-encoder --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder .agents/skills/reranking-cross-encoder && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "reranking-cross-encoder" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder into .agents/skills/reranking-cross-encoder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reranking-cross-encoder", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill reranking-cross-encoder -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill reranking-cross-encoder --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder .cursor/skills/reranking-cross-encoder && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "reranking-cross-encoder" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder into .cursor/skills/reranking-cross-encoder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reranking-cross-encoder", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add VectorSpaceLab/AREX-Skill --skill reranking-cross-encoder -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill reranking-cross-encoder --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder .gemini/skills/reranking-cross-encoder && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "reranking-cross-encoder" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder into .gemini/skills/reranking-cross-encoder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reranking-cross-encoder", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install VectorSpaceLab/AREX-Skill reranking-cross-encoderInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add VectorSpaceLab/AREX-Skill --skill reranking-cross-encoder -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder .github/skills/reranking-cross-encoder && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "reranking-cross-encoder" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder into .github/skills/reranking-cross-encoder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reranking-cross-encoder", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill reranking-cross-encoder -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill reranking-cross-encoder --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder .opencode/skills/reranking-cross-encoder && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "reranking-cross-encoder" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder into .opencode/skills/reranking-cross-encoder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reranking-cross-encoder", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
reranking-cross-encoder- GitHub stars
- 330
- Token cost
- ~807 tokens
- SKILL.md length
- 274 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 159
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses for sentence-transformers CrossEncoder pair scoring, reranking, rank API usage, retrieve-and-rerank handoffs, multimodal reranker routing, and activation/softmax/numlabels…
- Sentence-transformers CrossEncoder pair scoring
- SKILL.md covers Route Here For, Route Elsewhere, Fast Pattern and Essential References, plus 1 more section
- Runs Python scripts from its folder
- Retrieve-and-rerank handoffs
What it does
Reranking Cross Encoder is an agent skill from VectorSpaceLab/AREX-Skill. Use for sentence-transformers CrossEncoder pair scoring, reranking, rank API usage, retrieve-and-rerank handoffs, multimodal reranker routing, and activation/softmax/numlabels pitfalls.
Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/api-reference.md`, `references/troubleshooting.md` and `references/workflows.md`).
It sits in AI & LLM Engineering, covering Retrieval-augmented generation and Embeddings. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is Apache-2.0.
When your agent uses it
- Sentence-transformers CrossEncoder pair scoring
- Retrieve-and-rerank handoffs
- Multimodal reranker routing
- Activation/softmax/numlabels pitfalls
Example prompts
- “/reranking-cross-encoder”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Reranking Cross Encoder loads about 807 tokens when it runs, and up to ~5.7k if it reads all its reference files. Until then it costs about 53 tokens; SKILL.md has 274 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its Apache-2.0 licence (© VectorSpaceLab). 274 words, ~807 tokens.
Download SKILL.mdSave it as
.claude/skills/reranking-cross-encoder/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- reranking-cross-encoder
- description
- Use for sentence-transformers CrossEncoder pair scoring, reranking, rank API usage, retrieve-and-rerank handoffs, multimodal reranker routing, and activation/softmax/num_labels pitfalls.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- Apache 2.0
Reranking Cross Encoder
Use this sub-skill when the task is about scoring input pairs with CrossEncoder, reranking an already-retrieved candidate list, choosing between a reranker and a bi-encoder, or debugging CrossEncoder predict/rank outputs.
Route Here For
- Pair scoring with
CrossEncoder.predict, including single pair vs batch-of-pairs shape decisions. - Reranking an existing list of candidate documents with
CrossEncoder.rank,top_k,return_documents, stablecorpus_idhandling, batching, prompts, and device placement. - Choosing a CrossEncoder reranker over a bi-encoder when accuracy on a limited candidate set matters more than precomputed embeddings or high-throughput first-stage retrieval.
- Regression reranker vs pair-classification setup, especially
num_labels,activation_fn, andapply_softmaxbehavior. - Multimodal reranker routing for text-image/audio/video-capable CrossEncoder checkpoints.
Route Elsewhere
- First-stage dense retrieval,
semantic_search, hard-negative mining, quantized embeddings, and vector database orchestration belong in../retrieval-and-utilities/SKILL.md. - Detailed loss/evaluator/trainer selection belongs in
../evaluation-and-training/SKILL.md. - ONNX/OpenVINO export and backend optimization belong in
../backend-export-optimization/SKILL.md. - Dense
SentenceTransformer.encodeembeddings and similarity belong in../embeddings-and-similarity/SKILL.md.
Fast Pattern
from sentence_transformers import CrossEncoder
model = CrossEncoder("cross-encoder/ms-marco-MiniLM-L6-v2")
query = "How many people live in Berlin?"
documents = [
"Berlin had 3,520,031 registered inhabitants.",
"Berlin is well known for its museums.",
]
results = model.rank(query, documents, top_k=2, return_documents=True)rank returns dictionaries sorted by descending score. Each result includes corpus_id from the input documents list, score, and text when return_documents=True.
Essential References
- API details:
references/api-reference.md - Reranking workflows:
references/workflows.md - Failure diagnosis:
references/troubleshooting.md - Safe CLI smoke helper:
scripts/cross_encoder_rerank_smoke.py --help
Ground Rules
- CrossEncoders score pairs jointly; they do not create reusable document embeddings.
rankis for single-label rerankers (num_labels == 1); usepredictfor multi-class pair classifiers.- Preserve stable corpus IDs by reranking the exact candidate list order and mapping
corpus_idback to first-stage hits. - For MS MARCO-style rerankers, raw logits may be unbounded; pass
activation_fn=torch.nn.Sigmoid()if the downstream consumer needs 0-1 scores. Ranking order is usually unchanged by monotonic activations. - Do not make the reranker retrieve the whole corpus. Retrieve top candidates first, then rerank only that shortlist.
© VectorSpaceLab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts, references) in skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/api-reference.md
- references/troubleshooting.md
- references/workflows.md
- scripts/cross_encoder_rerank_smoke.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Reranking Cross Encoder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Reranking Cross Encoder this skillVectorSpaceLab/AREX-Skill | 330 | — | ~807 | Automated safety check: Pass | Apache-2.0 | |
| Chroma Vector DatabaseOrchestra-Research/AI-Research-SKILLs | 13k | 7 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Ms Agent Framework RAGshuyu-labs/WebCode | 278 | — | ~1.1k | Automated safety check: Pass | Custom licence | |
| Evaluate RAGai-evals-course/evals-skills | 1.5k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Pgvector Semantic Searchtimescale/pg-aiguide | 1.9k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | |
| Memory Upgradeprofbernardoj/everclaw-community-branches | 112 | — | ~574 | Automated safety check: Pass | MIT |
Similar skills
Ms Agent Framework RAG
shuyu-labs/WebCode
Comprehensive guide for building Agentic RAG systems using Microsoft Agent Framework in C.
Evaluate RAG
ai-evals-course/evals-skills
Guides evaluation of a RAG system by diagnosing failures in traces, building a retrieval test set and scoring retrieval and generation separately.
Pgvector Semantic Search
timescale/pg-aiguide
A skill your agent uses for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search.
Memory Upgrade
profbernardoj/everclaw-community-branches
Diagnose and fix broken memory search in OpenClaw. An agent skill from profbernardoj/everclaw-community-branches.
Embedding Strategies
wshobson/agents
Helps choose and tune embedding models for semantic search and RAG: model comparison, chunking, preprocessing, normalization and caching.
More from VectorSpaceLab/AREX-Skill
All 159 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents And Middleware
VectorSpaceLab/AREX-Skill
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
Related
Categories
Questions about Reranking Cross Encoder
What does Reranking Cross Encoder do?
A skill your agent uses for sentence-transformers CrossEncoder pair scoring, reranking, rank API usage, retrieve-and-rerank handoffs, multimodal reranker routing, and activation/softmax/numlabels…. Reranking Cross Encoder is an agent skill from VectorSpaceLab/AREX-Skill. Use for sentence-transformers CrossEncoder pair scoring, reranking, rank API usage, retrieve-and-rerank handoffs, multimodal reranker routing, and activation/softmax/numlabels pitfalls.
When should I use Reranking Cross Encoder?
Reranking Cross Encoder fits situations like: sentence-transformers CrossEncoder pair scoring; retrieve-and-rerank handoffs; multimodal reranker routing; activation/softmax/numlabels pitfalls.
How do I install Reranking Cross Encoder in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill reranking-cross-encoder -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder in VectorSpaceLab/AREX-Skill) into .claude/skills/reranking-cross-encoder in your project. Claude Code loads it when a task matches its description.
How do I install Reranking Cross Encoder in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill reranking-cross-encoder -a codex`. Or copy the skill folder (skills/repositories/repo-skills/sentence-transformers/sub-skills/reranking-cross-encoder in VectorSpaceLab/AREX-Skill) into .agents/skills/reranking-cross-encoder in your project. Codex loads it when a task matches its description.
Can I use Reranking Cross Encoder in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VectorSpaceLab/AREX-Skill --skill reranking-cross-encoder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reranking-cross-encoder, .gemini/skills/reranking-cross-encoder, .github/skills/reranking-cross-encoder and .opencode/skills/reranking-cross-encoder in your project.
What does Reranking Cross Encoder need to run?
Going by SKILL.md and its folder, Reranking Cross Encoder needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Reranking Cross Encoder access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Reranking Cross Encoder safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Reranking Cross Encoder use?
Reranking Cross Encoder is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Reranking Cross Encoder use?
About 807 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.9k tokens, read only when the agent opens those files.
What are the alternatives to Reranking Cross Encoder?
Skills that share tags, products or a category with Reranking Cross Encoder: Chroma Vector Database (Orchestra-Research/AI-Research-SKILLs, 13k stars), Ms Agent Framework RAG (shuyu-labs/WebCode, 278 stars), Evaluate RAG (ai-evals-course/evals-skills, 1.5k stars) and Pgvector Semantic Search (timescale/pg-aiguide, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Reranking Cross Encoder?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 330 GitHub stars. The repository holds 159 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.