New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Train Sentence Transformers

by waybarrios in waybarrios/opencode-power-pack

Train or fine-tune SentenceTransformer bi-encoders, CrossEncoder rerankers, or SparseEncoder models, including losses, negatives, evaluation, distillation, LoRA, and Matryoshka.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Train Sentence Transformers

skills CLI
$ npx skills add waybarrios/opencode-power-pack --skill train-sentence-transformers -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install waybarrios/opencode-power-pack train-sentence-transformers --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/waybarrios/opencode-power-pack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/train-sentence-transformers .claude/skills/train-sentence-transformers && rm -rf skills-src

Use ~/.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/

Facts

Skill name
train-sentence-transformers
GitHub stars
534
Token cost
~2.2k tokens
SKILL.md length
803 words
Files
28 (incl. scripts, references)
Skills in repo
32
Repo updated
First seen
Licence
Apache-2.0

At a glance

Train or fine-tune SentenceTransformer bi-encoders, CrossEncoder rerankers, or SparseEncoder models, including losses, negatives, evaluation, distillation, LoRA, and Matryoshka.

  • Works in 5 steps: Identify the model type → Required reading → Defaults → …
  • Sentence-transformers training tasks
  • SKILL.md covers 1. Identify the model type, 2. Required reading, 3. Defaults and 4. Constraints the produced…, plus 2 more sections
  • Runs Python scripts from its folder; calls pip and hf; needs HF_TOKEN

What it does

Train Sentence Transformers is an agent skill from waybarrios/opencode-power-pack. Train or fine-tune SentenceTransformer bi-encoders, CrossEncoder rerankers, or SparseEncoder models, including losses, negatives, evaluation, distillation, LoRA, and Matryoshka. Use for sentence-transformers training tasks.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 29 other files, including scripts and reference files (for example `references/base_model_selection.md`, `references/dataset_formats.md` and `references/evaluators_cross_encoder.md`).

It sits in AI & LLM Engineering, covering Embeddings and Fine-tuning. The repository describes itself as: 54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more. The licence is Apache-2.0.

When your agent uses it

  • Sentence-transformers training tasks
  • Tasks that involve Embeddings
  • Tasks that involve Fine-tuning

Example prompts

  • “/train-sentence-transformers”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Identify the model type
  2. Required reading
  3. Defaults
  4. Constraints the produced script must satisfy
  5. Workflow

What it can do on your machine

Read from SKILL.md and the folder at commit 9dccb6d. 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 4 files in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • pip
    • hf

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • HF_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Train Sentence Transformers loads about 2.2k tokens when it runs, and up to ~31k if it reads all its reference files. Until then it costs about 63 tokens; SKILL.md has 803 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~31k

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 waybarrios/opencode-power-pack at commit 9dccb6d, republished under its Apache-2.0 licence (© waybarrios). 803 words, ~2,159 tokens.

Download SKILL.mdSave it as .claude/skills/train-sentence-transformers/SKILL.md (or your agent's skills folder). This skill also uses 27 other files; get the full folder from GitHub.
name
train-sentence-transformers
description
Train or fine-tune SentenceTransformer bi-encoders, CrossEncoder rerankers, or SparseEncoder models, including losses, negatives, evaluation, distillation, LoRA, and Matryoshka. Use for sentence-transformers training tasks.
license
Apache-2.0 (modified; see UPSTREAMS.json)

Train a sentence-transformers Model

This SKILL.md is a router, not a manual. It tells you which references and example scripts to load for your task. The actual content — recommended losses, evaluators, training-script structure, model selection, training-arg knobs, troubleshooting — lives in references/ and scripts/.

Do not synthesize a training script from this file alone. Open the per-type production template (scripts/train_<type>_example.py) and copy it as your starting point. The templates contain load-bearing scaffolding (autocast helper, model-card class, logger silencing list, force=True, seed, TF32, version-compatible imports, named-evaluator metric handling) that prior agent runs have repeatedly missed when rolling their own from a synthesized snippet.

1. Identify the model type

TagClassWhat it doesWhen to pick
[SentenceTransformer]SentenceTransformer (bi-encoder)Maps each input to a fixed-dim dense vectorRetrieval, similarity, clustering, classification, paraphrase mining, dedup
[CrossEncoder]CrossEncoder (reranker)Scores (query, passage) pairs jointlyTwo-stage retrieval (rerank top-100 from bi-encoder), pair classification
[SparseEncoder]SparseEncoder (SPLADE)Sparse vectors over the vocabularyLearned-sparse retrieval, inverted-index backends (Elasticsearch / OpenSearch / Lucene)

Tiebreakers when the request is ambiguous: "embedding model" / "vector search" / "similarity" → [SentenceTransformer]. "rerank" / "ranker" / "two-stage" → [CrossEncoder]. "SPLADE" / "sparse" / "inverted index" → [SparseEncoder]. If still unclear, ask.

2. Required reading

Read these in full before writing any code. Do not triage by perceived relevance.

Per-type — always required

[SentenceTransformer]

  • references/losses_sentence_transformer.md — loss-to-data-shape mapping; BatchSamplers.NO_DUPLICATES requirement for MNRL-family; Cached* ↔ gradient_checkpointing incompatibility.
  • references/evaluators_sentence_transformer.md — evaluator-to-task mapping; metric_for_best_model key construction (named vs unnamed); per-evaluator primary_metric values.
  • references/model_architectures.md — encoder vs decoder vs static vs Router pipelines; pooling rules (mean / cls / lasttoken); auto-mean-pooling behavior for fresh-start MLM bases.
  • scripts/train_sentence_transformer_example.py — production template; copy this as your starting point.

[CrossEncoder]

  • references/losses_cross_encoder.md — pointwise / pairwise / listwise / distillation; pos_weight derivation; activation_fn=Identity() mandatory for non-BCE losses (silent eval-rank collapse otherwise).
  • references/evaluators_cross_encoder.md — CrossEncoderRerankingEvaluator recipe; named-evaluator key format eval_{name}_{primary_metric}.
  • scripts/train_cross_encoder_example.py — production template; copy this as your starting point.

[SparseEncoder]

  • references/losses_sparse_encoder.md — SpladeLoss wrapper requirement; FLOPS regularizer weights; smoke-test active-dim ramp behavior.
  • references/evaluators_sparse_encoder.md — SparseNanoBEIREvaluator (English-only) and the in-domain alternative; eval_{name}_{primary_metric} key format.
  • scripts/train_sparse_encoder_example.py — production template; copy this as your starting point.
Cross-cutting — always required (regardless of task)
  • references/training_args.md — TrainingArguments knobs, precision rules (load fp32 + autocast bf16/fp16; never torch_dtype=bfloat16), warmup_steps (float) vs deprecated warmup_ratio, save_steps must be a multiple of eval_steps for load_best_model_at_end, schedulers, HPO, tracker, resume, hub-push variants.
  • references/dataset_formats.md — column-matching rules (label name auto-detection; column-order-not-name); reshaping recipes; hard-negative mining options.
  • references/base_model_selection.md — discovery commands; per-type model namespaces; ModernBERT-family max_seq_length=8192 trap; datasets >= 4 script-loader rejection; non-English starting-point shortcuts.
  • references/troubleshooting.md — symptom-indexed failure recipes. Skim the section headings on every run, even a healthy one; the "Metrics don't improve" and "Hub push fails" entries cover bugs that bite frequently and are cheaper to recognize before they fire than to debug after.
Cross-cutting — load when applicable
  • references/hardware_guide.md — VRAM sizing, multi-GPU, FSDP / DeepSpeed, HF Jobs flavors. Required for >24GB models, multi-GPU, or HF Jobs runs.
  • references/hf_jobs_execution.md — required when running on HF Jobs.
  • references/prompts_and_instructions.md — required when using prompt-tuned bases (E5, BGE, GTE, Qwen3-Embedding, Instructor, Nomic, etc.) or adding query: / passage: style prefixes.
Show full SKILL.md (325 more words)Show less
Variant scripts (open when the task matches)
  • [SentenceTransformer] scripts/train_sentence_transformer_<matryoshka|multi_dataset|with_lora|distillation|make_multilingual|static_embedding>_example.py.
  • [CrossEncoder] scripts/train_cross_encoder_<distillation|listwise>_example.py.
  • [SparseEncoder] scripts/train_sparse_encoder_distillation_example.py.
  • Hard-negative mining CLI — scripts/mine_hard_negatives.py.

3. Defaults

Override only if the user specifies otherwise:

  • Local execution. Pitch HF Jobs only if local hardware can't fit the job.
  • Single run. After it completes, propose experimentation if the user would benefit (weak/marginal verdict, "see how high you can push it" framing, etc.). Iteration rules in references/training_args.md (Experimentation section).
  • Public Hub push at end-of-run, wrapped in try-except. On HF Jobs (ephemeral env) ALSO enable in-trainer push (push_to_hub=True + hub_strategy="every_save"); details in references/hf_jobs_execution.md.

4. Constraints the produced script must satisfy

These are non-negotiable contracts. Implementation lives in the production templates and references — do not reinvent.

  • Capture the pre-training evaluator score as baseline_eval before trainer.train().
  • Emit a single end-of-run line: VERDICT: WIN|MARGINAL|REGRESSION | score=... | baseline=... | delta=.... A monitor scrapes for this.
  • Silence httpx, httpcore, huggingface_hub, urllib3, filelock, fsspec to WARNING (otherwise HF download URLs flood the agent's context).
  • Tee logs to logs/{RUN_NAME}.log.
  • End with model.push_to_hub(...) wrapped in try/except.
  • Smoke-test before any long run (max_steps=1 + tiny dataset slice). The production templates show one common pattern (SMOKE_TEST env var).
  • [CrossEncoder] Include EarlyStoppingCallback(patience>=3) — CE rerankers often peak mid-training and regress.
  • [SparseEncoder] Log query_active_dims / corpus_active_dims on the verdict line; high nDCG with collapsed sparsity is not a win. The keys come back name-prefixed (e.g. ..._query_active_dims); use suffix matching to pluck them — see the SPARSE production template for the exact pattern.

5. Workflow

  1. Identify the model type (§1). Ask if ambiguous.
  2. Load the §2 required-reading files for that type.
  3. Open scripts/train_<type>_example.py and copy it as your starting point.
  4. Replace MODEL_NAME, DATASET_NAME, RUN_NAME, the loss, and the evaluator with the user's task. Cross-check loss/data-shape match against references/losses_<type>.md; cross-check the metric_for_best_model key against references/evaluators_<type>.md (named evaluators format the key as eval_{name}_{primary_metric}).
  5. Smoke-test (max_steps=1).
  6. Run.
  7. After the run, append to logs/experiments.md and propose iteration if the verdict is weak/marginal.

Prerequisites

bash
pip install "sentence-transformers[train]>=5.0"        # add [train,image] / [audio] / [video] for [SentenceTransformer] multimodal
pip install trackio                                    # optional tracker; or wandb / tensorboard / mlflow
hf auth login                                          # or set HF_TOKEN with write scope (for Hub push)

GPU strongly recommended. CPU works only for demos and [SentenceTransformer] StaticEmbedding.

© waybarrios, 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 27 other files (scripts, references) in skills/train-sentence-transformers of waybarrios/opencode-power-pack.

  • SKILL.md
  • references/base_model_selection.md
  • references/dataset_formats.md
  • references/evaluators_cross_encoder.md
  • references/evaluators_sentence_transformer.md
  • references/evaluators_sparse_encoder.md
  • references/hardware_guide.md
  • references/hf_jobs_execution.md
  • references/losses_cross_encoder.md
  • references/losses_sentence_transformer.md
  • references/losses_sparse_encoder.md
  • references/model_architectures.md
  • references/prompts_and_instructions.md
  • references/training_args.md
  • references/troubleshooting.md
  • scripts/mine_hard_negatives.py
  • scripts/train_cross_encoder_distillation_example.py
  • scripts/train_cross_encoder_example.py
  • scripts/train_cross_encoder_listwise_example.py
  • … and 9 more

Open the folder on GitHubat commit 9dccb6d

Compare with similar skills

Train Sentence Transformers 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.

Train Sentence Transformers compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Train Sentence Transformers this skillwaybarrios/opencode-power-pack534—~2.2kAutomated safety check: PassApache-2.0
Sentence-Transformers Training Routerhuggingface/skills11k1 repos~2.6kAutomated safety check: PassApache-2.0
Unimoljinzhezenggroup/computational-chemistry-agent-skills148—~1.5kAutomated safety check: PassLGPL-3.0-or-later
Waypoint BioK-Dense-AI/scientific-agent-skills48k1 repos~4.2kAutomated safety check: PassMIT
LLM Opsdavila7/claude-code-templates33k3 repos~2kAutomated safety check: PassMIT
Embedder APIsorryhyun/anima_lora125—~544Automated safety check: PassMIT

Similar skills

  • Sentence-Transformers Training Router

    huggingface/skills

    Official

    Routes a sentence-transformers training task to the right model type and required reference docs and example scripts, covering bi-encoders, rerankers, sparse and multi-vector models.

    11k GitHub starsUsed in 1 repo~2.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Unimol

    jinzhezenggroup/computational-chemistry-agent-skills

    A standardized CLI wrapper for Uni-Mol molecular ML workflows that handles representation extraction (embeddings), model training (regression/classification), and property prediction with built-in…

    148 GitHub stars~1.5k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Waypoint Bio

    K-Dense-AI/scientific-agent-skills

    Supports work with Outpost Bio's open microbiome foundation models - the Waypoint checkpoints (Waypoint-6m, Waypoint-45m, Waypoint-170m), the Atlas pretraining corpus, the Compass eight-task…

    48k GitHub starsUsed in 1 repo~4.2k tokens
    AI & LLM EngineeringAuto-check passed

  • LLM Ops

    davila7/claude-code-templates

    LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

    33k GitHub starsUsed in 3 repos~2k tokens
    AI & LLM EngineeringAuto-check passed

  • Embedder API

    sorryhyun/anima_lora

    The animalora programmatic façade for embedders — namespaces and lazy re-exports, the request-driven GenerationRequest inference path, adapter family from checkpoint metadata, and ANIMAHOME path…

    125 GitHub stars~544 tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Gemini Live API

    google/skills

    Official

    Generates a Gemini LiveAPI client service class in the user's chosen programming language.

    21k GitHub stars~2.5k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

More from waybarrios/opencode-power-pack

All 32 skills in this repo

  • Hf Cloud Sagemaker Iam Preflight

    waybarrios/opencode-power-pack

    Verify or select a SageMaker execution role before creating models, endpoints, or training jobs.

    534 GitHub stars~1.6k tokensUpdated 4 days ago
    Auto-check passed

  • Huggingface LLM Trainer

    waybarrios/opencode-power-pack

    Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion.

    534 GitHub stars~3k tokensUpdated 4 days ago
    Auto-check passed

  • Huggingface Vision Trainer

    waybarrios/opencode-power-pack

    Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs.

    534 GitHub stars~2.7k tokensUpdated 4 days ago
    Auto-check passed

  • Codeql

    waybarrios/opencode-power-pack

    Run CodeQL database creation and security queries, add data-extension models, or process CodeQL SARIF.

    534 GitHub starsUsed in 2 repos~3.7k tokens
    Auto-check passed

  • Semgrep

    waybarrios/opencode-power-pack

    Run Semgrep static analysis across a codebase, optionally using Semgrep Pro for cross-file taint analysis.

    534 GitHub stars~2.4k tokensUpdated 4 days ago
    Auto-check passed

  • Insecure Defaults

    waybarrios/opencode-power-pack

    Detects fail-open insecure defaults (hardcoded secrets, weak auth, permissive security) that allow apps to run insecurely in production.

    534 GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check passed

Categories

Questions about Train Sentence Transformers

What does Train Sentence Transformers do?

Train or fine-tune SentenceTransformer bi-encoders, CrossEncoder rerankers, or SparseEncoder models, including losses, negatives, evaluation, distillation, LoRA, and Matryoshka. Train Sentence Transformers is an agent skill from waybarrios/opencode-power-pack. Train or fine-tune SentenceTransformer bi-encoders, CrossEncoder rerankers, or SparseEncoder models, including losses, negatives, evaluation, distillation, LoRA, and Matryoshka.

When should I use Train Sentence Transformers?

Train Sentence Transformers fits situations like: sentence-transformers training tasks; tasks that involve Embeddings; tasks that involve Fine-tuning.

How do I install Train Sentence Transformers in Claude Code?

Run `npx skills add waybarrios/opencode-power-pack --skill train-sentence-transformers -a claude-code`. Or copy the skill folder (skills/train-sentence-transformers in waybarrios/opencode-power-pack) into .claude/skills/train-sentence-transformers in your project. Claude Code loads it when a task matches its description.

How do I install Train Sentence Transformers in Codex?

Run `npx skills add waybarrios/opencode-power-pack --skill train-sentence-transformers -a codex`. Or copy the skill folder (skills/train-sentence-transformers in waybarrios/opencode-power-pack) into .agents/skills/train-sentence-transformers in your project. Codex loads it when a task matches its description.

Can I use Train Sentence Transformers 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 waybarrios/opencode-power-pack --skill train-sentence-transformers -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/train-sentence-transformers, .gemini/skills/train-sentence-transformers, .github/skills/train-sentence-transformers and .opencode/skills/train-sentence-transformers in your project.

What does Train Sentence Transformers need to run?

Going by SKILL.md and its folder, Train Sentence Transformers needs Python for the scripts in its folder, the command-line tools its instructions call (pip and hf) and credentials named HF_TOKEN. Our summary lists: Python 3.

Does Train Sentence Transformers access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Train Sentence Transformers 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 Train Sentence Transformers use?

Train Sentence Transformers 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 Train Sentence Transformers use?

About 2.2k tokens (SKILL.md is roughly 8.6k 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 29k tokens, read only when the agent opens those files.

What are the alternatives to Train Sentence Transformers?

Skills that share tags, products or a category with Train Sentence Transformers: Sentence-Transformers Training Router (huggingface/skills, 11k stars), Unimol (jinzhezenggroup/computational-chemistry-agent-skills, 148 stars), Waypoint Bio (K-Dense-AI/scientific-agent-skills, 48k stars) and LLM Ops (davila7/claude-code-templates, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Train Sentence Transformers?

waybarrios (a GitHub user) maintains it in waybarrios/opencode-power-pack, which has 534 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on October 6, 2026.

Source: waybarrios/opencode-power-pack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.