Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub…
- Stars
- 23
- Version
- v1
- Copies
- 0
Overview
Waxell rates it high risk: 7 findings, highest severity critical.
- Highest severity
- critical
- Findings
- 7
- What ran
- Static analysis
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked 2 days ago
Result
High risk Waxell rates it high risk: 7 findings, highest severity critical.
Checked with static analysis: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. Nothing was run. How the checks work
Findings (7)
critical · 1
- critical
Tells Claude to download a script and pipe it to a shell
references/hf_jobs_execution.md:9 · skill_risk:S1
high · 6
- high
Tells Claude to install unpinned packages (trackio)
SKILL.md:107 · skill_risk:S2
- high
Tells Claude to install unpinned packages (duckdb)
references/base_model_selection.md:79 · skill_risk:S2
- high
Tells Claude to install unpinned packages (wandb)
references/training_args.md:192 · skill_risk:S2
- high
Tells Claude to install unpinned packages (optuna)
references/training_args.md:251 · skill_risk:S2
- high
Tells Claude to install unpinned packages (trackio)
references/troubleshooting.md:90 · skill_risk:S2
- high
Tells Claude to install unpinned packages (bitsandbytes)
scripts/train_sentence_transformer_with_lora_example.py:70 · skill_risk:S2
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
One version so far: v1 (2.0), seen 2026-11-03.
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More productivity skills and plugins
cargogetcargohqRouter for the Cargo CLI skill bundle: load first for anything Cargo, and whenever a task spans two Cargo domains. Explains what each… High riskProductivityEngineering21
ae-generate-tracking-planthinkingaiagenticengineInteractive generation of an AE tracking plan and upload. Trigger words: 埋点方案、埋点模板、tracking plan、AE 方案生成、create tracking… Review findingsProductivityEngineering21
os-usezrongCross-platform operating system automation and screen control toolkit. Use when users need screenshots, mouse/keyboard control, visual… Review findingsProductivityResearch13
emblem-ai-agent-walletemblemcompanyConnect to EmblemVault and manage wallet-aware workflows via EmblemAI with review-first, operator-controlled actions. Supports Solana,… Review findingsProductivityResearch12