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

Embedder API

by sorryhyun in 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…

MITAuto-check passedAI & LLM Engineering

Install Embedder API

skills CLI
$ npx skills add sorryhyun/anima_lora --skill embedder-api -a claude-code

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

GitHub CLI
$ gh skill install sorryhyun/anima_lora embedder-api --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/sorryhyun/anima_lora.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/embedder-api .claude/skills/embedder-api && 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
embedder-api
GitHub stars
125
Token cost
~544 tokens
SKILL.md length
190 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

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…

  • Tasks that involve Fine-tuning
  • SKILL.md covers Namespaces, Inference is request-driven and Path anchoring — ANIMA_HOME
  • Calls uv
  • Tasks that involve Embeddings

What it does

Embedder API is an agent skill from 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 anchoring. Load before writing or editing an examples/ script, embedding the trainer in another program, or changing what animalora re-exports.

Its SKILL.md is about 540 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Fine-tuning and Embeddings. The repository describes itself as: optimized anima lora training script. The licence is MIT.

When your agent uses it

  • Tasks that involve Fine-tuning
  • Tasks that involve Embeddings

Example prompts

  • “/embedder-api”

What it can do on your machine

Read from SKILL.md and the folder at commit d3a5fc4. 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

    Shell commands in SKILL.md call:

    • uv

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

  • Network

    No URLs in SKILL.md. Its commands use uv, 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 no API keys, tokens, secrets or passwords.

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

Context cost

Embedder API loads about 544 tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 190 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~544

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from sorryhyun/anima_lora at commit d3a5fc4, republished under its MIT licence (© sorryhyun). 190 words, ~544 tokens.

Download SKILL.mdSave it as .claude/skills/embedder-api/SKILL.md (or your agent's skills folder).
name
embedder-api
description
The anima_lora programmatic façade for embedders — namespaces and lazy re-exports, the request-driven GenerationRequest inference path, adapter family from checkpoint metadata, and ANIMA_HOME path anchoring. Load before writing or editing an examples/ script, embedding the trainer in another program, or changing what anima_lora re-exports.

Programmatic API (anima_lora)

uv sync installs the repo editable, so anima_lora is importable anywhere. Runnable scripts live in examples/ (high-level flows + raw primitives); examples/README.md is the embedder guide.

Namespaces

Canonical homes are unchanged — library.inference, library.config.io, library.anima.weights, library.models.qwen_vae, library.runtime.device. anima_lora/__init__.py is a lazy (PEP 562) re-export of the curated entry points, grouped into namespaces anima_lora.{models, inference, config, training, captioning}. Pre-namespace flat names (anima_lora.generate) stay as aliases. ROOT is the repo root. anima_lora.training loads repo-root train.py by path, so AnimaTrainer etc. work from any CWD.

Inference is request-driven

Build a typed GenerationRequest (library/inference/request.py) and call .to_args(), which routes through inference.parse_args so every getattr()-read knob is populated. Long-tail method flags ride extra_argv.

Adapter family lives in the checkpoint metadata, not the call — the DiT loader merges-or-keeps-live accordingly. Prompt encoding installs two process-global strategy singletons lazily (ensure_text_strategies).

Path anchoring — ANIMA_HOME

Repo-relative model/config paths resolve against the repo home (library.env.anima_home() / resolve_under_home()), not the CWD. Set ANIMA_HOME for a relocated checkout, or override individual model paths with ANIMA_DIT / ANIMA_VAE / ANIMA_TEXT_ENCODER.

The anchor is wired at the config-loader chokepoint (library/config/io.py) and at the model-loader leaves (load_anima_model / load_vae / load_qwen3_text_encoder). New code opening a repo-relative path must call resolve_under_home().

© sorryhyun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/embedder-api of sorryhyun/anima_lora.

Open the folder on GitHubat commit d3a5fc4

Compare with similar skills

Embedder API 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.

Embedder API compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Embedder API this skillsorryhyun/anima_lora125—~544Automated safety check: PassMIT
Sentence-Transformers Training Routerhuggingface/skills11k1 repos~2.6kAutomated safety check: PassApache-2.0
Train Sentence Transformerswaybarrios/opencode-power-pack533—~2.2kAutomated safety check: PassApache-2.0
Unimoljinzhezenggroup/computational-chemistry-agent-skills1481 repos~1.5kAutomated safety check: PassLGPL-3.0-or-later
Waypoint BioK-Dense-AI/scientific-agent-skills48k2 repos~4.2kAutomated safety check: PassMIT
LLM Opsdavila7/claude-code-templates32k4 repos~2kAutomated 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

  • Train Sentence Transformers

    waybarrios/opencode-power-pack

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

    533 GitHub stars~2.2k tokensUpdated 2 days ago
    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 starsUsed in 1 repo~1.5k tokens
    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 2 repos~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.

    32k GitHub starsUsed in 4 repos~2k tokens
    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 sorryhyun/anima_lora

All 12 skills in this repo

  • Model Catalog

    sorryhyun/anima_lora

    The model catalog (library/downloads.py) — one Asset row per weight (repo, files, destination, installed probe), packs, resolve() name order, and the rule that loaders import their default paths…

    125 GitHub stars~502 tokensUpdated today
    Auto-check passed

  • Qwen21

    sorryhyun/anima_lora

    Qwen-Image-2.1 LoRA line (NOT Anima) — running cache/train through the daemon, make gui-qwen, the CacheRequest/TrainRequest flag surface and how to add a field, model-dir resolution, cache layout…

    125 GitHub stars~1.9k tokensUpdated today
    Auto-check: notes

  • Anime Tools

    sorryhyun/anima_lora

    The trainer ↔ animetools boundary — what the curation split moved out, the typed request/stage API the make targets build, the git-pin dev loop and its stale-venv trap, and the tests that guard the…

    125 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Bucketing

    sorryhyun/anima_lora

    Free-fit native-shape bucketing — the token bands per edge tier, tier choice at preprocess time, the compiledynamicseq coupling and per-tier graph budget, and why training never needs --targetres.

    125 GitHub stars~932 tokensUpdated today
    Auto-check passed

  • Captions

    sorryhyun/anima_lora

    Caption pipeline — position-clause grammar (never hand-split a caption), make caption-autotag modes, make caption-position (v2 rewrite rules and gates), and the preprocess-stage wiring for both.

    125 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Custom Nodes

    sorryhyun/anima_lora

    The ComfyUI node map — which node lives in which standalone repo vs in-tree under customnodes/, where each is symlinked, and the vendor-sync rule for the vendor/ subsets.

    125 GitHub stars~470 tokensUpdated today
    Auto-check passed

Categories

Questions about Embedder API

What does Embedder API do?

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…. Embedder API is an agent skill from 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 anchoring.

When should I use Embedder API?

Embedder API fits situations like: tasks that involve Fine-tuning; tasks that involve Embeddings.

How do I install Embedder API in Claude Code?

Run `npx skills add sorryhyun/anima_lora --skill embedder-api -a claude-code`. Or copy the skill folder (.claude/skills/embedder-api in sorryhyun/anima_lora) into .claude/skills/embedder-api in your project. Claude Code loads it when a task matches its description.

How do I install Embedder API in Codex?

Run `npx skills add sorryhyun/anima_lora --skill embedder-api -a codex`. Or copy the skill folder (.claude/skills/embedder-api in sorryhyun/anima_lora) into .agents/skills/embedder-api in your project. Codex loads it when a task matches its description.

Can I use Embedder API 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 sorryhyun/anima_lora --skill embedder-api -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/embedder-api, .gemini/skills/embedder-api, .github/skills/embedder-api and .opencode/skills/embedder-api in your project.

What does Embedder API need to run?

Going by SKILL.md and its folder, Embedder API needs the command-line tools its instructions call (uv).

Does Embedder API access the network?

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

Is Embedder API 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. Review the folder before installing.

What licence does Embedder API use?

Embedder API is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Embedder API use?

About 544 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Embedder API?

Skills that share tags, products or a category with Embedder API: Sentence-Transformers Training Router (huggingface/skills, 11k stars), Train Sentence Transformers (waybarrios/opencode-power-pack, 533 stars), Unimol (jinzhezenggroup/computational-chemistry-agent-skills, 148 stars) and Waypoint Bio (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Embedder API?

sorryhyun (a GitHub user) maintains it in sorryhyun/anima_lora, which has 125 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 8, 2026.

Source: sorryhyun/anima_lora on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.