LLM Router
curiositech/some_claude_skills
Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements.
Local TensorZero documentation reference (latest). An agent skill from olorehq/olore.
$ npx skills add olorehq/olore --skill olore-tensorzero-latest -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install olorehq/olore olore-tensorzero-latest --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/olorehq/olore.git skills-src && mkdir -p .claude/skills && cp -r skills-src/vault/packages/tensorzero/latest .claude/skills/olore-tensorzero-latest && 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 "olore-tensorzero-latest" agent skill from https://github.com/olorehq/olore/tree/main/vault/packages/tensorzero/latest into .claude/skills/olore-tensorzero-latest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "olore-tensorzero-latest", 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/olorehq/olore/tree/main/vault/packages/tensorzero/latestType 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 olorehq/olore --skill olore-tensorzero-latest -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install olorehq/olore olore-tensorzero-latest --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/olorehq/olore.git skills-src && mkdir -p .agents/skills && cp -r skills-src/vault/packages/tensorzero/latest .agents/skills/olore-tensorzero-latest && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "olore-tensorzero-latest" agent skill from https://github.com/olorehq/olore/tree/main/vault/packages/tensorzero/latest into .agents/skills/olore-tensorzero-latest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "olore-tensorzero-latest", 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 olorehq/olore --skill olore-tensorzero-latest -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install olorehq/olore olore-tensorzero-latest --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/olorehq/olore.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/vault/packages/tensorzero/latest .cursor/skills/olore-tensorzero-latest && 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 "olore-tensorzero-latest" agent skill from https://github.com/olorehq/olore/tree/main/vault/packages/tensorzero/latest into .cursor/skills/olore-tensorzero-latest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "olore-tensorzero-latest", 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/olorehq/olore.git --path vault/packages/tensorzero/latest--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 olorehq/olore --skill olore-tensorzero-latest -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install olorehq/olore olore-tensorzero-latest --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/olorehq/olore.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/vault/packages/tensorzero/latest .gemini/skills/olore-tensorzero-latest && 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 "olore-tensorzero-latest" agent skill from https://github.com/olorehq/olore/tree/main/vault/packages/tensorzero/latest into .gemini/skills/olore-tensorzero-latest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "olore-tensorzero-latest", 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 olorehq/olore olore-tensorzero-latestInstalls 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 olorehq/olore --skill olore-tensorzero-latest -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/olorehq/olore.git skills-src && mkdir -p .github/skills && cp -r skills-src/vault/packages/tensorzero/latest .github/skills/olore-tensorzero-latest && 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 "olore-tensorzero-latest" agent skill from https://github.com/olorehq/olore/tree/main/vault/packages/tensorzero/latest into .github/skills/olore-tensorzero-latest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "olore-tensorzero-latest", 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 olorehq/olore --skill olore-tensorzero-latest -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install olorehq/olore olore-tensorzero-latest --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/olorehq/olore.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/vault/packages/tensorzero/latest .opencode/skills/olore-tensorzero-latest && 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 "olore-tensorzero-latest" agent skill from https://github.com/olorehq/olore/tree/main/vault/packages/tensorzero/latest into .opencode/skills/olore-tensorzero-latest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "olore-tensorzero-latest", 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.
olore-tensorzero-latestLocal TensorZero documentation reference (latest). An agent skill from olorehq/olore.
Olore Tensorzero Latest is an agent skill from olorehq/olore. Local TensorZero documentation reference (latest). TensorZero documentation. Use for LLM gateway configuration, inference API, model provider integrations, optimization (fine-tuning, DICL), experimentation, evaluations, deployment, and observability.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 95 other files (for example `TOC.md`).
It sits in AI & LLM Engineering, covering Model routing and gateways, A/B testing and Fine-tuning. It works with OpenAI. The repository describes itself as: Turn library docs into local Agent Skills. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 430d86c. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Olore Tensorzero Latest loads about 1.6k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 312 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.
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.
The full file from olorehq/olore at commit 430d86c, republished under its MIT licence (© olorehq). 312 words, ~1,608 tokens.
.claude/skills/olore-tensorzero-latest/SKILL.md (or your agent's skills folder). This skill also uses 90 other files; get the full folder from GitHub.TensorZero is an open-source stack for industrial-grade LLM applications that unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
contents/
├── gateway/ # LLM gateway API, configuration, and guides (18 files)
├── integrations/
│ └── model-providers/ # Provider integrations: OpenAI, Anthropic, AWS, GCP, etc. (20 files)
├── deployment/ # Deploying gateway, UI, ClickHouse, Postgres, Redis (8 files)
├── operations/ # Auth, rate limits, credentials, metrics, cost tracking (9 files)
├── optimization/ # Fine-tuning (SFT), DICL, GEPA prompt optimization (4 files)
├── evaluations/ # Inference and workflow evaluations (6 files)
├── experimentation/ # A/B tests and experiment namespaces (3 files)
├── observability/ # Querying historical inferences (1 file)
├── index.mdx # Product overview
├── quickstart.mdx # Getting started
└── faq.mdx # FAQ| Topic | Key Files |
|---|---|
| Getting started / quickstart | contents/quickstart.mdx, contents/index.mdx |
| Gateway configuration reference | contents/gateway/configuration-reference.mdx |
| Inference API (calling LLMs) | contents/gateway/api-reference/inference.mdx, contents/gateway/call-any-llm.mdx |
| OpenAI-compatible API | contents/gateway/api-reference/inference-openai-compatible.mdx, contents/gateway/call-the-openai-responses-api.mdx |
| Functions and variants | contents/gateway/configure-functions-and-variants.mdx |
| Prompt templates | contents/gateway/create-a-prompt-template.mdx |
| Structured outputs | contents/gateway/generate-structured-outputs.mdx |
| Tool / function calling | contents/gateway/guides/tool-use.mdx |
| Embeddings | contents/gateway/generate-embeddings.mdx |
| Batch inference | contents/gateway/api-reference/batch-inference.mdx, contents/gateway/guides/batch-inference.mdx |
| Feedback and metrics | contents/gateway/api-reference/feedback.mdx, contents/gateway/guides/metrics-feedback.mdx |
| Retries and fallbacks | contents/gateway/guides/retries-fallbacks.mdx |
| Inference caching | contents/gateway/guides/inference-caching.mdx |
| Episodes (multi-turn) | contents/gateway/guides/episodes.mdx |
| Datasets and datapoints | contents/gateway/api-reference/datasets-datapoints.mdx |
| Data model | contents/gateway/data-model.mdx |
| Model provider integrations (all) | contents/integrations/model-providers/index.mdx |
| OpenAI, Azure, Anthropic, Gemini | contents/integrations/model-providers/openai.mdx, contents/integrations/model-providers/azure.mdx, contents/integrations/model-providers/anthropic.mdx, contents/integrations/model-providers/google-ai-studio-gemini.mdx |
| AWS (Bedrock, SageMaker) | contents/integrations/model-providers/aws-bedrock.mdx, contents/integrations/model-providers/aws-sagemaker.mdx |
| GCP Vertex AI | contents/integrations/model-providers/gcp-vertex-ai-anthropic.mdx, contents/integrations/model-providers/gcp-vertex-ai-gemini.mdx |
| Self-hosted models (vLLM, TGI, SGLang) | contents/integrations/model-providers/vllm.mdx, contents/integrations/model-providers/tgi.mdx, contents/integrations/model-providers/sglang.mdx |
| OpenAI-compatible providers | contents/integrations/model-providers/openai-compatible.mdx |
| Deployment (gateway, UI) | contents/deployment/tensorzero-gateway.mdx, contents/deployment/tensorzero-ui.mdx |
| Database setup | contents/deployment/clickhouse.mdx, contents/deployment/postgres.mdx, contents/deployment/valkey-redis.mdx |
| Upgrading | contents/deployment/upgrade-tensorzero.mdx |
| Authentication and credentials | contents/operations/set-up-auth-for-tensorzero.mdx, contents/operations/manage-credentials.mdx |
| Rate limits | contents/operations/enforce-custom-rate-limits.mdx, contents/operations/centralize-auth-rate-limits-and-more.mdx |
| Cost and usage tracking | contents/operations/track-usage-and-cost.mdx |
| OpenTelemetry / Prometheus | contents/operations/export-opentelemetry-traces.mdx, contents/operations/export-prometheus-metrics.mdx |
| Extending TensorZero | contents/operations/extend-tensorzero.mdx |
| Optimization overview | contents/optimization/index.mdx |
| Supervised fine-tuning (SFT) | contents/optimization/supervised-fine-tuning-sft.mdx |
| Dynamic in-context learning (DICL) | contents/optimization/dynamic-in-context-learning-dicl.mdx |
| GEPA prompt optimization | contents/optimization/gepa.mdx |
| Evaluations overview | contents/evaluations/index.mdx |
| Inference evaluations | contents/evaluations/inference-evaluations/tutorial.mdx, contents/evaluations/inference-evaluations/configuration-reference.mdx |
| Workflow evaluations | contents/evaluations/workflow-evaluations/tutorial.mdx, contents/evaluations/workflow-evaluations/api-reference.mdx |
| A/B testing | contents/experimentation/run-static-ab-tests.mdx, contents/experimentation/run-adaptive-ab-tests.mdx |
| Querying historical inferences | contents/observability/query-historical-inferences.mdx |
Use this skill when the user asks about:
TOC.md for complete file listing by directorycontents/{path}© olorehq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 90 other files in vault/packages/tensorzero/latest of olorehq/olore.
Open the folder on GitHubat commit 430d86c
Olore Tensorzero Latest 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 |
|---|---|---|---|---|---|---|
| Olore Tensorzero Latest this skillolorehq/olore | 104 | — | ~1.6k | Automated safety check: Pass | MIT | |
| LLM Routercuriositech/some_claude_skills | 244 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Shogun Bloom Configyohey-w/multi-agent-shogun | 1.4k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Codex Model Routing Teamzjp1997720/codex-model-routing-team | 158 | — | ~736 | Automated safety check: Pass | MIT | |
| Observability Architecturemajiayu000/litellm-rs | 117 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Fine-Tuning ExpertJeffallan/claude-skills | 12k | — | ~1.7k | Automated safety check: Pass | MIT |
curiositech/some_claude_skills
Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements.
yohey-w/multi-agent-shogun
Interactive wizard: guided questions with multiple-choice options about subscriptions, then outputs a ready-to-paste capabilitytiers YAML + fixed agent model assignments.
zjp1997720/codex-model-routing-team
在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务,由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流;也用于用户明确要求模型路由、后台 Worker、Agents Team…
majiayu000/litellm-rs
LiteLLM-RS Observability Architecture. An agent skill from majiayu000/litellm-rs.
Jeffallan/claude-skills
Guides LLM fine-tuning with LoRA and QLoRA through Hugging Face PEFT, from dataset validation and training checks to adapter merging, quantization and deployment.
Luciole-Studio/Misaka-Agent
Evolve prompts/regex/SQL/code with Imbue's evolution loop. An agent skill from Luciole-Studio/Misaka-Agent.
olorehq/olore
Build documentation packages from configs. An agent skill from olorehq/olore.
olorehq/olore
Local A2A (Agent-to-Agent) protocol documentation (latest). An agent skill from olorehq/olore.
olorehq/olore
Local bunit documentation reference (latest). An agent skill from olorehq/olore.
olorehq/olore
Local Cargo documentation reference (latest). An agent skill from olorehq/olore.
olorehq/olore
Local claude-code documentation reference (latest). An agent skill from olorehq/olore.
olorehq/olore
Local dotnet-aspire documentation reference (latest). An agent skill from olorehq/olore.
Works with
Categories
Local TensorZero documentation reference (latest). An agent skill from olorehq/olore. Olore Tensorzero Latest is an agent skill from olorehq/olore. Local TensorZero documentation reference (latest).
Olore Tensorzero Latest fits situations like: LLM gateway configuration; model provider integrations; optimization (fine-tuning; experimentation.
Run `npx skills add olorehq/olore --skill olore-tensorzero-latest -a claude-code`. Or copy the skill folder (vault/packages/tensorzero/latest in olorehq/olore) into .claude/skills/olore-tensorzero-latest in your project. Claude Code loads it when a task matches its description.
Run `npx skills add olorehq/olore --skill olore-tensorzero-latest -a codex`. Or copy the skill folder (vault/packages/tensorzero/latest in olorehq/olore) into .agents/skills/olore-tensorzero-latest in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add olorehq/olore --skill olore-tensorzero-latest -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/olore-tensorzero-latest, .gemini/skills/olore-tensorzero-latest, .github/skills/olore-tensorzero-latest and .opencode/skills/olore-tensorzero-latest in your project.
SKILL.md names no scripts, command-line tools or credentials: Olore Tensorzero Latest is instructions for the agent only.
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.
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.
Olore Tensorzero Latest is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Olore Tensorzero Latest: LLM Router (curiositech/some_claude_skills, 244 stars), Shogun Bloom Config (yohey-w/multi-agent-shogun, 1.4k stars), Codex Model Routing Team (zjp1997720/codex-model-routing-team, 158 stars) and Observability Architecture (majiayu000/litellm-rs, 117 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
olorehq (a GitHub organization) maintains it in olorehq/olore, which has 104 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 10, 2026.
Source: olorehq/olore on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.