Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
A skill your agent uses when adding or debugging classifier/collision guidance, a custom reward or guidancefn, GuidanceWrapper behavior, or guided nuPlan simulation in Diffusion-Planner.
Install Guidance
$ npx skills add VectorSpaceLab/AREX-Skill --skill guidance -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill guidance --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/diffusion-planner/sub-skills/guidance .claude/skills/guidance && 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 "guidance" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/diffusion-planner/sub-skills/guidance into .claude/skills/guidance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guidance", 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/diffusion-planner/sub-skills/guidanceType 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 guidance -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill guidance --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/diffusion-planner/sub-skills/guidance .agents/skills/guidance && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "guidance" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/diffusion-planner/sub-skills/guidance into .agents/skills/guidance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guidance", 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 guidance -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill guidance --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/diffusion-planner/sub-skills/guidance .cursor/skills/guidance && 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 "guidance" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/diffusion-planner/sub-skills/guidance into .cursor/skills/guidance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guidance", 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/diffusion-planner/sub-skills/guidance--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 guidance -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill guidance --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/diffusion-planner/sub-skills/guidance .gemini/skills/guidance && 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 "guidance" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/diffusion-planner/sub-skills/guidance into .gemini/skills/guidance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guidance", 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 guidanceInstalls 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 guidance -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/diffusion-planner/sub-skills/guidance .github/skills/guidance && 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 "guidance" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/diffusion-planner/sub-skills/guidance into .github/skills/guidance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guidance", 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 guidance -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 guidance --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/diffusion-planner/sub-skills/guidance .opencode/skills/guidance && 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 "guidance" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/diffusion-planner/sub-skills/guidance into .opencode/skills/guidance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guidance", 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
guidance- GitHub stars
- 331
- Token cost
- ~1.2k tokens
- SKILL.md length
- 528 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 157
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses when adding or debugging classifier/collision guidance, a custom reward or guidancefn, GuidanceWrapper behavior, or guided nuPlan simulation in Diffusion-Planner.
- Works in 4 steps: Read the API contract before writing a → Follow the guided workflow: establish the → If the reward is zero, detached,… → …
- Debugging classifier/collision guidance
- SKILL.md covers Applicability and boundaries, Fast route, Non-negotiable runtime contract and Bundled verification
- Runs Python scripts from its folder; calls python
What it does
Guidance is an agent skill from VectorSpaceLab/AREX-Skill. Use when adding or debugging classifier/collision guidance, a custom reward or guidancefn, GuidanceWrapper behavior, or guided nuPlan simulation in Diffusion-Planner.
Its SKILL.md is about 1.2k 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 Development. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is Apache-2.0.
When your agent uses it
- Debugging classifier/collision guidance
- A custom reward
- GuidanceWrapper behavior
- Guided nuPlan simulation in Diffusion-Planner
Example prompts
- “/guidance”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Read the API contract before writing a
- Follow the guided workflow: establish the
- If the reward is zero, detached, non-finite, or the wrapper fails before the
- Keep custom code in a project-owned extension/worktree. Treat the original
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.
Shell commands in SKILL.md call:
python
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
Guidance loads about 1.2k tokens when it runs, and up to ~7.7k if it reads all its reference files. Until then it costs about 44 tokens; SKILL.md has 528 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). 528 words, ~1,175 tokens.
Download SKILL.mdSave it as
.claude/skills/guidance/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- guidance
- description
- Use when adding or debugging classifier/collision guidance, a custom reward or guidance_fn, GuidanceWrapper behavior, or guided nuPlan simulation in Diffusion-Planner.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- NO_LICENSE
Diffusion-Planner guidance
Use this sub-skill for the guidance extension point in Diffusion-Planner. It
teaches a Researcher to reason about GuidanceWrapper, write a differentiable
custom guidance callable, preserve the planner's tensor/device/normalization
contracts, configure guided sampling, and diagnose failures such as NaNs,
detached rewards, empty collision pairs, or shape mismatches.
Applicability and boundaries
Natural triggers include classifier guidance, collision avoidance
guidance, custom reward, guidance_fn, GuidanceWrapper, and guided
nuPlan simulation. Do not use this sub-skill for generic training or an
un-guided simulation; use the sibling skills for those tasks:
- Diffusion-Planner root skill for shared repository setup and provenance.
- model-training for training and checkpoints.
- closed-loop-planning for ordinary planner and nuPlan simulation setup.
The sibling links are part of the planned graph; the guidance files themselves remain self-contained and do not assume that sibling instructions are loaded.
Fast route
- Read the API contract before writing a
guidance function. In particular, distinguish the flattened sampler input
from the
[B, P, T, 4]view seen by guidance functions. - Follow the guided workflow: establish the interpreter and nuPlan paths as user configuration, run the deterministic local smoke helper, then launch only when checkpoint, dataset, maps, and simulation permissions are available.
- If the reward is zero, detached, non-finite, or the wrapper fails before the simulation starts, use the troubleshooting playbook.
- Keep custom code in a project-owned extension/worktree. Treat the original checkout as evidence; do not make a future Researcher patch or open it in place merely to try a guidance experiment.
Show full SKILL.md (282 more words)Show less
Non-negotiable runtime contract
A custom function has the public shape:
def my_guidance_fn(x, t, cond, inputs) -> torch.Tensor:
"""Return a differentiable per-batch guidance energy."""The live wrapper currently invokes registered functions with **kwargs, so a
practical implementation should accept inputs by keyword and tolerate
additional keyword arguments when the deployment passes them. It must return a
finite torch.Tensor whose computation graph reaches the differentiable parts
of x; the DPM classifier adapter differentiates the returned energy with
respect to the sampler input. cond is commonly None in this repository.
GuidanceWrapper receives the flattened sampler tensor, applies the model
correction and inverse normalizers, and then calls each registered function.
The guidance function therefore sees physical-unit state and inverse-normalized
observation fields, not the normalized tensors fed to the model. The wrapper
also passes model, model_condition, state_normalizer, and
observation_normalizer in keyword arguments. The built-in collision function
uses neighbor_current_mask and neighbor_agents_past from inputs.
The guided YAML selects GuidanceWrapper as guidance_fn; the decoder passes
it to DPM-Solver in classifier mode with guidance scale 0.5. The supplied
launch script is a semantic example only: replace its placeholder dataset and
nuPlan locations and its private interpreter/sudo invocation with an
interpreter that the Researcher controls. See the workflow reference for the
safe equivalent.
Bundled verification
From the repository root, run the helper with the prepared environment (or an equivalent environment that can import the installed package):
/path/to/diffusion-planner-inspection/bin/python \
skills/disco/diffusion-planner/sub-skills/guidance/scripts/synthetic_guidance_smoke.pyThe helper uses fixed in-memory rectangles and a tiny [B=1, P=2, T=3, 4]
tensor. It checks rectangle geometry, the live collision function, wrapper
normalization hooks, finiteness, and autograd connectivity; it does not fetch
nuPlan data, checkpoints, or launch workers. Use --help to see its options.
For the exact signatures, tensor layout, guided YAML meaning, and failure recovery, continue to the bundled references rather than guessing from a simulation error.
© 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/diffusion-planner/sub-skills/guidance of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/api-reference.md
- references/troubleshooting.md
- references/workflows.md
- scripts/synthetic_guidance_smoke.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Guidance 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 |
|---|---|---|---|---|---|---|
| Guidance this skillVectorSpaceLab/AREX-Skill | 331 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 4 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from VectorSpaceLab/AREX-Skill
All 157 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 Guidance
What does Guidance do?
A skill your agent uses when adding or debugging classifier/collision guidance, a custom reward or guidancefn, GuidanceWrapper behavior, or guided nuPlan simulation in Diffusion-Planner. Guidance is an agent skill from VectorSpaceLab/AREX-Skill. Use when adding or debugging classifier/collision guidance, a custom reward or guidancefn, GuidanceWrapper behavior, or guided nuPlan simulation in Diffusion-Planner.
When should I use Guidance?
Guidance fits situations like: debugging classifier/collision guidance; A custom reward; guidanceWrapper behavior; guided nuPlan simulation in Diffusion-Planner.
How do I install Guidance in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill guidance -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/diffusion-planner/sub-skills/guidance in VectorSpaceLab/AREX-Skill) into .claude/skills/guidance in your project. Claude Code loads it when a task matches its description.
How do I install Guidance in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill guidance -a codex`. Or copy the skill folder (skills/repositories/repo-skills/diffusion-planner/sub-skills/guidance in VectorSpaceLab/AREX-Skill) into .agents/skills/guidance in your project. Codex loads it when a task matches its description.
Can I use Guidance 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 guidance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/guidance, .gemini/skills/guidance, .github/skills/guidance and .opencode/skills/guidance in your project.
What does Guidance need to run?
Going by SKILL.md and its folder, Guidance needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Guidance 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 Guidance 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 Guidance use?
Guidance is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Guidance use?
About 1.2k tokens (SKILL.md is roughly 4.7k 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 6.6k tokens, read only when the agent opens those files.
What are the alternatives to Guidance?
Skills that share tags, products or a category with Guidance: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Guidance?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 331 GitHub stars. The repository holds 157 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.