No Explicit Any
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing TypeScript files for type safety regressions, during code review of functions that handle external data, or when the codebase has ESLint warnings for…
FunSearch (Program Search) method skill. An agent skill from Optima-CityU/LLM4AD_Next.
BSD-3-ClauseAuto-check passed
Install Funsearch
$ npx skills add Optima-CityU/LLM4AD_Next --skill funsearch -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Optima-CityU/LLM4AD_Next funsearch --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/Optima-CityU/LLM4AD_Next.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/algo-design/funsearch .claude/skills/funsearch && 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 "funsearch" agent skill from https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/funsearch into .claude/skills/funsearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "funsearch", 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/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/funsearchType 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 Optima-CityU/LLM4AD_Next --skill funsearch -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Optima-CityU/LLM4AD_Next funsearch --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Optima-CityU/LLM4AD_Next.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/algo-design/funsearch .agents/skills/funsearch && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "funsearch" agent skill from https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/funsearch into .agents/skills/funsearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "funsearch", 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 Optima-CityU/LLM4AD_Next --skill funsearch -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Optima-CityU/LLM4AD_Next funsearch --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Optima-CityU/LLM4AD_Next.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/algo-design/funsearch .cursor/skills/funsearch && 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 "funsearch" agent skill from https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/funsearch into .cursor/skills/funsearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "funsearch", 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/Optima-CityU/LLM4AD_Next.git --path skills/algo-design/funsearch--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 Optima-CityU/LLM4AD_Next --skill funsearch -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Optima-CityU/LLM4AD_Next funsearch --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Optima-CityU/LLM4AD_Next.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/algo-design/funsearch .gemini/skills/funsearch && 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 "funsearch" agent skill from https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/funsearch into .gemini/skills/funsearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "funsearch", 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 Optima-CityU/LLM4AD_Next funsearchInstalls 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 Optima-CityU/LLM4AD_Next --skill funsearch -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Optima-CityU/LLM4AD_Next.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/algo-design/funsearch .github/skills/funsearch && 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 "funsearch" agent skill from https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/funsearch into .github/skills/funsearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "funsearch", 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 Optima-CityU/LLM4AD_Next --skill funsearch -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Optima-CityU/LLM4AD_Next funsearch --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Optima-CityU/LLM4AD_Next.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/algo-design/funsearch .opencode/skills/funsearch && 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 "funsearch" agent skill from https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/funsearch into .opencode/skills/funsearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "funsearch", 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
funsearch- GitHub stars
- 574
- Token cost
- ~604 tokens
- SKILL.md length
- 252 words
- Files
- 2
- Skills in repo
- 24
- Repo updated
- First seen
- Licence
- BSD-3-Clause
At a glance
FunSearch (Program Search) method skill. An agent skill from Optima-CityU/LLM4AD_Next.
- Works in 3 steps: Method Essence → Recommended Parameters → Acceptance Criteria
- The user explicitly requests FunSearch / Program Search
- SKILL.md covers 1. Method Essence, 2. Recommended Parameters and 4. Acceptance Criteria
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Funsearch is an agent skill from Optima-CityU/LLM4AD_Next. FunSearch (Program Search) method skill. USE WHEN the user explicitly requests FunSearch / Program Search, or wants search with a programs database that stores and samples from high-scoring programs.
Its SKILL.md is about 600 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `params.yaml`).
The repository describes itself as: A next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use. The licence is BSD-3-Clause.
When your agent uses it
- The user explicitly requests FunSearch / Program Search
- Wants search with a programs database that stores and samples from high-scoring programs
Example prompts
- “/funsearch”
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit e3d3f7b. 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
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.
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
Funsearch loads about 604 tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 252 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from Optima-CityU/LLM4AD_Next at commit e3d3f7b, republished under its BSD-3-Clause licence (© Optima-CityU). 252 words, ~604 tokens.
Download SKILL.mdSave it as
.claude/skills/funsearch/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- funsearch
- description
- FunSearch (Program Search) method skill. USE WHEN the user explicitly requests FunSearch / Program Search, or wants search with a programs database that stores and samples from high-scoring programs.
- triggers
- funsearch, program search, database-driven search
FunSearch Skill
Paper: Romera-Paredes et al., "Mathematical discoveries from program search with large language models", Nature 625 (2024).
1. Method Essence
FunSearch organizes search using a ProgramsDatabase: programs are stored and indexed by evaluation score, with sampling prioritizing high-score buckets for mutation. New programs are evaluated and stored by score, forming a "high-score priority, low-score elimination" evolution. It also uses an islands mechanism for diversity: multiple independent sub-populations evolve separately, with periodic exchange.
Core components:
- Database: Archive of programs + scores, stratified by score (higher score = higher probability of being sampled as parent)
- Sampler: Generates mutation prompts from high-score programs (not from empty prompts)
- Evaluator: Independent evaluation, results written back to database
2. Recommended Parameters
See params.yaml in this directory for the recommended parameter configuration.
What Happens During Evolution
- Database initialized with seed programs (or random generation)
- Each generation:
- Sample parent from high-score bucket
- Generate N variants via LLM mutation
- Evaluate variants independently
- Store scored variants back to database
- Optionally: eliminate low-score programs
- Islands evolve independently, periodically exchanging best programs
- Database naturally stratifies: top programs dominate sampling
Common Pitfalls
- Database collapses (all programs similar) → increase island count or mutation diversity
- Too aggressive elimination → lose useful building blocks; increase
population_size - No improvement → check if sampling always picks the same parent; increase
samples_per_prompt
4. Acceptance Criteria
- Database stratification visible (programs in different score buckets)
- High-score programs repeatedly used as mutation parents (exploitation)
- Periodic sampling from lower buckets (exploration)
- Clear elimination of consistently low-scoring programs
- Final best program in top database bucket
© Optima-CityU, BSD-3-Clause. 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 1 other file in skills/algo-design/funsearch of Optima-CityU/LLM4AD_Next.
- SKILL.md
- params.yaml
Open the folder on GitHubat commit e3d3f7b
Compare with similar skills
Funsearch 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 |
|---|---|---|---|---|---|---|
| Funsearch this skillOptima-CityU/LLM4AD_Next | 574 | — | ~604 | Automated safety check: Pass | BSD-3-Clause | |
| No Explicit Anythedaviddias/Front-End-Checklist | 74k | — | ~565 | Automated safety check: Pass | MIT | |
| Santa Methodaffaan-m/ECC | 276k | 3 repos | ~3.1k | Automated safety check: Pass | MIT | |
| Santa Methodaffaan-m/ECC | 276k | — | ~2.1k | Automated safety check: Pass | MIT | |
| Santa Methodaffaan-m/ECC | 276k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Strict Programming Practicescode-yeongyu/oh-my-openagent | 70k | — | ~9.5k | Automated safety check: Pass | Custom licence |
Similar skills
Santa Method
affaan-m/ECC
Multi-agent adversarial verification: two independent reviewers with the same rubric must both pass before output ships, with a fix-and-re-review convergence loop and human escalation cap.
Santa Method
affaan-m/ECC
収束ループを持つマルチエージェント敵対的検証。2つの独立したレビューエージェントが両方合格して初めて出力を出荷できます。
Santa Method
affaan-m/ECC
具有收敛循环的多智能体对抗验证。两个独立的审查代理必须都通过，输出才能发送。
Strict Programming Practices
code-yeongyu/oh-my-openagent
Applies strict, type-first coding rules for Python, Rust, TypeScript and Go, loading the matching language reference before the agent writes or edits any code.
Referral Program
alirezarezvani/claude-skills
When the user wants to design, launch, or optimize a referral or affiliate program.
More from Optima-CityU/LLM4AD_Next
All 24 skills in this repoProposal Foundation Layout
Optima-CityU/LLM4AD_Next
A skill your agent uses when establishing a research proposal's project foundation, submission constraints, and presentation system before section drafting begins.
Llm4ad Task Builder
Optima-CityU/LLM4AD_Next
A skill your agent uses when a user wants to build an LLM4ADNext task package — a runnable directory that lets the LLM4AD platform evolve an algorithm for their problem.
Document Knowledge Organizer
Optima-CityU/LLM4AD_Next
Organize one or more Markdown source documents into high-fidelity, editable knowledge blocks.
Proposal Final Review
Optima-CityU/LLM4AD_Next
A skill your agent uses when assembling a completed staged Typst proposal and checking its evidence, logic, citations, structure, and export readiness.
Proposal Foundation Feasibility
Optima-CityU/LLM4AD_Next
A skill your agent uses when documenting a proposal's research foundation, available conditions, team support, feasibility, and risk controls from author-supplied facts.
Proposal Innovation Plan
Optima-CityU/LLM4AD_Next
A skill your agent uses when distilling a proposal's innovations and defining milestones, annual plans, contingency points, and expected outcomes.
Questions about Funsearch
What does Funsearch do?
FunSearch (Program Search) method skill. An agent skill from Optima-CityU/LLM4AD_Next. Funsearch is an agent skill from Optima-CityU/LLM4AD_Next. FunSearch (Program Search) method skill.
When should I use Funsearch?
Funsearch fits situations like: the user explicitly requests FunSearch / Program Search; wants search with a programs database that stores and samples from high-scoring programs.
How do I install Funsearch in Claude Code?
Run `npx skills add Optima-CityU/LLM4AD_Next --skill funsearch -a claude-code`. Or copy the skill folder (skills/algo-design/funsearch in Optima-CityU/LLM4AD_Next) into .claude/skills/funsearch in your project. Claude Code loads it when a task matches its description.
How do I install Funsearch in Codex?
Run `npx skills add Optima-CityU/LLM4AD_Next --skill funsearch -a codex`. Or copy the skill folder (skills/algo-design/funsearch in Optima-CityU/LLM4AD_Next) into .agents/skills/funsearch in your project. Codex loads it when a task matches its description.
Can I use Funsearch 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 Optima-CityU/LLM4AD_Next --skill funsearch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/funsearch, .gemini/skills/funsearch, .github/skills/funsearch and .opencode/skills/funsearch in your project.
What does Funsearch need to run?
SKILL.md names no scripts, command-line tools or credentials: Funsearch is instructions for the agent only.
Does Funsearch 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 Funsearch 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 Funsearch use?
Funsearch is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Funsearch use?
About 604 tokens (SKILL.md is roughly 2.4k 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 Funsearch?
Skills that share tags, products or a category with Funsearch: No Explicit Any (thedaviddias/Front-End-Checklist, 74k stars), Santa Method (affaan-m/ECC, 276k stars), Santa Method (affaan-m/ECC, 276k stars) and Santa Method (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Funsearch?
Optima-CityU (a GitHub organization) maintains it in Optima-CityU/LLM4AD_Next, which has 574 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 9, 2026.
Source: Optima-CityU/LLM4AD_Next on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.