Reflection Method Call
IvanMurzak/Unity-MCP
Call a C method by reflection — including private methods. An agent skill from IvanMurzak/Unity-MCP.
Reflective Evolution (ReEvo) method skill. An agent skill from Optima-CityU/LLM4AD_Next.
BSD-3-ClauseAuto-check passed
Install Reevo
$ npx skills add Optima-CityU/LLM4AD_Next --skill reevo -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Optima-CityU/LLM4AD_Next reevo --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/reevo .claude/skills/reevo && 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 "reevo" agent skill from https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/reevo into .claude/skills/reevo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reevo", 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/reevoType 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 reevo -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Optima-CityU/LLM4AD_Next reevo --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/reevo .agents/skills/reevo && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "reevo" agent skill from https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/reevo into .agents/skills/reevo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reevo", 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 reevo -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Optima-CityU/LLM4AD_Next reevo --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/reevo .cursor/skills/reevo && 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 "reevo" agent skill from https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/reevo into .cursor/skills/reevo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reevo", 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/reevo--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 reevo -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Optima-CityU/LLM4AD_Next reevo --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/reevo .gemini/skills/reevo && 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 "reevo" agent skill from https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/reevo into .gemini/skills/reevo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reevo", 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 reevoInstalls 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 reevo -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/reevo .github/skills/reevo && 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 "reevo" agent skill from https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/reevo into .github/skills/reevo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reevo", 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 reevo -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 reevo --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/reevo .opencode/skills/reevo && 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 "reevo" agent skill from https://github.com/Optima-CityU/LLM4AD_Next/tree/main/skills/algo-design/reevo into .opencode/skills/reevo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reevo", 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
reevo- GitHub stars
- 574
- Token cost
- ~650 tokens
- SKILL.md length
- 284 words
- Files
- 2
- Skills in repo
- 24
- Repo updated
- First seen
- Licence
- BSD-3-Clause
At a glance
Reflective Evolution (ReEvo) method skill. An agent skill from Optima-CityU/LLM4AD_Next.
- Works in 3 steps: Method Essence → Recommended Parameters → Acceptance Criteria
- The user explicitly requests ReEvo / Reflective Evolution
- 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
Reevo is an agent skill from Optima-CityU/LLM4AD_Next. Reflective Evolution (ReEvo) method skill. USE WHEN the user explicitly requests ReEvo / Reflective Evolution, or wants evolution with reflection mechanisms that summarize failure lessons and inject them into the next generation.
Its SKILL.md is about 650 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 ReEvo / Reflective Evolution
- Wants evolution with reflection mechanisms that summarize failure lessons and inject them into the next generation
Example prompts
- “/reevo”
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
Reevo loads about 650 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 284 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). 284 words, ~650 tokens.
Download SKILL.mdSave it as
.claude/skills/reevo/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- reevo
- description
- Reflective Evolution (ReEvo) method skill. USE WHEN the user explicitly requests ReEvo / Reflective Evolution, or wants evolution with reflection mechanisms that summarize failure lessons and inject them into the next generation.
- triggers
- reevo, reflective evolution, reflection-based evolution
Reflective Evolution (ReEvo) Skill
Paper: Ye et al., "ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution", NeurIPS 2024.
1. Method Essence
ReEvo adds a reflection layer to the evolution loop (sample → evaluate → select): before each generation, it summarizes success/failure patterns from historical samples and injects the reflection into the prompt, so the next mutation "stands on experience" rather than trying blindly. Reflection has two levels:
- Long-term reflection: Overall summary of all historical individuals — "what structures work/fail, what patterns repeatedly fail"
- Short-term reflection: Local review of the most recent N individuals (N=5) — "what changed last round, how did it perform"
2. Recommended Parameters
See params.yaml in this directory for the recommended parameter configuration.
Parameter Guidance:
population_size: 8-12 gives more material for reflection; start with 8.mutation_rate: 0.5 is balanced; increase for more diversity, decrease for stability.max_sample_nums: ReEvo is more sample-efficient than EoH; 100 is often sufficient.
What Happens During Evolution
- Population initialized; reflection buffer empty
- Each generation:
- Compute short-term reflection (last 5 individuals) and long-term reflection (all history)
- Generate offspring via LLM with reflection-augmented prompts
- Evaluate, select, update population
- Reflection evolves: as more individuals are evaluated, reflections become more insightful
- Common pattern: early generations explore broadly; later generations refine based on accumulated wisdom
Common Pitfalls
- Reflection becomes too vague → reduce window size or add more specific prompts
- No improvement after reflection → check if the problem is too constrained for the operator
- Overfitting to reflection → occasionally force exploration with fresh random mutations
4. Acceptance Criteria
- Reflection prompts appear in the evolution log before each generation
- Population shows improvement correlated with reflection insights
- Short-term and long-term reflections are distinct (not redundant)
- Best individual incorporates ideas from reflection (traceable in code changes)
© 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/reevo of Optima-CityU/LLM4AD_Next.
- SKILL.md
- params.yaml
Open the folder on GitHubat commit e3d3f7b
Compare with similar skills
Reevo 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 |
|---|---|---|---|---|---|---|
| Reevo this skillOptima-CityU/LLM4AD_Next | 574 | — | ~650 | Automated safety check: Pass | BSD-3-Clause | |
| Reflection Method CallIvanMurzak/Unity-MCP | 4.4k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| Reflection Method FindIvanMurzak/Unity-MCP | 4.4k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Reflectalirezarezvani/claude-skills | 28k | 1 repos | ~2.4k | Automated safety check: Pass | MIT | |
| No Explicit Anythedaviddias/Front-End-Checklist | 74k | — | ~565 | Automated safety check: Pass | MIT | |
| Evolutionsickn33/agentic-awesome-skills | 47k | 2 repos | ~3.1k | Automated safety check: Pass | MIT |
Similar skills
Reflection Method Find
IvanMurzak/Unity-MCP
Find C methods across every loaded assembly by name / type / parameters — including private methods.
Reflect
alirezarezvani/claude-skills
Mid-conversation reflection skill that pauses execution and zooms out from detail-mode to honestly reassess direction, assumptions, and bias.
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…
Evolution
sickn33/agentic-awesome-skills
This skill enables makepad-skills to self-improve continuously during development.
Reflection Coach
paperclipai/paperclip
Reflect on another agent's recent execution record and propose the smallest durable instruction, skill, or tool-description change.
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 Reevo
What does Reevo do?
Reflective Evolution (ReEvo) method skill. An agent skill from Optima-CityU/LLM4AD_Next. Reevo is an agent skill from Optima-CityU/LLM4AD_Next. Reflective Evolution (ReEvo) method skill.
When should I use Reevo?
Reevo fits situations like: the user explicitly requests ReEvo / Reflective Evolution; wants evolution with reflection mechanisms that summarize failure lessons and inject them into the next generation.
How do I install Reevo in Claude Code?
Run `npx skills add Optima-CityU/LLM4AD_Next --skill reevo -a claude-code`. Or copy the skill folder (skills/algo-design/reevo in Optima-CityU/LLM4AD_Next) into .claude/skills/reevo in your project. Claude Code loads it when a task matches its description.
How do I install Reevo in Codex?
Run `npx skills add Optima-CityU/LLM4AD_Next --skill reevo -a codex`. Or copy the skill folder (skills/algo-design/reevo in Optima-CityU/LLM4AD_Next) into .agents/skills/reevo in your project. Codex loads it when a task matches its description.
Can I use Reevo 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 reevo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reevo, .gemini/skills/reevo, .github/skills/reevo and .opencode/skills/reevo in your project.
What does Reevo need to run?
SKILL.md names no scripts, command-line tools or credentials: Reevo is instructions for the agent only.
Does Reevo 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 Reevo 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 Reevo use?
Reevo 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 Reevo use?
About 650 tokens (SKILL.md is roughly 2.6k 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 Reevo?
Skills that share tags, products or a category with Reevo: Reflection Method Call (IvanMurzak/Unity-MCP, 4.4k stars), Reflection Method Find (IvanMurzak/Unity-MCP, 4.4k stars), Reflect (alirezarezvani/claude-skills, 28k stars) and No Explicit Any (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Reevo?
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.