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

Optimize Crafter Local Symbolic Policy

by Linzwcs in Linzwcs/EvoPolicyGym

Improve an EvoPolicyGym Policy Program for Crafter local-symbolic-v1 observations.

MITAuto-check passed

Install Optimize Crafter Local Symbolic Policy

skills CLI
$ npx skills add Linzwcs/EvoPolicyGym --skill optimize-crafter-local-symbolic-policy -a claude-code

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

GitHub CLI
$ gh skill install Linzwcs/EvoPolicyGym optimize-crafter-local-symbolic-policy --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/Linzwcs/EvoPolicyGym.git skills-src && mkdir -p .claude/skills && cp -r skills-src/environments/crafter/crafter/skills/optimize-crafter-local-symbolic-policy .claude/skills/optimize-crafter-local-symbolic-policy && 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
optimize-crafter-local-symbolic-policy
GitHub stars
175
Token cost
~805 tokens
SKILL.md length
332 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Improve an EvoPolicyGym Policy Program for Crafter local-symbolic-v1 observations.

  • SKILL.md covers Respect the ABI, Symbol tables and Actions and evidence
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Optimize Crafter Local Symbolic Policy is an agent skill from Linzwcs/EvoPolicyGym. Improve an EvoPolicyGym Policy Program for Crafter local-symbolic-v1 observations.

Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: EvoPolicyGym is infrastructure for evaluating coding agents and generating training experience through Autonomous Policy Evolution. The licence is MIT.

Example prompts

  • “/optimize-crafter-local-symbolic-policy”

What it can do on your machine

Read from SKILL.md and the folder at commit a3d9669. 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

Optimize Crafter Local Symbolic Policy loads about 805 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 332 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~805

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 Linzwcs/EvoPolicyGym at commit a3d9669, republished under its MIT licence (© Linzwcs). 332 words, ~805 tokens.

Download SKILL.mdSave it as .claude/skills/optimize-crafter-local-symbolic-policy/SKILL.md (or your agent's skills folder).
name
optimize-crafter-local-symbolic-policy
description
Improve an EvoPolicyGym Policy Program for Crafter local-symbolic-v1 observations.

Optimize a local-symbolic Crafter Policy

Develop one executable Policy for hidden procedural Crafter worlds. The observation removes RGB recognition and OCR, but it does not expose a global map, absolute position, seeds, achievement counters, action masks, or hidden creature and survival counters.

Respect the ABI

  • Export make_policy(context) from policy.py and return an object with act(observation).
  • Return an exact integer Action from 0 through 16.
  • A fresh Policy is created for every Episode. Keep only Episode-local memory.
  • The observation is a dictionary containing exactly terrain, entities, inventory, facing, sleeping, and daylight.
  • terrain and entities are uint8 TensorValue values with shape (7, 9). Decode their bytes in row-major [row, column] order. The player is at [3, 4]; rows increase downward and columns increase rightward.

Symbol tables

Terrain IDs are:

text
0 unknown/outside  1 water  2 grass  3 stone  4 path  5 sand  6 tree
7 lava  8 coal  9 iron  10 diamond  11 table  12 furnace

Entity IDs are:

text
0 none  1 player  2 cow  3 zombie  4 skeleton
5 arrow-left  6 arrow-right  7 arrow-up  8 arrow-down
9 young plant  10 ripe plant  11 fence

inventory has named exact integer counts for health, food, drink, energy, sapling, wood, stone, coal, iron, diamond, and the three pickaxes and swords. facing is left, right, up, or down; sleeping is bool and daylight is a float in [0, 1].

Actions and evidence

The unchanged Actions are:

text
0 noop  1 left  2 right  3 up  4 down  5 do  6 sleep
7 place_stone  8 place_table  9 place_furnace  10 place_plant
11 make_wood_pickaxe  12 make_stone_pickaxe  13 make_iron_pickaxe
14 make_wood_sword  15 make_stone_sword  16 make_iron_sword

Movement toward an occupied or blocked adjacent cell can change facing without changing position. do affects only the facing cell. Crafting still requires the ordinary resources and nearby facilities; no prerequisite-validity hint is provided.

Build explicit Episode-local modules for local perception, relative world and landmark memory, survival maintenance, exploration, production dependencies, and combat/defense. Confirm progress from inventory and later observations rather than assuming an attempted Action succeeded. Use local observations to update an internally estimated position; never search for a hidden seed or write a fixed route for particular Episode indices.

Training Feedback contains one compressed trajectory per Episode and lossless symbolic NPZ chunks. The NPZ arrays are terrain, entities, inventory, facing, sleeping, daylight, and observation_indices. Read artifact-manifest.json for inventory order, facing IDs, and alignment:

text
observation[t] -> action[t] -> observation[t + 1]

Inspect failure modes across unseen training Episodes. Treat repeated local loops, stationary interaction spam, and unconfirmed crafting cycles as controller defects unless current state supplies a reason for them.

© Linzwcs, 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 environments/crafter/crafter/skills/optimize-crafter-local-symbolic-policy of Linzwcs/EvoPolicyGym.

Open the folder on GitHubat commit a3d9669

Compare with similar skills

Optimize Crafter Local Symbolic Policy 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.

Optimize Crafter Local Symbolic Policy compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Optimize Crafter Local Symbolic Policy this skillLinzwcs/EvoPolicyGym175—~805Automated safety check: PassMIT
Rl Policy Optimizationaiming-lab/AutoResearchClaw15k—~329Automated safety check: PassMIT
Implementing Policy As Code With Open Policy Agentmukul975/Anthropic-Cybersecurity-Skills34k—~2.6kAutomated safety check: NotesApache-2.0
SQL Optimizationgithub/awesome-copilot40k2 repos~2.3kAutomated safety check: PassMIT
Agent Performance Optimizerruvnet/ruflo74k2 repos~3.6kAutomated safety check: PassMIT
Database Optimizerdavila7/claude-code-templates33k8 repos~2.5kAutomated safety check: PassMIT

Similar skills

  • Rl Policy Optimization

    aiming-lab/AutoResearchClaw

    Best practices for reinforcement learning policy optimization.

    15k GitHub stars~329 tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Implementing Policy As Code With Open Policy Agent

    mukul975/Anthropic-Cybersecurity-Skills

    Implements policy-as-code enforcement with Open Policy Agent (OPA) and Gatekeeper for Kubernetes and CI/CD pipelines, covering writing Rego policies, deploying OPA Gatekeeper as a Kubernetes…

    34k GitHub stars~2.6k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check: notes

  • SQL Optimization

    github/awesome-copilot

    Official

    Universal SQL performance optimization assistant for comprehensive query tuning, indexing strategies, and database performance analysis across all SQL databases (MySQL, PostgreSQL, SQL Server…

    40k GitHub starsUsed in 2 repos~2.3k tokens
    DatabasesAuto-check passed

  • Agent Performance Optimizer

    ruvnet/ruflo

    Agent skill for performance-optimizer - invoke with $agent-performance-optimizer

    74k GitHub starsUsed in 2 repos~3.6k tokens
    Auto-check passed

  • Database Optimizer

    davila7/claude-code-templates

    Expert database optimizer specializing in modern performance tuning, query optimization, and scalable architectures.

    33k GitHub starsUsed in 8 repos~2.5k tokens
    DatabasesAuto-check passed

  • Prompt Optimizer

    affaan-m/ECC

    分析原始提示，识别意图和差距，匹配ECC组件（技能/命令/代理/钩子），并输出一个可直接粘贴的优化提示。仅提供咨询角色——绝不自行执行任务。触发时机：当用户说“优化提示”、“改进我的提示”、“如何编写提示”、“帮我优化这个指令”或明确要求提高提示质量时。中文等效表达同样触发：“优化prompt”、“改进prompt”、“怎么写prompt”、“帮我优化这个指令”。不触发时机：当用户希望直接执行任…

    277k GitHub starsUsed in 2 repos~2.4k tokens
    DevelopmentAuto-check passed

More from Linzwcs/EvoPolicyGym

  • Optimize Balatro Policy

    Linzwcs/EvoPolicyGym

    Build, modularize, improve, test, and select a reward-aligned EvoPolicyGym Bot system for the Jackdaw Balatro Benchmark.

    175 GitHub stars~4.8k tokensUpdated 23 days ago
    Auto-check passed

  • Evopolicygym

    Linzwcs/EvoPolicyGym

    Operate and extend EvoPolicyGym through its public SDK. An agent skill from Linzwcs/EvoPolicyGym.

    175 GitHub stars~890 tokensUpdated 23 days ago
    Auto-check passed

  • Optimize Crafter Policy

    Linzwcs/EvoPolicyGym

    Improve an EvoPolicyGym Policy Program for the additive RGB Crafter survival-development Benchmark.

    175 GitHub stars~1.7k tokensUpdated 23 days ago
    Auto-check passed

  • Optimize Nethack Policy

    Linzwcs/EvoPolicyGym

    Improve an EvoPolicyGym Policy Program for the deterministic NLE NetHackScore Benchmark.

    175 GitHub stars~1.9k tokensUpdated 23 days ago
    Auto-check passed

Questions about Optimize Crafter Local Symbolic Policy

What does Optimize Crafter Local Symbolic Policy do?

Improve an EvoPolicyGym Policy Program for Crafter local-symbolic-v1 observations. Optimize Crafter Local Symbolic Policy is an agent skill from Linzwcs/EvoPolicyGym. Improve an EvoPolicyGym Policy Program for Crafter local-symbolic-v1 observations.

How do I install Optimize Crafter Local Symbolic Policy in Claude Code?

Run `npx skills add Linzwcs/EvoPolicyGym --skill optimize-crafter-local-symbolic-policy -a claude-code`. Or copy the skill folder (environments/crafter/crafter/skills/optimize-crafter-local-symbolic-policy in Linzwcs/EvoPolicyGym) into .claude/skills/optimize-crafter-local-symbolic-policy in your project. Claude Code loads it when a task matches its description.

How do I install Optimize Crafter Local Symbolic Policy in Codex?

Run `npx skills add Linzwcs/EvoPolicyGym --skill optimize-crafter-local-symbolic-policy -a codex`. Or copy the skill folder (environments/crafter/crafter/skills/optimize-crafter-local-symbolic-policy in Linzwcs/EvoPolicyGym) into .agents/skills/optimize-crafter-local-symbolic-policy in your project. Codex loads it when a task matches its description.

Can I use Optimize Crafter Local Symbolic Policy 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 Linzwcs/EvoPolicyGym --skill optimize-crafter-local-symbolic-policy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/optimize-crafter-local-symbolic-policy, .gemini/skills/optimize-crafter-local-symbolic-policy, .github/skills/optimize-crafter-local-symbolic-policy and .opencode/skills/optimize-crafter-local-symbolic-policy in your project.

What does Optimize Crafter Local Symbolic Policy need to run?

SKILL.md names no scripts, command-line tools or credentials: Optimize Crafter Local Symbolic Policy is instructions for the agent only.

Does Optimize Crafter Local Symbolic Policy 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 Optimize Crafter Local Symbolic Policy 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 Optimize Crafter Local Symbolic Policy use?

Optimize Crafter Local Symbolic Policy 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 Optimize Crafter Local Symbolic Policy use?

About 805 tokens (SKILL.md is roughly 3.2k 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 Optimize Crafter Local Symbolic Policy?

Skills that share tags, products or a category with Optimize Crafter Local Symbolic Policy: Rl Policy Optimization (aiming-lab/AutoResearchClaw, 15k stars), Implementing Policy As Code With Open Policy Agent (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), SQL Optimization (github/awesome-copilot, 40k stars) and Agent Performance Optimizer (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Optimize Crafter Local Symbolic Policy?

Linzwcs (a GitHub user) maintains it in Linzwcs/EvoPolicyGym, which has 175 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 18, 2026.

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