It Operations
davila7/claude-code-templates
Manages IT infrastructure, monitoring, incident response, and service reliability.
Operate and extend EvoPolicyGym through its public SDK. An agent skill from Linzwcs/EvoPolicyGym.
MITAuto-check passed
Install Evopolicygym
$ npx skills add Linzwcs/EvoPolicyGym --skill evopolicygym -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Linzwcs/EvoPolicyGym evopolicygym --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/Linzwcs/EvoPolicyGym.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/evopolicygym .claude/skills/evopolicygym && 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 "evopolicygym" agent skill from https://github.com/Linzwcs/EvoPolicyGym/tree/main/skills/evopolicygym into .claude/skills/evopolicygym/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evopolicygym", 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/Linzwcs/EvoPolicyGym/tree/main/skills/evopolicygymType 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 Linzwcs/EvoPolicyGym --skill evopolicygym -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Linzwcs/EvoPolicyGym evopolicygym --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Linzwcs/EvoPolicyGym.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/evopolicygym .agents/skills/evopolicygym && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "evopolicygym" agent skill from https://github.com/Linzwcs/EvoPolicyGym/tree/main/skills/evopolicygym into .agents/skills/evopolicygym/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evopolicygym", 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 Linzwcs/EvoPolicyGym --skill evopolicygym -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Linzwcs/EvoPolicyGym evopolicygym --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Linzwcs/EvoPolicyGym.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/evopolicygym .cursor/skills/evopolicygym && 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 "evopolicygym" agent skill from https://github.com/Linzwcs/EvoPolicyGym/tree/main/skills/evopolicygym into .cursor/skills/evopolicygym/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evopolicygym", 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/Linzwcs/EvoPolicyGym.git --path skills/evopolicygym--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 Linzwcs/EvoPolicyGym --skill evopolicygym -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Linzwcs/EvoPolicyGym evopolicygym --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Linzwcs/EvoPolicyGym.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/evopolicygym .gemini/skills/evopolicygym && 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 "evopolicygym" agent skill from https://github.com/Linzwcs/EvoPolicyGym/tree/main/skills/evopolicygym into .gemini/skills/evopolicygym/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evopolicygym", 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 Linzwcs/EvoPolicyGym evopolicygymInstalls 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 Linzwcs/EvoPolicyGym --skill evopolicygym -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Linzwcs/EvoPolicyGym.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/evopolicygym .github/skills/evopolicygym && 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 "evopolicygym" agent skill from https://github.com/Linzwcs/EvoPolicyGym/tree/main/skills/evopolicygym into .github/skills/evopolicygym/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evopolicygym", 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 Linzwcs/EvoPolicyGym --skill evopolicygym -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Linzwcs/EvoPolicyGym evopolicygym --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Linzwcs/EvoPolicyGym.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/evopolicygym .opencode/skills/evopolicygym && 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 "evopolicygym" agent skill from https://github.com/Linzwcs/EvoPolicyGym/tree/main/skills/evopolicygym into .opencode/skills/evopolicygym/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evopolicygym", 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
evopolicygym- GitHub stars
- 175
- Token cost
- ~890 tokens
- SKILL.md length
- 374 words
- Files
- 8 (incl. references)
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Operate and extend EvoPolicyGym through its public SDK. An agent skill from Linzwcs/EvoPolicyGym.
- Host/operator setup
- SKILL.md covers Route the task, Preserve the command and Skill… and Preserve public and security…
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Policy Program evaluation
What it does
Evopolicygym is an agent skill from Linzwcs/EvoPolicyGym. Operate and extend EvoPolicyGym through its public SDK. Use for Host/operator setup, Policy Program evaluation, Coding Agent Run configuration, CodingAgent provider integration, Benchmark distribution authoring, retained Run diagnostics, or Kernel development. Do not use as a Benchmark-specific Policy-strategy Skill inside an active Run.
Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `agents/openai.yaml`, `references/authoring.md` and `references/diagnostics.md`).
The repository describes itself as: EvoPolicyGym is infrastructure for evaluating coding agents and generating training experience through Autonomous Policy Evolution. The licence is MIT.
When your agent uses it
- Host/operator setup
- Policy Program evaluation
- Coding Agent Run configuration
- CodingAgent provider integration
Example prompts
- “/evopolicygym”
Requirements
- Python 3
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
Evopolicygym loads about 890 tokens when it runs, and up to ~6.2k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 374 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 Linzwcs/EvoPolicyGym at commit a3d9669, republished under its MIT licence (© Linzwcs). 374 words, ~890 tokens.
Download SKILL.mdSave it as
.claude/skills/evopolicygym/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- evopolicygym
- description
- Operate and extend EvoPolicyGym through its public SDK. Use for Host/operator setup, Policy Program evaluation, Coding Agent Run configuration, CodingAgent provider integration, Benchmark distribution authoring, retained Run diagnostics, or Kernel development. Do not use as a Benchmark-specific Policy-strategy Skill inside an active Run.
EvoPolicyGym
Use this Skill for caller-side EvoPolicyGym work. Keep Host orchestration, Benchmark behavior, the Coding Agent workspace, and Episode-local Policy execution as separate authority boundaries.
Route the task
Load only the references required by the current task:
- Install or select packages: read references/setup.md.
- Build or directly evaluate a Policy Program: read references/evaluation.md.
- Configure and execute a Coding Agent Run: read references/run.md.
- Integrate another Coding Agent provider: read references/providers.md.
- Author or modify a Benchmark distribution: read references/authoring.md completely before editing it.
- Diagnose a retained Run: read references/diagnostics.md and inspect the records without repairing them.
- Change the Kernel: read the repository
AGENTS.mdandARCHITECTURE.mdbefore editing, then follow their ownership and verification rules.
When a task spans workflows, perform setup or authoring first, direct Evaluation second, and a Coding Agent Run last.
Preserve the command and Skill boundaries
- Treat
evopolicygymas the Host/operator command presentation and use the public Python SDK for Evaluation, Run, and authoring workflows. - Treat
evopolicygym-sessionas an Agent-only client projected into one active Run. The Host-generated task is authoritative for its current submit, finish, workspace, and budget instructions. - Do not invoke Session commands as an external operator or duplicate their syntax in a provider integration.
- Pass Benchmark-specific Skills explicitly as immutable
AgentSkill.from_directory()inputs torun(). They are independent Run inputs, not Benchmark properties, and are never exposed to the Policy. - Do not use this general Skill as a substitute for a task-specific Benchmark-strategy Skill inside a Run.
Show full SKILL.md (135 more words)Show less
Preserve public and security boundaries
- Confirm Python 3.12, the installed EvoPolicyGym version, and the selected Environment distribution before constructing imports or commands.
- Treat every Environment as an independently installable distribution. Read its package documentation instead of guessing imports, factories, extras, or task configuration.
- Use only the supported public SDK. External distributions may import
evopolicygym.authoring; they must not import private_...modules. - Keep Policy-visible values within the bounded
PolicyValueABI. Never cross the Policy boundary with Host paths, descriptors, credentials, private Episode seeds, Case identity, scorer objects, or custom Python objects. - Treat
ProcessExecution.unsafe()as an acknowledgement, not isolation. The Agent and Policy execute with the current operating-system user's authority. - Never silently replace a requested virtualization profile with local process execution.
Follow the selected reference's workflow-specific verification and reporting checklist. Report only fields relevant to the operation performed.
© 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
SKILL.md and 7 other files (references) in skills/evopolicygym of Linzwcs/EvoPolicyGym.
- SKILL.md
- agents/openai.yaml
- references/authoring.md
- references/diagnostics.md
- references/evaluation.md
- references/providers.md
- references/run.md
- references/setup.md
Open the folder on GitHubat commit a3d9669
Compare with similar skills
Evopolicygym 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 |
|---|---|---|---|---|---|---|
| Evopolicygym this skillLinzwcs/EvoPolicyGym | 175 | — | ~890 | Automated safety check: Pass | MIT | |
| It Operationsdavila7/claude-code-templates | 33k | 1 repos | ~3.7k | Automated safety check: Pass | MIT | |
| Cross Host Federationruvnet/ruflo | 74k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Operator Approval Loopaffaan-m/ECC | 276k | — | ~3.3k | Automated safety check: Pass | MIT | |
| Business Operations Skillsalirezarezvani/claude-skills | 28k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Kubernetes Operatoralirezarezvani/claude-skills | 28k | — | ~2.8k | Automated safety check: Pass | MIT |
Similar skills
Cross Host Federation
ruvnet/ruflo
Join and operate a signed cross-host agentbbs federation, and coordinate work claims across nodes.
Operator Approval Loop
affaan-m/ECC
Operator approval contract with internal filing notices for agent-drafted outbound messages, hashed drafts, epoch-keyed decisions, durable delivery claims and receipts, and a pre-draft baseline gate.
Business Operations Skills
alirezarezvani/claude-skills
A skill your agent uses when running, diagnosing, or designing internal business operations — process documentation, vendor SLAs, capacity planning, internal comms, SOP/runbook authoring…
Kubernetes Operator
alirezarezvani/claude-skills
A skill your agent uses when building a Kubernetes Operator — custom controllers that reconcile CRD state.
Escaping Containers To Host
mukul975/Anthropic-Cybersecurity-Skills
Exploits privileged pods, host mounts, runC CVEs, and exposed Docker sockets to break out of a container and reach the underlying host during an authorized container-security assessment.
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.
Optimize Crafter Local Symbolic Policy
Linzwcs/EvoPolicyGym
Improve an EvoPolicyGym Policy Program for Crafter local-symbolic-v1 observations.
Optimize Crafter Policy
Linzwcs/EvoPolicyGym
Improve an EvoPolicyGym Policy Program for the additive RGB Crafter survival-development Benchmark.
Optimize Nethack Policy
Linzwcs/EvoPolicyGym
Improve an EvoPolicyGym Policy Program for the deterministic NLE NetHackScore Benchmark.
Questions about Evopolicygym
What does Evopolicygym do?
Operate and extend EvoPolicyGym through its public SDK. An agent skill from Linzwcs/EvoPolicyGym. Evopolicygym is an agent skill from Linzwcs/EvoPolicyGym. Operate and extend EvoPolicyGym through its public SDK.
When should I use Evopolicygym?
Evopolicygym fits situations like: host/operator setup; policy Program evaluation; coding Agent Run configuration; codingAgent provider integration.
How do I install Evopolicygym in Claude Code?
Run `npx skills add Linzwcs/EvoPolicyGym --skill evopolicygym -a claude-code`. Or copy the skill folder (skills/evopolicygym in Linzwcs/EvoPolicyGym) into .claude/skills/evopolicygym in your project. Claude Code loads it when a task matches its description.
How do I install Evopolicygym in Codex?
Run `npx skills add Linzwcs/EvoPolicyGym --skill evopolicygym -a codex`. Or copy the skill folder (skills/evopolicygym in Linzwcs/EvoPolicyGym) into .agents/skills/evopolicygym in your project. Codex loads it when a task matches its description.
Can I use Evopolicygym 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 evopolicygym -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evopolicygym, .gemini/skills/evopolicygym, .github/skills/evopolicygym and .opencode/skills/evopolicygym in your project.
What does Evopolicygym need to run?
SKILL.md names no scripts, command-line tools or credentials: Evopolicygym is instructions for the agent only. Our summary lists: Python 3.
Does Evopolicygym 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 Evopolicygym 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 Evopolicygym use?
Evopolicygym 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 Evopolicygym use?
About 890 tokens (SKILL.md is roughly 3.6k 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 5.3k tokens, read only when the agent opens those files.
What are the alternatives to Evopolicygym?
Skills that share tags, products or a category with Evopolicygym: It Operations (davila7/claude-code-templates, 33k stars), Cross Host Federation (ruvnet/ruflo, 74k stars), Operator Approval Loop (affaan-m/ECC, 276k stars) and Business Operations Skills (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Evopolicygym?
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.