How do I install the Create Skill Proxy En skill?

Run npx skillmds@latest add roebi/create-skill-proxy-en in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Create Skill Proxy En safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Create Skill Proxy En?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Create Skill Proxy En free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under CC BY-NC-SA 4.

Who published Create Skill Proxy En?

roebi (@roebi) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Create Skill Proxy En by roebi — Agent Skill

Name: Create Skill Proxy En
Author: roebi

Create Skill Proxy En

Creates a local proxy skill that wraps a remote Agent Skill from any GitHub repository. The proxy pins the remote skill to an exact commit hash and SHA-256 checksum so the agent verifies content integrity on every use. Use when a user wants to add an external skill to their skill library, proxy a remote skill, pin and trust a skill from GitHub, or wrap a foreign skill safely. Trigger phrases: "proxy this skill", "add external skill", "wrap remote skill", "pin this skill from GitHub".

roebi 035c1f0 6 files · 39.4 KB Updated Sep 17, 2026

File contents

Create Skill Proxy

Creates a local <n>-proxy skill that wraps a remote Agent Skill.

⚠️ Liability disclaimer

The creator of the 'Skill Proxy' is not liable for any damages arising from the use of this 'Skill Proxy'. The risk and responsibility lies exclusively with the user who uses this 'Skill Proxy'. If the 'Skill Proxy' user is an agent, then the user who is responsible for that agent bears the responsibility.

What this skill does

The proxy pins the remote skill to a specific commit hash and SHA-256 checksum. Every time the agent activates the proxy, it fetches the remote SKILL.md and verifies the checksum before following any instructions. If the checksum does not match, the agent stops and alerts the user.

This follows the Page Object Pattern — the proxy hides where a skill lives while keeping all trusted external skills in one place under your control.

Inputs

Parameter	Required	Description
`REMOTE_URL`	Yes	Any GitHub URL pointing to the remote skill (see URL forms below)
`OUTPUT_DIR`	No	Parent directory to write the proxy skill into (default: `./skills`)

Accepted URL forms

All five forms are accepted and translated automatically:

Input form	Example
Repo root	`https://github.com/observerw/skill-container`
Tree root	`https://github.com/observerw/skill-container/tree/main`
Tree path	`https://github.com/observerw/skill-container/tree/main/skills/my-skill`
Blob file	`https://github.com/observerw/skill-container/blob/main/SKILL.md`
Raw URL	`https://raw.githubusercontent.com/observerw/skill-container/main/SKILL.md`

Workflow

uv run scripts/create-proxy.py \
  --url "https://github.com/observerw/skill-container" \
  --output-dir ./skills

The script:

Translates input URL to raw content URL (see references/url-translation.md)
Fetches SKILL.md content from remote
Validates frontmatter against agentskills.io spec — aborts if invalid
Fetches current HEAD commit hash via GitHub API
Computes SHA-256 of the fetched content
Generates <n>-proxy/SKILL.md with pinned commit URL and checksum
Runs skills-ref validate on the generated proxy skill
Prints the created skill path and next steps

Re-verifying and updating proxies

# Re-verify: check if remote content still matches pinned checksum
uv run scripts/verify-proxy.py --proxy ./skills/skill-container-proxy

# Update: re-fetch, re-validate, update commit pin and checksum
uv run scripts/update-proxy.py --proxy ./skills/skill-container-proxy

Run verify-proxy.py periodically or in CI to detect upstream changes. Run update-proxy.py only after consciously reviewing the upstream changes.

Reference files

references/url-translation.md — full URL translation rules and examples
references/proxy-format.md — exact format of generated proxy SKILL.md

---name: create-skill-proxy-endescription: Creates a local proxy skill that wraps a remote Agent Skill from any GitHub repository. The proxy pins the remote skill to an exact commit hash and SHA-256 checksum so the agent verifies content integrity on every use. Use when a user wants to add an external skill to their skill library, proxy a remote skill, pin and trust a skill from GitHub, or wrap a foreign skill safely. Trigger phrases: "proxy this skill", "add external skill", "wrap remote skill", "pin this skill from GitHub".license: CC BY-NC-SA 4.0---# Create Skill ProxyCreates a local `<n>-proxy` skill that wraps a remote Agent Skill.## ⚠️ Liability disclaimerThe creator of the 'Skill Proxy' is not liable for any damages arisingfrom the use of this 'Skill Proxy'. The risk and responsibility liesexclusively with the user who uses this 'Skill Proxy'. If the 'Skill Proxy'user is an agent, then the user who is responsible for that agent bearsthe responsibility.## What this skill doesThe proxy pins the remote skill to a specific commit hash and SHA-256checksum. Every time the agent activates the proxy, it fetches the remoteSKILL.md and verifies the checksum before following any instructions.If the checksum does not match, the agent stops and alerts the user.This follows the Page Object Pattern — the proxy hides where a skill liveswhile keeping all trusted external skills in one place under your control.## Inputs| Parameter | Required | Description ||-----------|----------|-------------|| `REMOTE_URL` | Yes | Any GitHub URL pointing to the remote skill (see URL forms below) || `OUTPUT_DIR` | No | Parent directory to write the proxy skill into (default: `./skills`) |## Accepted URL formsAll five forms are accepted and translated automatically:| Input form | Example ||-----------|---------|| Repo root | `https://github.com/observerw/skill-container` || Tree root | `https://github.com/observerw/skill-container/tree/main` || Tree path | `https://github.com/observerw/skill-container/tree/main/skills/my-skill` || Blob file | `https://github.com/observerw/skill-container/blob/main/SKILL.md` || Raw URL | `https://raw.githubusercontent.com/observerw/skill-container/main/SKILL.md` |## Workflow```bashuv run scripts/create-proxy.py \ --url "https://github.com/observerw/skill-container" \ --output-dir ./skills```The script:1. Translates input URL to raw content URL (see `references/url-translation.md`)2. Fetches `SKILL.md` content from remote3. Validates frontmatter against agentskills.io spec — aborts if invalid4. Fetches current HEAD commit hash via GitHub API5. Computes SHA-256 of the fetched content6. Generates `<n>-proxy/SKILL.md` with pinned commit URL and checksum7. Runs `skills-ref validate` on the generated proxy skill8. Prints the created skill path and next steps## Re-verifying and updating proxies```bash# Re-verify: check if remote content still matches pinned checksumuv run scripts/verify-proxy.py --proxy ./skills/skill-container-proxy# Update: re-fetch, re-validate, update commit pin and checksumuv run scripts/update-proxy.py --proxy ./skills/skill-container-proxy```Run `verify-proxy.py` periodically or in CI to detect upstream changes.Run `update-proxy.py` only after consciously reviewing the upstream changes.## Reference files- `references/url-translation.md` — full URL translation rules and examples- `references/proxy-format.md` — exact format of generated proxy SKILL.md

Frequently asked questions