Skillforge Repo To Skill
Use this skill when the task is to turn a GitHub repository or local codebase into a portable agent skill for Claude, Codex, GitHub Copilot, OpenClaw, Hermes, or other Agent Skills compatible runtimes.
Install
$ agentstack add skill-xiaokillua-skillforge-skillforge-repo-to-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-xiaokillua-skillforge-skillforge-repo-to-skill) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
SkillForge Repo to Skill
Use this skill when the user wants to package a repository as an agent skill instead of manually writing SKILL.md.
Workflow
- Run
skillforge inspect SOURCEto understand the repo first. - Run
skillforge doctorif the user needs to know which local runtimes are ready. - Review the extracted install commands, usage commands, and audit severity.
- Run
skillforge build SOURCE --target TARGET --output DIR --verifyas the default path. - If you need a second pass later, run
skillforge verify PATH --target TARGETagainst the generated result. - If the user wants a shareable artifact, run
skillforge report SOURCE --target TARGET --artifacts DIR --output FILE. - Open the generated
references/SECURITY-AUDIT.mdbefore trusting upstream scripts. - Deliver the target-specific folder, and use the
.skillarchive only as an optional sharing artifact.
Common Commands
Inspect:
skillforge inspect owner/repoCheck local runtime readiness:
skillforge doctor
skillforge doctor --markdownBuild everything:
skillforge build owner/repo --target all --output ./dist --verifyBuild a Codex-ready layout:
skillforge build owner/repo --target codex --output ./dist --verifyBuild a Claude Code-ready layout:
skillforge build owner/repo --target claude --output ./dist --verifyGenerate a shareable report:
skillforge report owner/repo --target all --artifacts ./dist --output ./skillforge-report.mdVerify the generated bundle:
skillforge verify ./dist --target claudeSafety Notes
- Do not ignore
highaudit findings without human review. - Keep the generated skill concise and point to
references/for detail. - If the repo is a monorepo, verify that the extracted commands match the correct package or service.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: xiaokillua
- Source: xiaokillua/skillforge
- License: MIT
- Homepage: https://github.com/xiaokillua/skillforge/blob/main/docs/TUTORIAL.md
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.