JPeetz/agent-skills / skills/skill-development/skill-portability-and-packaging
skill-portability-and-packaging
VerifiedUse this skill when packaging or porting agent skills.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 1.4 KB |
| LICENSE | other | 1.1 KB |
| SKILL.md | skill md | 17.4 KB |
| evals/evals.json | config | 2.5 KB |
| references/sources.md | markdown | 3.3 KB |
| scripts/check_package.pyexecutable | script | 5.1 KB |
references/sources.md
View on GitHub# Sources
Upstream specifications and host documentation behind the portability rules in
this skill. Host paths and CLI flags change; re-check these before publishing a
package that depends on an exact path.
## Specification and format
- **Agent Skills specification** — https://agentskills.io/specification
Canonical layout, `name` constraints (1–64 chars, `a-z0-9-`, no leading/trailing
hyphen, no `--`, must match parent dir), `description` 1–1024 chars,
`compatibility` ≤500 chars, `metadata` string map, experimental `allowed-tools`,
progressive disclosure (~100-token metadata, <5000-token body, <500 lines).
- **Agent Skills reference implementation** — https://github.com/agentskills/agentskills
`skills-ref validate ./my-skill`.
## Host paths and behavior
- **Skills Paths for Other AI Coding Assistants** (VoltAgent/awesome-agent-skills
README) — https://github.com/VoltAgent/awesome-agent-skills#skills-paths-for-other-ai-coding-assistants
Table of project/global roots for Claude Code, Codex, Cursor, Gemini CLI,
Antigravity, GitHub Copilot, OpenCode, Windsurf; quality criteria including the
"no absolute paths" rule.
- **Claude Code skills** — https://code.claude.com/docs/en/skills
- **Codex skills** — https://developers.openai.com/codex/skills
- **Cursor skills** — https://cursor.com/docs/context/skills
- **Gemini CLI skills** — https://geminicli.com/docs/cli/skills/
- **GitHub Copilot skills** — https://docs.github.com/en/copilot/concepts/agents/about-agent-skills
- **OpenCode skills** — https://opencode.ai/docs/skills
- **Windsurf Cascade skills** — https://docs.windsurf.com/windsurf/cascade/skills
- **Antigravity skills** — https://antigravity.google/docs/skills
- **OpenClaw — creating skills** — https://docs.openclaw.ai/tools/creating-skills
Workspace `skills/` layout, `{baseDir}` placeholder, OpenClaw-only frontmatter
keys (`user-invocable`, `command-dispatch`, `requires.bins`).
- **OpenClaw — skills config** — https://docs.openclaw.ai/tools/skills-config
Root precedence, `skills.load.extraDirs`, symlink containment and
`allowSymlinkTargets`.
## Packaging and distribution
- **vercel-labs/skills (npx skills)** — https://github.com/vercel-labs/skills
`add` / `use` / `list` / `find` / `remove` / `update` / `init`, `-g`, `-a`,
`-s`, `--copy`, symlink-vs-copy install methods, download and extract caps.
- **skills.sh directory** — https://skills.sh
- **anthropics/skills** — https://github.com/anthropics/skills
Reference skill collection (docx, pdf, pptx, skill-creator, template); layout
and frontmatter conventions used by first-party skills.
- **Claude Code plugins overview** — https://code.claude.com/docs/en/plugins/overview
`.claude-plugin/plugin.json`, root-level `skills/`, `agents/`, `hooks/`,
`.mcp.json`; `/plugin-name:skill-name` invocation.
- **Claude Code — create a marketplace** — https://code.claude.com/docs/en/plugins/create-marketplace
`.claude-plugin/marketplace.json` with `name`, `owner`, `plugins[]`; relative
`source` paths without `..`; `plugin@marketplace` install ids.
## Repo-local conventions
- **JPeetz/agent-skills** — https://github.com/JPeetz/agent-skills
Category layout `skills/<category>/<skill>/`, 60-character description budget,
`LICENSE` / `CHANGELOG.md` / `evals/evals.json` / `references/` package shape,
`scripts/validate_skill.py` gate.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |