Skip to content

JPeetz/agent-skills / skills/skill-development/skill-portability-and-packaging

skill-portability-and-packaging

Verified

Use this skill when packaging or porting agent skills.

FileKindSize
CHANGELOG.mdmarkdown1.4 KB
LICENSEother1.1 KB
SKILL.mdskill md17.4 KB
evals/evals.jsonconfig2.5 KB
references/sources.mdmarkdown3.3 KB
scripts/check_package.pyexecutablescript5.1 KB

CHANGELOG.md

View on GitHub
# Changelog

## [1.0.0] - 2026-11-13

- Initial release of the Skill Portability and Packaging skill.
- Covers the spec's hard rules (name/folder equality, 64-char name, 1024-char
  description) and the canonical directory layout.
- Documents the per-host install matrix for Claude Code, Codex, Cursor, Gemini
  CLI, Antigravity, GitHub Copilot, OpenCode, Windsurf, OpenClaw (including its
  root precedence and symlink containment rule), and Hermes.
- Adds description budgeting guidance: routing triggers first, tail trimming per
  host truncation limits.
- Adds packaging routes for loose skills, Claude Code plugins
  (`.claude-plugin/plugin.json`), and marketplaces (`.claude-plugin/marketplace.json`),
  plus `npx skills add` installation.
- Adds portability hazard sweep (absolute paths, host tool names, interpreters,
  frontmatter dialects, file modes, case sensitivity, precedence collisions,
  size caps).
- Adds the install verification loop that proves the loaded copy is the edited copy,
  and security packaging rules for published skills.
- Ships `scripts/check_package.py`, a stdlib-only pre-flight check (name/folder,
  charset, description budget, version format, secret and absolute-path sweep,
  plugin-layout mistake detection).
- Includes `evals/evals.json` with three grading scenarios and
  `references/sources.md` with the upstream specifications and host docs.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall