Skip to content

xonika9/agent-skills / skills/x9-onboarding

x9-onboarding

Verified

Use after installing or updating `x9-*` skills to check their readiness and compare the current harness with the bundled x9 configuration profile — «проверь готовность x9-скиллов», «настрой Codex как у автора», "check installed x9 skills", "apply the recommended harness settings". Do not use for general environment diagnosis, account authorization, or unrelated configuration editing.

references/claude-code.md

View on GitHub
# Claude Code adapter

Use this adapter only from Claude Code. First inspect Claude Code's live skill, agent,
and tool interfaces. Do not rely on remembered CLI flags, models, configuration shapes, or
filesystem discovery as runtime evidence.

Check requirements under [Runtime Checks and Guidance](declarations.md#runtime-checks-and-guidance).

## Configuration

Use `profiles/claude.json` with `~/.claude/settings.json`. Confirm current setting names,
scope, precedence, model aliases, and installed plugin identifiers through Claude Code's
official settings documentation and live interfaces before proposing profile paths. Do
not read or edit `~/.claude.json`, `settings.local.json`, project settings, managed
settings, SSH data, unrelated environment values, hooks, or status-line commands.

The sole environment path in the public profile is
`env.CLAUDE_CODE_AUTO_COMPACT_WINDOW`. Compare and merge that exact path without reading,
reporting, or modifying any other environment entry.

Apply an `enabledPlugins` entry only when the exact plugin is already installed; this
skill does not install plugins or marketplaces.

After approval, merge supported paths under the
[shared configuration contract](configuration.md). Validate the result as JSON without
echoing values. Report when a new Claude Code session is required; do not start one.
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: 471kUpdated 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