Claude Skills by inho-team

Draft, review, and create one GitHub issue through the optional Qissue adapter and an existing gh CLI login. Use when the user asks to file or report a bug, feature request, or question, including "create an issue", "file a bug", "이슈 올려줘", or "버그 리포트".

First of two skills declaring the same name to trigger the duplicate-name violation.

Second of two skills declaring the same name to trigger the duplicate-name violation.

Body. Description is intentionally empty to trigger the empty-description violation.

Name is intentionally empty to trigger the empty-name violation.

A valid control fixture whose name matches its directory and has a non-empty description.

The name field does not match the directory name to trigger the mismatch violation.

This SKILL.md intentionally has no YAML front matter block.

Quoted name and description must be treated as unquoted YAML scalars, so this is a valid control (no violation).

Test fixture for Qcommit policy compliance — all required sentences present, no forbidden phrases in policy.

Test fixture for Qcommit policy violation — missing required sentence and forbidden phrase present.

Test fixture for the Korean-inversion exploit — negation marker appears AFTER the forbidden phrase, so the line is a mandate, not a prohibition. Must be detected.

Test fixture for the pre-heading exploit — forbidden phrase placed before any policy heading (former section-scoping blind spot). Must be detected.

Sets up Claude Code and Codex shell shortcuts. Use when asked for Claude or Codex terminal aliases, cc/cx shortcuts, shell launcher setup, or restoration of the Qcc-setup workflow.

Use when the user says 'commit', 'push', or 'save changes'. Creates human-written commits with no Co-Authored-By, AI-style language, or emoji.

Context preservation and session handoff. Use when the user wants to save state, handoff, save context, end session, or continue later.

Critical thinking verification for SIVS stages. Spawns adversarial sub-agents to stress-test specs, implementations, and merge readiness. Also hosts structured debate and evidence-backed risk proof modes. Use for 'review critically', 'stress test this', 'devil advocate', debates, risk proof, or auto-invoked by Qgenerate-spec, Qexecute -verify, Esupervision-orchestrator.

Opens a local read-only dashboard for QE database state. Use when asked to view, inspect, or check the QE DB, dashboard, stored tasks, sessions, plans, verification results, or .qe state.

Use when a routed pipeline or an active task artifact (TASK_REQUEST UUID) needs execution or the -verify quality loop — router-owned internal PSE unit. Use Qgoal to enter.

Use when a routed goal or plan handoff needs TASK_REQUEST and VERIFY_CHECKLIST documents — router-owned internal PSE unit. Use Qgoal to enter; use Qplan for roadmap work.

Explicit single-Goal alias for Qplan. Use when the user enters Qgoal with the active client prefix.

Use when starting or resuming a Plan. Runs bounded tacit-knowledge intake when needed, creates or updates a roadmap, then advances one verified Goal at a time. Use Qgoal only as a goal-intake alias.

Use when resuming work, restoring context, continuing from where you left off, or loading a previous session after compaction or a session break.

Use for "update plugin", "upgrade", "update qe", "update codex", or "codex plugin". Updates marketplace metadata/cache, framework files, installed Codex assets, and the bridge for the current install.

Shows the current QE Framework version. Use when asked 'what version', 'qe version', 'show version', or 'check version'.