skills/version/SKILL.md
Use when you need to check the current plugin version, latest published release, and what changed between them.
npx skillsauth add seokan-jeong/team-shinchan team-shinchan:versionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
node -e "const p=JSON.parse(require('fs').readFileSync('${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json','utf-8'));console.log(p.version)"
Store result as CURRENT_VERSION.
gh release list --repo seokan-jeong/team-shinchan --limit 1 --json tagName,publishedAt --jq '.[0]' 2>/dev/null || echo '{"error":"gh not available or no releases"}'
Extract tag name and strip leading v to get PUBLISHED_VERSION.
Extract publishedAt as PUBLISHED_DATE.
If gh fails or no releases found, set PUBLISHED_VERSION = "unknown".
Compare CURRENT_VERSION vs PUBLISHED_VERSION:
CURRENT_VERSION > PUBLISHED_VERSION: local is ahead (unreleased changes exist)CURRENT_VERSION == PUBLISHED_VERSION: local is up to dateCURRENT_VERSION < PUBLISHED_VERSION: local is behind (update available)If versions differ, read CHANGELOG.md and extract all entries between the two versions.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Team-Shinchan Version Info
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Local version: v{CURRENT_VERSION}
Published version: v{PUBLISHED_VERSION} ({PUBLISHED_DATE})
Status: {ahead|up to date|behind}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
If versions differ, also show:
Changes between v{LOWER} and v{HIGHER}:
{changelog entries — keep concise, show Added/Changed/Fixed sections}
If local is behind, suggest:
To update: claude plugin update team-shinchan
If local is ahead, suggest:
Unreleased changes detected. Use /team-shinchan:release --version <X.Y.Z> to publish.
development
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, a completeness critic, and a schema-validated rubric judge. Opt-in main-loop Workflow tier.
data-ai
Deterministic loop-until-done for high-stakes long-running tasks — a worker/verifier loop the script bounds by iteration cap, token budget, and stagnation, closed by an Action-Kamen gate. Opt-in main-loop Workflow tier.
testing
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.
development
Deterministic competitive code tournament — N builders independently solve one task and return patches, an Action-Kamen judge scores them head-to-head, the winner is picked by score and applied. Opt-in main-loop Workflow tier.