AILANG Post-Release Tasks

Automate post-release eval baselines, dashboard updates, and changelog metrics.

33|5|Updated Sep 26, 2025
One-click install
npx skills add https://github.com/sunholo-data/ailang --skill ailang-post-release-tasks
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: AILANG Post-Release Tasks
Source: https://github.com/sunholo-data/ailang/tree/main/.claude/skills/post-release
Command: npx skills add https://github.com/sunholo-data/ailang --skill ailang-post-release-tasks

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and resources (resource) components.

What problem does it solve?

Post-release tasks like running evaluation baselines, updating dashboards, and extracting metrics for changelogs are critical but often manual, time-consuming, and prone to errors. This Skill automates these essential steps, ensuring accurate and up-to-date post-release documentation.

Core Features & Use Cases

  • Automated Eval Baselines: Run comprehensive evaluation baselines with all production models for both AILANG and Python, providing robust performance data.
  • Dashboard Updates: Automatically update the website benchmark dashboard, preserving historical data and clearing caches, ensuring the public-facing metrics are current.
  • Changelog Metric Extraction: Extract and format key benchmark metrics for easy inclusion in CHANGELOG.md, including automatic comparison with previous versions, eliminating manual data entry.
  • Use Case: After a successful release, when a user says "run post-release tasks for v0.3.14," this Skill will execute the full eval baseline, update the website dashboard, and provide a ready-to-paste changelog entry, ensuring all post-release documentation is accurate and up-to-date.

Quick Start

Run evaluation baseline for a release version (all models)

.claude/skills/post-release/scripts/run_eval_baseline.sh 0.3.14 --full

Update website benchmark dashboard with new release data

.claude/skills/post-release/scripts/update_dashboard.sh 0.3.14

Extract benchmark metrics for CHANGELOG.md

.claude/skills/post-release/scripts/extract_changelog_metrics.sh

Frequently Asked Questions about AILANG Post-Release Tasks

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate post-release evaluation and dashboard updates after deploying a new version?

Post-release automation runs comprehensive evaluation baselines across all production models, updates your website benchmark dashboard with new metrics, and extracts key data for changelog entries—eliminating manual steps and reducing errors after each release.

What benchmark metrics can I extract automatically for my CHANGELOG after a release?

Extract benchmark metrics through automated comparison with previous versions, pulling performance data from the full 46-benchmark evaluation suite across all production models, then format results ready to paste into CHANGELOG.md without manual data entry.

Can I run evaluation baselines for all production models at once during post-release?

Yes, the `--full` flag runs comprehensive evaluation baselines across all production models for both AILANG and Python, providing complete performance data needed for accurate post-release documentation and dashboard updates.

How do I update the website benchmark dashboard and preserve historical release data?

Dashboard updates automatically merge new release metrics while preserving historical data and clearing caches, ensuring your public-facing benchmark metrics stay current without losing past performance records.

What pre-flight checks run before executing post-release tasks?

Pre-flight checks validate your environment and Git status before running post-release tasks, enforcing requirements like version format (with or without leading 'v'), full benchmarking completion, and JSON validation to prevent incomplete or corrupted releases.

Does post-release automation handle design document migration and Git commits?

Yes, the workflow moves design docs from planned to implemented status, runs docs-sync to verify website accuracy, and commits all changes to Git, completing the full post-release cycle in one execution.