AILANG Post-Release Tasks

github:sunholo-data/ailang · first committed 2025-10-19 · source · badge

Run automated post-release workflow (eval baselines, dashboard, docs) for AILANG releases. Executes 46-benchmark suite (medium/hard/stretch) + full standard eval with validation and progress reporting. Use when user says "post-release tasks for vX.X.X" or "update dashboard". Fully autonomous with pre-flight checks.

Skill Health: not yet scored

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

Version history

42 commits to this file on GitHub (newest first).

2026-08-04 · commit f574c4b · chore(eval): v0.32.0 curation cycle — 4 promotions, 8 demotions
2026-08-03 · commit 7c938c4 · docs(changelog): v0.32.0 header + default-on/DeepSeek entries, fix stale links
2026-08-03 · commit 59b18b9 · docs(eval): M4 — SKILL.md real cost data, CHANGELOG, first live comparison
2026-07-21 · commit 93d90f8 · feat(eval): retire per-cycle benchmark data churn (W4+W5)
2026-07-20 · commit e77ec5b · feat(eval-web): OS leaderboard release-evolution view + automatic release pickup
2026-07-11 · commit c533bb5 · feat(eval): unified local+cloud dashboard — one leaderboard for on-device + API
2026-07-11 · commit 8cb1836 · feat(eval): per-language ELO + agent-mode redesign + frontier re-tier
2026-07-11 · commit c86ef29 · docs(post-release): frontier tier + v0.29.0 re-tier counts in baseline workflow
2026-06-23 · commit 7fddf74 · data(stats): backfill codebase-stats history v0.15→v0.24, refresh page + enforce in post-release
2026-06-16 · commit 743ee0b · feat(eval): per-release local-model eval trend (M-EVAL-OS-LONGITUDINAL)
2026-06-12 · commit b8a4fbf · docs(post-release): never run smoke tier for cloud models
2026-06-09 · commit a16cb9e · fix(eval): exclude non-benchmark meta-file events.yml from nightly set
2026-06-09 · commit 7cb6993 · feat(eval): nightly runs smoke+core with baseline-gated regression alerts
2026-06-05 · commit 3f52e61 · eval: refresh post-release model suites to modern OS + fix agent harness routing
2026-06-05 · commit abba6ab · docs: codex agent CLI needs one-time --with-api-key login (post-release prereqs)
2026-06-05 · commit aec0c94 · docs: remove gemini CLI from agent prereqs (deprecated, uninstalled)
2026-04-26 · commit 5a77eee · docs+skills: post-release skill update, benchmark audit script, EXECUTOR_SHAPE refresh
2026-04-24 · commit e11b410 · feat(eval): add lang_harness_suite + v0.14.1 full baseline (Steps 1+2+3)
2026-04-23 · commit 924f182 · benhcmrk docs and ra data
2026-04-22 · commit 35092b8 · brains
2026-04-21 · commit ab1b91c · post-release: tier-aware eval baseline (v0.14.0 tier system)
2026-04-13 · commit ca477d8 · skills dynamic
2026-03-06 · commit 6f45a68 · Archive CHANGELOG into themed files and update docs search
2026-02-14 · commit 8ac0985 · hook up ailang chains to evals
2026-02-11 · commit 0ef26ec · reproducability
2025-12-19 · commit b021ee4 · planning out features for axiom
2025-12-14 · commit c8b5092 · skills vs agents
2025-12-10 · commit 104059b · Release v0.5.9
2025-12-08 · commit b7e0086 · feat(post-release): smarter design doc cleanup with status checking
2025-12-08 · commit 1dfa898 · feat(post-release): auto-move design docs to implemented folder
2025-12-05 · commit bd01c54 · clean up roadmap docs
2025-12-04 · commit e18a23c · Organize design docs and add post-release cleanup script
2025-11-29 · commit d8afa90 · post release improvements
2025-11-28 · commit 8a26c44 · evals
2025-11-16 · commit 4ffc4f0 · benchmarks
2025-11-01 · commit 3e82e3a · Implement P0 and P1 post-release workflow improvements
2025-10-29 · commit 491b58f · benchmarks
2025-10-29 · commit 8ecb538 · new benchmark analysis
2025-10-28 · commit 13636a2 · skillzzz
2025-10-27 · commit d366f3a · benchmark
2025-10-21 · commit 66f2237 · Update post-release SKILL.md with new capabilities
2025-10-19 · commit 1996657 · add claude skills

Archived snapshots