- Extract shared repo-checkout logic into .gitea/ci/prepare_repo.sh,
removing ~47 lines of duplication from standards-check.yml and test.yml
- Remove unused TEST_WORKSPACE env var from test.yml
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Remove docs/tsl/syntax_book/ (superseded by docs/tsl/syntax/)
- Remove data/tsl_reference_catalog_source/ (catalog already generated
into docs/tsl/reference/catalog/, source no longer needed)
- Remove scripts/build_tsl_reference_catalog.ps1 (build script for
the above source)
- Remove test assertion that referenced the deleted data/ source index
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Move all third-party skills from codex/skills/ to codex/skills/thirdparty/
- Move .sources/ to codex/skills/thirdparty/.sources/
- Delete systematic-debugging/CREATION-LOG.md (internal dev note, not skill content)
- Update sync_thirdparty_skills.sh paths and conflict detection
- Update thirdparty_skills.json source_list paths
- Update install_skills_action to collect from both own and thirdparty dirs,
logging [thirdparty] tag for third-party installs
- Update SKILLS.md directory structure docs
- Update tests to reflect new paths
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
remove obsolete main_language placeholders and language summary template text
limit generated .agents guidance to configured langs and normalize AGENT_RULES trailing newlines
document install_skills no_backup behavior and refresh tests for deployment links and sync flows
Unhide the tracked docs and test updates that were left under assume-unchanged, remove the shipped tsl-guide skill, and align the deploy_root-related test coverage with the current external-clone rules.
replace the superpowers-only workflow with a manifest-driven pipeline
sync ui-ux-pro-max into codex/skills and document source lists
fix the prettier path test so the Python suite passes on Windows
replace the old select/record progress flow with a single main_loop claim/finish CLI.
route template execution through main_loop only, remove the legacy plan_progress entry points, and update tests to enforce the new behavior.
run the thirdparty superpowers snapshot updater on a daily schedule.
trigger sync-superpowers automatically when thirdparty/skill is updated and cover the new automation with workflow tests.
remove the stale superpowers list block from SKILLS.md so the document routes to the source list only.
clear assume-unchanged and skip-worktree flags in the sync workflow before refreshing the workspace, and add a regression test for that safeguard.
normalize Windows path-like TOML config values, regenerate .agents/index.md on sync, keep the SKILLS.md superpowers section route-only, and ignore generated Python cache dirs.
add regression coverage for load_config() and the standards sync behavior touched by these fixes.
csh
ci[bot]
csh
playbook-bot