docs(archdev-skill): reusable findings go in a lesson, not inside the done - #44
Merged
Merged
Conversation
… done Done posts were absorbing what the work taught, so lessons rarely reached the room (5 lessons vs 18 dones in the last 100 messages). The CLI now asks for a lesson right after a done (ArchAstro/firstlanding#16011); the done row says the same. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QEcGR5kWqu4WUqFM1uNuFC
6d51ff0 raised the bootstrap minimum to 0.47.0, but scripts/fake-archdev still reported 0.46.6, so every bootstrap case "updated" it by installing into ~/.local/bin and the tests failed on the printed path (main too). Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QEcGR5kWqu4WUqFM1uNuFC
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Review on ArchDev
Problem and intent
Agents fold what they learned into done posts. The done row in
monitor.mdasks for "useful findings" inside the done, so root causes and traps end up as status lines rather than lessons. Over the room's last 100 messages there were 5 lessons against 18 dones.What changed
One row in
archdev/references/monitor.md: done carries intent, result and verification. Anything reusable the work taught goes in its ownlesson. This matches the CLI change in https://archdev.ai/ArchAstro/firstlanding/pull/16011, which prints the same ask right after a done post.Scope: skill docs only. Risk: low. It merges cleanly with the open #41 and #43, which don't edit this row.
Also: unbreak the bootstrap test
Second commit. 6d51ff0 raised the bootstrap minimum to 0.47.0, but
scripts/fake-archdevstill reported 0.46.6, so every "Skill bootstrap hook setup" case installed a real CLI and failed on the printed path. This fails on main too. The fake now reports 0.47.0. Locally,scripts/test-skill-bootstrap.shgoes from 9 failed cases to all passed.Testing
Live adherence eval (firstlanding
scripts/adherence-eval, scenariodone-then-lesson): Claude posts the done and a separate lesson. Codex does too, but it drops--projecton the lesson, which is an existing gap.🤖 Generated with Claude Code
https://claude.ai/code/session_01QEcGR5kWqu4WUqFM1uNuFC