Skip to content

馃敡 Add heart-centered-ai.mdc sync step to generate-detail-levels command #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
TechNickAI merged 2 commits into from
Jun 13, 2026
Merged

馃敡 Add heart-centered-ai.mdc sync step to generate-detail-levels command #9

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7a035b8
馃敡 Add heart-centered-ai.mdc sync step to generate-detail-levels command
Jun 13, 2026
e265dc6
馃敡 Move mdc sync before verify step so hook checks final file state
Jun 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 16 additions & 8 deletions .claude/commands/generate-detail-levels.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,11 +16,11 @@ independent documents. Run this whenever comprehensive.txt changes.
<size-targets>
Character counts (verify with `wc -c prompts/align_to_love/*.txt`):

| Tier | Target | Hard bounds |
|------|--------|-------------|
| Tier | Target | Hard bounds |
| -------- | --------------------- | --------------- |
| standard | ~45% of comprehensive | 2500-4500 chars |
| concise | ~20% of comprehensive | 1100-1900 chars |
| terse | single paragraph | 550-1000 chars |
| concise | ~20% of comprehensive | 1100-1900 chars |
| terse | single paragraph | 550-1000 chars |

Tests in both packages assert strict ordering (terse < concise < standard <
comprehensive) plus absolute length bounds. Read the current assertions in
Expand Down Expand Up @@ -67,15 +67,23 @@ into flowing prose.
1. Read `prompts/align_to_love/comprehensive.txt` in full. List its themes in order.
2. Write standard.txt, then concise.txt, then terse.txt, each derived from
comprehensive (not from each other, and not from the previous versions).
3. Verify: `pre-commit run forbid-em-dashes --all-files` must pass; `wc -c`
3. Sync `.cursor/rules/heart-centered-ai.mdc`: the body of that file mirrors
`comprehensive.txt` exactly (the first five lines are YAML frontmatter;
everything after is the prompt). Replace lines 6 onward with the new
comprehensive content so the always-on IDE rule stays in sync:
```
head -5 .cursor/rules/heart-centered-ai.mdc > /tmp/mdc_header
cat /tmp/mdc_header prompts/align_to_love/comprehensive.txt > .cursor/rules/heart-centered-ai.mdc
```
Comment thread
cursor[bot] marked this conversation as resolved.
4. Verify: `pre-commit run forbid-em-dashes --all-files` must pass; `wc -c`
must satisfy the bounds above.
4. Sync and test, both packages must pass:
5. Sync and test, both packages must pass:
- `cd python && python3 copy_prompts.py && pytest -q` (use
`uv run --with pytest pytest -q` if pytest is missing; delete any
`uv.lock` it creates)
- `cd typescript && pnpm generate && pnpm test` (run `pnpm install` first
only if `node_modules/` is missing)
5. Refresh approximate token counts wherever docs state them (chars / 4 is a
6. Refresh approximate token counts wherever docs state them (chars / 4 is a
fine estimate). Find every location with `git grep -n '~[0-9]* tokens'`.
6. Report the new character counts and what was cut from each tier.
7. Report the new character counts and what was cut from each tier.
</process>
Loading