aboutsummaryrefslogtreecommitdiff
path: root/docs/architecture
diff options
context:
space:
mode:
authorCraig Jennings <c@cjennings.net>2026-05-29 12:03:03 -0500
committerCraig Jennings <c@cjennings.net>2026-05-29 12:03:03 -0500
commit7a861eda6dc785ea9767886e13cab1166b3f5d22 (patch)
tree57471a9820636dd9460e01de83b8286aff381d76 /docs/architecture
parent2f9f8eb52405c42b64a9af14a7f3c789ea25f4ce (diff)
downloadrulesets-7a861eda6dc785ea9767886e13cab1166b3f5d22.tar.gz
rulesets-7a861eda6dc785ea9767886e13cab1166b3f5d22.zip
docs(todo): file [#C] :spec: TODO to build Craig's writing voice profile from real corpora
Files a TODO under Rulesets Open Work to mine Craig's actual writing (sent email across all three accounts, commit messages, PR bodies, org files he authored, slack threads, long-form artifacts) into a grounded voice profile. The voice/SKILL.md patterns today are observation-derived. Some are spot-on. Others are intuition. A corpus pass would tell us which patterns are genuinely Craig's voice, which were guesses, and which Craig-specific positive traits the current ruleset misses entirely. Output: voice/references/voice-profile.org with findings cited to evidence samples, plus a reconciliation pass against voice/SKILL.md to confirm, strengthen, weaken, add, or remove patterns based on what the corpus shows. Approach phased into corpus assembly, analysis (subagent-friendly), draft profile, reconcile-with-user. The body includes a privacy note: raw corpus stays out of commits if the project's remote ever stops being private. There's no urgency. The work is useful but optional, hence [#C].
Diffstat (limited to 'docs/architecture')
0 files changed, 0 insertions, 0 deletions