Skip to content

Revise ROADMAP to reflect current implementation status#59

Merged
SebastianElvis merged 1 commit into
mainfrom
SebastianElvis/roadmap-revise
May 2, 2026
Merged

Revise ROADMAP to reflect current implementation status#59
SebastianElvis merged 1 commit into
mainfrom
SebastianElvis/roadmap-revise

Conversation

@SebastianElvis
Copy link
Copy Markdown
Owner

Summary

  • Document the layered L1/L2/L3 eval system shipped in Add layered eval system with Claude CLI as judge #58 (graders, judge, rubrics, fixtures, orchestrator) — previously the ROADMAP only mentioned `evals.json`.
  • Add missing `[x]` entries for `/clarify-goal` and `/brainstorm` (already built); update the design-decisions skill list accordingly.
  • Replace stale references: `cross-verify` → `/critique`; "11 skill directories" → 10.
  • Split the unchecked end-to-end test task into actionable follow-ups: source the 3 paper PDFs, expand L1+L2 fixture coverage beyond `analyze-paper`, calibrate judge prompts against `evals/golden/`.

No status changes to H2–H6: unchecked items there (LaTeX synthesis, multi-model backends beyond Codex, `search-dblp/scholar/venue`, evidence taxonomy, proactive reformulation) genuinely remain undone.

Test plan

  • `git diff origin/main...` reviewed — only `dev/ROADMAP.md` changes
  • N/A: docs-only change, no code paths affected

🤖 Generated with Claude Code

Update dev/ROADMAP.md to match actual repo state: document the
layered L1/L2/L3 eval system, add missing /clarify-goal and
/brainstorm task entries, correct the skill count (10, not 11),
replace stale cross-verify references with /critique, and split
the test-pipeline task into source-PDFs, expand-fixtures, and
calibrate-judge follow-ups.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
@SebastianElvis SebastianElvis merged commit ea6f2c4 into main May 2, 2026
4 checks passed
@SebastianElvis SebastianElvis deleted the SebastianElvis/roadmap-revise branch May 2, 2026 06:06
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant