fix(research,codex-plan-review,implement): integer steps, name-key refs - #131
Merged
Conversation
research's Step 3.4/3.5 were h2 top-level steps numbered as decimals, implying nonexistent sub-steps of Step 3. Renumber the top-level steps to a contiguous integer sequence (3.4->4, 3.5->5, 4->6, 5->7) and update research's internal self-references. Convert research's inbound cross-skill references from number-based to name-based so future renumbers cannot break them: codex-plan-review's "Step 3.5" -> "Plan review gate"; implement's two "Step 2.B" -> "derivational-hypothesis verification". Closes #130
📝 WalkthroughWalkthroughThe research workflow now uses contiguous top-level step numbers, explicit clean or flagged outcomes, a plan review gate, user approval, and GitHub posting stages. Related skills use named research references, and the marketplace metadata version is incremented. ChangesResearch workflow alignment
Estimated code review effort: 2 (Simple) | ~10 minutes Sequence Diagram(s)sequenceDiagram
participant ResearchWorkflow
participant User
participant GitHub
ResearchWorkflow->>ResearchWorkflow: Run reachability check
ResearchWorkflow->>ResearchWorkflow: Emit clean or flagged result
ResearchWorkflow->>User: Offer plan review and approval
User->>ResearchWorkflow: Approve plan contract
ResearchWorkflow->>GitHub: Validate body and route plan
Possibly related PRs
Suggested reviewers: Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Pull request overview
Renumbers research’s top-level (H2) steps from misleading decimal numbering to a contiguous integer sequence, and updates cross-skill references to research to be name-keyed (so future renumbers don’t break inbound links). Also bumps the marketplace version to publish the behavior change.
Changes:
- Renumber
skills/research/SKILL.mdtop-level steps (3.4/3.5 → 4/5, shifting later steps accordingly) and update internal step references. - Update inbound cross-skill references to
researchincodex-plan-reviewandimplementto use step names rather than step numbers. - Bump
.claude-plugin/marketplace.jsonversion from2026.7.25to2026.7.26.
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| skills/research/SKILL.md | Renumbers top-level steps to contiguous integers and updates internal references to match. |
| skills/implement/SKILL.md | Replaces number-keyed references to research steps with name-keyed references (but one name currently doesn’t match research’s heading). |
| skills/codex-plan-review/SKILL.md | Updates the inbound reference to research to use the “Plan review gate” step name instead of a step number. |
| .claude-plugin/marketplace.json | Version bump to publish the skill behavior/reference changes. |
Comments suppressed due to low confidence (1)
skills/implement/SKILL.md:105
- This reference points to “derivational-hypothesis verification”, but
researchhas no step/heading by that name; its Step 2.B is titled “Derivational hypotheses …”. Using the actual heading name keeps the reference stable and discoverable.
3. **Required action when halted:** Surface to the user with: the proposed example, the deductive properties it is being relied on to satisfy (e.g., "this Hamiltonian must be U(1)-symmetric, must be Hermitian, must be non-diagonal in the chosen basis, must exercise the multi-sector path"), and the request to extend the plan's `Derivations` section before proceeding. The derivation itself is performed in `research`'s derivational-hypothesis verification, not in implementation.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@skills/research/SKILL.md`:
- Around line 205-209: Update the Step 4 output and subsequent workflow in the
research skill instructions so a flagged reachability result blocks progression:
require rescope or defer resolution and user-facing handling before continuing.
Make the Step 5 plan review gate explicitly conditional on Step 4 being clean,
preventing flagged plans from reaching approval or Step 7.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 9c84890f-1fdc-4d0e-8e0b-4b3407a3bce5
📒 Files selected for processing (4)
.claude-plugin/marketplace.jsonskills/codex-plan-review/SKILL.mdskills/implement/SKILL.mdskills/research/SKILL.md
Copilot review flagged that "research's derivational-hypothesis verification" paraphrased Step 2.B's heading and was not discoverable. Use the heading's actual name so the name-keyed reference resolves by search: "research's Derivational hypotheses step".
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 4 out of 4 changed files in this pull request and generated no new comments.
Comments suppressed due to low confidence (2)
skills/implement/SKILL.md:28
- The name-key cross-skill reference uses “Derivational hypotheses step”, but
research’s Step 2.B heading is “Derivational hypotheses (deductive verification in main context)”. Using the exact heading phrase (“Derivational hypotheses”) makes the reference easier to resolve by search and better matches the stated goal of name-keyed linking.
- **Derivations** (specific examples and their deductive properties, already verified in `research`'s Derivational hypotheses step). The list of examples whose properties have been derived defines the **derivationally cleared example set** — examples not on this list are unverified by the plan, regardless of how obvious their properties may seem.
skills/implement/SKILL.md:105
- This cross-skill reference should match
research’s Step 2.B heading text. The heading uses “Derivational hypotheses …”, so using that exact phrase improves discoverability and keeps the reference clearly name-keyed.
3. **Required action when halted:** Surface to the user with: the proposed example, the deductive properties it is being relied on to satisfy (e.g., "this Hamiltonian must be U(1)-symmetric, must be Hermitian, must be non-diagonal in the chosen basis, must exercise the multi-sector path"), and the request to extend the plan's `Derivations` section before proceeding. The derivation itself is performed in `research`'s Derivational hypotheses step, not in implementation.
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
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.
Summary
research's SKILL.md had## Step 3.4and## Step 3.5but no3.1–3.3. Those decimals read as sub-steps of Step 3, but both headings are##(h2) top-level steps — structural peers of Step 3 and Step 4 — whose decimal numbers merely place them between Step 3 and Step 4. This renumbers the top-level steps to a contiguous integer sequence and keysresearch's inbound cross-skill references on step names instead of numbers, so a future renumber cannot break them.Closes #130
Changes
skills/research/SKILL.md— renumber top-level steps3.4→4,3.5→5,4→6,5→7; Post sub-sections5.0/5.1→7.0/7.1; update the internal self-references.Step 2/2.A/2.B/Step 3keep their numbers, and the phrase "codex-plan-reviewper its Step 4 re-run rule" is preserved (thatStep 4namescodex-plan-review's own step).skills/codex-plan-review/SKILL.md— "researchStep 3.5" → "research's Plan review gate".skills/implement/SKILL.md— both "researchStep 2.B" → "research's Derivational hypotheses step" (matching Step 2.B's heading text)..claude-plugin/marketplace.json— version2026.7.25→2026.7.26.Test plan
No test suite (Markdown skill repo). Verified by:
rg '^## Step [0-9]+\.[0-9]' skills/research/SKILL.mdreturns nothing (no decimal top-level step heading remains).research's h2 step headings are now0,1,2,3,4,5,6,7;2.A/2.Bremain h3 under Step 2;7.0/7.1remain h3 under Step 7.rg '`research`\s+Step [0-9]' skillsreturns nothing (no number-keyed inbound reference toresearchremains).Step Nreference insideresearch's SKILL.md resolves to an existing heading.mdformatpre-commit hook (--number --compact-tables) passes.Notes
Two follow-ups are deliberately out of scope:
research(h3 letters2.A/2.Bvs h3 decimals7.0/7.1).quality-list→done-check/todo-check,codex-contract-test-review→bug-to-contract) to names.@coderabbitai ignore