Conversation
…llision Parallel rename for ce-doc-review (closes #688), mirroring PR #685's 33e00c4 commit for ce-code-review. Naming-only change — no behavior shift. User-facing labels: - Routing option B: "LFG. Apply the agent's best-judgment action per finding" -> "Auto-resolve with best judgment - apply per-finding edits the agent can defend, surface the rest". Picked "edits" over "fixes" since ce-doc-review applies document edits, not code patches. - Per-finding option D: "LFG the rest - apply the agent's best judgment to this and remaining findings" -> "Auto-resolve with best judgment on the rest". Self-describing, no em-dash needed. - Bulk-preview header: "LFG plan - N findings:" -> "Auto-resolve plan - N findings:" (and the K-already-decided variant). - SKILL.md frontmatter description: routing-option list updated. Internal prose: - "LFG" / "LFG (routing option B)" / "Top-level LFG" -> "best-judgment" / "best-judgment routing (option B)" / "Top-level best-judgment". Same rationale as ce-code-review's rename: user-facing surface uses "auto-resolve" because it describes the action; internal prose uses "best-judgment" to avoid lexical collision with `mode:autofix` (autofix is a top-level mode; best-judgment is a routing option within interactive mode). - "LFG-the-rest" -> "best-judgment-the-rest" in cross-reference prose. Files touched: - plugins/compound-engineering/skills/ce-doc-review/SKILL.md - plugins/compound-engineering/skills/ce-doc-review/references/walkthrough.md - plugins/compound-engineering/skills/ce-doc-review/references/bulk-preview.md - plugins/compound-engineering/skills/ce-doc-review/references/synthesis-and-presentation.md - plugins/compound-engineering/skills/ce-doc-review/references/open-questions-defer.md - tests/pipeline-review-contract.test.ts (label assertions updated) Tests: 908/908 pass. release:validate clean. Closes #688 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Merged
michaelvolz
pushed a commit
to michaelvolz/compound-engineering-plugin-windows-version
that referenced
this pull request
Apr 28, 2026
…llision (EveryInc#691) Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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.
Closes #688
Summary
Parallel rename for
ce-doc-review, mirroring the LFG → best-judgment rename PR #685 did force-code-review(commit33e00c40). Naming-only change — no behavior shift.Removes the lexical collision between
ce-doc-review's "LFG" routing option and the repo's/lfgmacro skill, and replaces "LFG" with descriptive labels that read better to humans.Key wording choice — "edits" not "fixes"
ce-code-review's option B readsapply per-finding fixes the agent can defend. Force-doc-review, the natural domain term is "edits" since the action is document edits rather than code patches:Auto-resolve with best judgment — apply per-finding edits the agent can defend, surface the restAuto-resolve with best judgment on the restThe internal prose uses "best-judgment path" / "best-judgment routing" — same rationale as
ce-code-review: user-facing surface uses "auto-resolve" (descriptive); internal prose uses "best-judgment" (avoids lexical collision withmode:autofix, since autofix is a top-level mode and best-judgment is a routing option within interactive mode).What changed
ce-doc-review/SKILL.mdce-doc-review/references/walkthrough.mdLFG-shaped prose, end-of-walk-through dispatch refs, completion-report path-name sectionce-doc-review/references/bulk-preview.mdce-doc-review/references/synthesis-and-presentation.mdce-doc-review/references/open-questions-defer.mdtests/pipeline-review-contract.test.tsTest plan
bun test— 908/908 passbun run release:validate— cleanLFG/lfgince-doc-review/and test files returns zero matchesReferences
ce-code-review33e00c40— the template for this work🤖 Generated with Claude Code