フィードバックチケットから実装プランを立てる plan-from-feedback スキルを追加#5863
Merged
TinyKitten merged 4 commits intodevfrom Apr 21, 2026
Merged
Conversation
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughプライベートリポジトリのIssueを取得し、スペース区切りの Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Skill as "plan-from-feedback\n(skill)"
participant CLI as "gh CLI"
participant Repo as "TrainLCD/Issues"
participant Analyzer as "Local Analyzer"
User->>Skill: 指定の`key=value`入力
Skill->>CLI: `gh issue list --repo TrainLCD/Issues ... --json ...`
CLI->>Repo: query open issues
Repo-->>CLI: issues (JSON)
CLI-->>Skill: returned issues
Skill->>Analyzer: フィルタ/難易度推定/本文参照
Analyzer-->>Skill: ranked candidates + rationales
Skill-->>User: コンパクトなMarkdown実装プラン（読み取り専用）
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (1)
.claude/skills/plan-from-feedback/SKILL.md (1)
90-90: Gemini 要約の位置づけを「補助情報」に弱めるのを推奨します。「一次情報として信頼してよい」は強すぎるため、
原文優先・要約は補助と明記すると誤要約耐性が上がります。Also applies to: 149-149
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.claude/skills/plan-from-feedback/SKILL.md at line 90, The current text treats the "Gemini 要約" (the section headed "## Geminiによる要約") as primary/authoritative ("一次情報として扱う"), which is too strong; revise the wording in both occurrences (around the line with "本文にある Gemini 要約（`## Geminiによる要約` 節）..." and the repeat at the later occurrence) to explicitly state that the original source takes priority and the Gemini summary is auxiliary — e.g., replace "一次情報として扱う" with "原文優先・要約は補助情報として扱う" or similar phrasing that demotes the summary to supporting information.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.claude/skills/plan-from-feedback/SKILL.md:
- Around line 88-100: Change the selection logic so you do the primary sort by
triage (P0>P1>P2>P3>untriaged) then by updatedAt (newest first) before taking
the top "count * 4" items for difficulty estimation; specifically, replace the
current "先頭から `count * 4` 件を上限" pre-slice with a pass that sorts the full
candidate set by triage then updatedAt and only then selects the first `count *
4` for running the difficulty inference used in the "difficulty フィルタとランキング"
step.
- Line 109: Update the placeholder in the template from "<html_url>" to "<url>"
so it matches the field returned by the GH query; locate the line containing
"URL: <html_url>" in SKILL.md and replace "<html_url>" with "<url>" to ensure
the template variable name matches the `url` field used on line 69.
---
Nitpick comments:
In @.claude/skills/plan-from-feedback/SKILL.md:
- Line 90: The current text treats the "Gemini 要約" (the section headed "##
Geminiによる要約") as primary/authoritative ("一次情報として扱う"), which is too strong;
revise the wording in both occurrences (around the line with "本文にある Gemini
要約（`## Geminiによる要約` 節）..." and the repeat at the later occurrence) to explicitly
state that the original source takes priority and the Gemini summary is
auxiliary — e.g., replace "一次情報として扱う" with "原文優先・要約は補助情報として扱う" or similar
phrasing that demotes the summary to supporting information.
🪄 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: CHILL
Plan: Pro
Run ID: 9ee981ec-2db9-4067-85fa-e955dd84ea82
📒 Files selected for processing (1)
.claude/skills/plan-from-feedback/SKILL.md
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Member
Author
Fixes Applied SuccessfullyFixed 1 file(s) based on 2 unresolved review comment(s). Files modified:
Commit: Applied fixes:
The latest autofix changes are on the |
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.claude/skills/plan-from-feedback/SKILL.md:
- Around line 96-100: The ordering for difficulty is ambiguous because `unknown`
is omitted from the listed sort order; update the spec text (the bullet
describing selection and sorting) to explicitly include `unknown` in the
difficulty precedence (e.g., "difficulty（`easy` > `medium` > `hard` >
`unknown`）") so implementations of the selection step that uses `difficulty` and
`updatedAt` (as described in the block containing "残存から `count` 件を選ぶ。並び順は:" and
the triage/difficulty/`updatedAt` rules) have an unambiguous order to follow.
🪄 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: CHILL
Plan: Pro
Run ID: f977aad2-bc8a-41bb-9412-d464b145a381
📒 Files selected for processing (1)
.claude/skills/plan-from-feedback/SKILL.md
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Member
Author
Fixes Applied SuccessfullyFixed 1 file(s) based on 1 unresolved review comment(s). Files modified:
Commit: Applied fixes:
The latest autofix changes are on the |
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.
概要
TrainLCD のフィードバック置き場（
TrainLCD/Issues）から open issue を取得し、トリアージレベルと Claude 推定の対応難易度で絞り込んで、各チケットに短い実装プランを付けてチャットに出力する read-only スキルplan-from-feedbackを追加する。変更の種類
変更内容
.claude/skills/plan-from-feedback/SKILL.mdを新規追加gh issue list --repo TrainLCD/Issuesをベースにした候補取得フローテスト
npm run lintが通ることnpm testが通ることnpm run typecheckが通ること.claude/skills/配下のみのメタ変更で、アプリ本体・ビルド成果物・CI ワークフローには影響しないため上記 3 コマンドは未実行。関連Issue
スクリーンショット（任意）
Summary by CodeRabbit