return-target-classification
A decision framework for classifying where to return review findings based on impact scope.
Install
mkdir -p .claude/skills/return-target-classification && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15097" && unzip -o skill.zip -d .claude/skills/return-target-classification && rm skill.zipInstalls to .claude/skills/return-target-classification
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when deciding the return target of a review finding between detailed design, implementation plan, test plan, or minor fix handlingKey capabilities
- →Determine if a review finding impacts requirements or design structure
- →Classify findings that affect design structure to be returned to Detailed Design
- →Classify findings related to execution order, preparation, or granularity to be closed in the Plan
- →Classify findings related to wording or layout as Minor Fixes
- →Record affected requirement IDs for each finding
- →Ensure re-review of the plan after non-minor design changes
How it works
The skill provides a procedure to classify review findings based on their impact on requirements, design structure, or execution plans, directing them to the appropriate resolution target.
Inputs & outputs
When to use return-target-classification
- →Classifying review feedback
- →Deciding on design vs plan changes
- →Setting resolution targets for defects
About this skill
Return Target Classification
When to Use
- レビュー結果の差し戻し先を決めるとき
- 影響範囲に応じて Detailed Design へ戻すか、Plan で閉じるかを決めるとき
Procedure
- 指摘が要件充足や設計構造に影響するかを確認する。
- 影響が設計構造に及ぶなら Detailed Design へ戻す。
- 影響が実行順、準備、粒度、担当割りだけなら Plan で閉じる。
- 影響が文面やレイアウトだけなら Minor Fix とする。
Checks
- 要件 ID に影響する指摘は Design か Plan のいずれかに分類する。
- 影響する要件 ID を必ず記録する。
- 非軽微な設計変更後は影響範囲のプラン再レビューを前提にする。
References
When not to use it
- →When the task is not about classifying review findings
- →When the finding does not relate to requirements, design, or plan
- →When the review process does not involve Detailed Design or Plan phases
Limitations
- →Applicable only for review findings classification
- →Requires existing Detailed Design and Plan phases for classification targets
- →Assumes findings can be categorized into design, plan, or minor fix impacts
How it compares
This skill offers a structured procedure for categorizing review feedback to determine its resolution target, providing a consistent approach compared to ad-hoc decision-making.
Compared to similar skills
return-target-classification side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| return-target-classification (this skill) | 0 | 2mo | No flags | Beginner |
| drift-analysis | 2 | 5mo | No flags | Intermediate |
| planning | 2 | 3mo | No flags | Intermediate |
| gsd-plan-checker | 1 | 4mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
drift-analysis
avifenesh
This skill should be used when the user asks about "plan drift", "reality check", "comparing docs to code", "project state analysis", "roadmap alignment", "implementation gaps", or needs guidance on identifying discrepancies between documented plans and actual implementation state.
planning
citypaul
Planning work in small, known-good increments. Use when starting significant work or breaking down complex tasks.
gsd-plan-checker
toonight
Validates plans before execution to catch issues early
feature-planning
mhattingpete
Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.
linear-ticket
useautumn
Refine rough engineering thoughts into structured Linear tickets with GitHub permalinks
design-to-issues
cloverich
Creates a GitHub epic and child issues from a design document's implementation plan. Use when a design doc has a reviewed plan section ready to be converted into trackable work.