'triage' 검색 결과

Sorts a personal inbox backlog into five buckets (needs-reply-today, needs-reply-this-week, waiting-on-others, FYI, noise), writes DRAFT reply text for the messages that need an answer (up to 10 per run), and returns a dated triage report as one Markdown document. Lists moves or archives only as proposals for the user to perform, and only where a rule the user supplied says so; the agent changes nothing in the mailbox. Use when the user asks to "triage my inbox", "sort my mail", "clean up my inbox", "catch up after leave" or "what needs a reply today or this week". Do not use for a shared support queue or helpdesk export, use ticket-triage-pack instead; for what the user promised or is owed, use commitment-catcher; for one named thread, answer directly. Drafts for human review; never approves, authorises or signs off.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Orchestrate HITL triage of review findings using parallel agents. Use when the user says 'triage these findings' or 'run findings triage' or has a batch of review findings to process.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Triage Linear issues and claim work with the Linear MCP tools - find the triage queue or your assigned work, check for duplicates and existing owners, set team/priority/labels, and claim an issue (assign to me, move to In Progress) only after confirming nobody else owns it. Use for "triage the queue", "what should I work on", "claim LIN-123".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

open Issue を triage して「次の仕事候補（N 件 + 推奨 1 件）」を窓口が人間へ提示する。 候補はオペレーターが書いたゴール台帳（registry/goals/）の条項に当たるものだけで、条項順に並ぶ。 tools/work_discovery_scan.py を 1 回実行し、その候補 JSON を 設計書 §5.2 / §12 の人間可読フォーマットでレンダリングするところで停止する（propose-only）。 起動主体は窓口に限定。手動 / イベント起動のみ（常駐 /loop なし）。 「次の仕事候補出して」「triage して」「次なにやる？」や PR マージ後の proactive next-dispatch で窓口が手動起動する。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

人間が承認したスコープの内側で triage → worker 派遣 → verify → push → PR 作成 → CI 監視 を完了駆動で自走し、PR ごとに merge gate で停止する窓口用のベルトコンベア。 「この範囲は自走してよい」「triage 上位の S 級バグを空き pane 分まで流して」等、 人間がスコープ承認を明示して複数候補を順に流したいときに窓口が起動する。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

直近N日（デフォルト1日）に更新された `cc-triage-scope` / `cc-pr-created` ラベル付きGitHub Issueのdescriptionとコメントを横断し、繰り返し現れる仕様判断・要件決定のロジックを再利用可能なルールとして抽出して `.claude/requirements/` 配下のタイプ別マークダウンへ集約・統合・圧縮したうえで、commit-push + create-prでPRを作成する（`cc-triage-scope`ラベル + 自分自身をAssignee）。作成したルールは create-issue / create-issue-from-issue-number / answer-issue-questions が仕様作成・判断の材料として読み込む。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Paperclip에서 정체되거나 검토 대기 중인 이슈를 살펴봅니다. 담당자와 상태를 명확히 하고 재개, 담당 변경, 장애 해소, 판단 요청, 종료 중 다음 행동을 정합니다.

• 업무 시작 시 담당 이슈 점검
• 미완료 이슈 수신함 정리
• 팀의 진행 상황 파악

Investigate WorldMonitor production errors using Sentry event details and source code. Classify issues as noise, already fixed, product bugs, ingestion problems, or needing human review, with tested fixes when code changes are requested.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate an issue from a Sentry URL or short ID
• Review unresolved issues and muted error reports
• Test noise filters and fixes for product bugs

Investigate failed Agent QA runs using recorded steps, logs, and saved evidence. Classify each failure, explain confidence and supporting findings, and identify the likely area to fix and the next action.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a failed or interrupted Agent QA run
• Reviewing saved evidence and execution logs
• Comparing recurring failures across recent runs

Turn previously fetched pull request reviews into an ordered action plan. Separate distinct findings, track deferred work in Linear, validate that every triage decision is complete, and produce JSON and Markdown files for the implementation phase.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning responses to fetched PR review feedback
• Separating multiple findings within a single review
• Tracking deferred review work in Linear

Work through GitHub pull request feedback by classifying findings, fixing code, running repository checks, and posting replies. With suitable permissions, the skill repeats Copilot reviews until the latest code is reviewed and every thread has an agent response.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Address outstanding Copilot review comments
• Run repeated reviews on a completed pull request
• Explain declined suggestions and hand off design decisions

Set up an email reporting button and an automated security response workflow. Classify reported messages, extract attack indicators, remove confirmed phishing emails, and send feedback to the people who reported them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deploying a phishing reporting button in Outlook
• Automating triage of a dedicated reporting mailbox
• Retracting confirmed phishing emails across inboxes

Inspect suspicious Android APK files without running them. Analyze permissions, app components, suspicious code patterns, and network indicators, then produce a JSON risk report to support malware triage and detection rule development.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Triage suspicious APK files without running them
• Inspect dangerous permission combinations and suspicious API calls
• Extract network indicators for malware detection rules

Assess incoming leads or rank a lead backlog by customer fit and buying intent. Receive evidence-based priorities, routing recommendations, and suggested first responses, with existing account ownership checked when CRM records are available.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prioritize leads from incoming inquiries
• Rank an uploaded lead backlog
• Check existing account ownership before routing a lead

Review Qwen Code issues and pull requests through staged checks. Assess product fit, code simplicity, and CI evidence, then prepare English and Chinese comments that explain findings and flag decisions needing maintainer attention.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Triage incoming Qwen Code issues
• Check pull requests against product direction
• Review changes for unnecessary complexity

Triage Google SecOps alerts by checking logs, related cases, asset importance, and threat intelligence. Classify findings, adjust severity and priority, and document evidence for closing benign cases or handing suspicious activity to incident responders.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Distinguish false alarms from malicious activity
• Review alert priority using asset risk
• Close duplicate cases with references

Review new and spiking Sentry errors, rank their impact, and check for existing GitHub issues. Create triage issues for the highest-impact untracked errors and post a Slack summary, while leaving Sentry error states and assignments unchanged.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review new and spiking errors every hour
• Avoid duplicate GitHub issues for Sentry errors
• Create issues with stack traces and impact details

Assess Verdaccio issues against the code, affected release lines, and related reports. Distinguish bugs from configuration problems or duplicates, then propose existing labels, next steps, and a reply draft backed by evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classifying a newly reported issue
• Checking which release lines a bug affects
• Finding duplicates and related fixes

Turn GitHub issue reports into actionable work by searching for duplicates, attempting reproduction, and assessing user impact. Organize issues with existing labels, appropriate owners, and milestones, while clearly recording what was and was not verified.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assessing newly reported GitHub issues
• Finding duplicate reports and recurring bugs
• Reproducing bugs and recording the results

Review open issues and discussions to organize a project's backlog. Identify possible duplicates, suggest priorities and labels, and record the top five actionable items and cases needing human attention in a state file.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Organizing a growing issue backlog
• Selecting the top five actionable issues
• Suggesting labels and possible duplicates

Evaluate supplied security findings against repository code and security policy without running the software. Classify each claim as confirmed, not actionable, or needing review, then rank relevant findings by exploitability and explain evidence gaps and next steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assess findings from a vulnerability scanner
• Review security tickets from Jira or Linear
• Evaluate GitHub alerts and security advisories

Review an incoming demand letter, extract its requests and deadlines, and check for related disputes. Produce an initial assessment with response options and a recommendation, then prepare a handoff for case intake or response preparation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extract requests, allegations, and deadlines from a demand letter
• Check whether an incoming demand relates to an existing matter
• Compare substantive, holding, settlement, and preservation options

Triage proposed personal data uses to determine whether they can proceed, need a privacy impact assessment, require a legally mandated assessment, or must stop. Results explain policy conflicts, applicable triggers, and conditions to address before proceeding.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether a new feature needs a privacy assessment
• Reviewing proposed data uses involving a vendor
• Finding conflicts with privacy policy commitments