'recommend rule' 검색 결과

Recommend runtime and V2 scene management: run recommendation requests, manage recommend scenes and rules, and verify the deployed recommendation path.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Investigate suspected email account takeovers by examining audit logs, sign-ins, inbox rules, and app permissions. Identify suspicious forwarding, unlikely travel between sign-ins, and unusual access, then summarize findings and recommended containment actions in a severity-rated report.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating suspected business email compromise
• Checking for suspicious external forwarding rules
• Reviewing unusual sign-ins and app permissions

Interactive BPA rule generation for Power BI semantic models; guided discovery, model investigation, and expert rule authoring. Automatically invoke when the user mentions "BPA rule", "Best Practice Analyzer", or asks to "create a BPA rule", "audit BPA rules", "recommend BPA rules", "set up BPA for my team", "check model for best practices", "validate BPA rules", "improve a BPA expression".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Investigate suspicious email forwarding and hidden inbox rules that may expose messages after an account compromise. The skill guides log analysis, validation, and reporting, helping analysts document evidence, assess risk, and recommend response actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating external forwarding after an account compromise
• Checking rules that delete security alerts
• Hunting for rules that forward executive emails

Assign unowned leads and opportunities using company routing rules and existing account relationships. Prepare a recommendation with its reasoning, draft handoff notes, and apply ownership changes after a person accepts or overrides each recommendation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assigning newly received leads to sales representatives
• Reviewing a queue of unassigned opportunities
• Preparing handoff notes with assignment reasons

Review AI agent instructions for unnecessary rules, contradictions, repetition, and vague wording. Get recommendations on what to remove, merge, clarify, or load only when needed, plus an estimate of savings in tokens, the units models process.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Cleaning up an overloaded CLAUDE.md
• Finding conflicting rules across instruction files
• Checking for redundancy after trimming instructions

Use this skill when the user is tuning a live or captured `doca-flow` pipeline with `doca_flow_tune` — snapshotting pipe / counter / KPI state, picking a tuning axis (rule placement, resource hints / table sizing, HW-offload mode) and a matching measurement (rule-install rate, lookup latency, hardware-counter delta), running offline or online (read-only or state-changing) modes, reading the dumper CSV / analyze JSON / visualize mermaid, or applying a recommendation back into the Flow program. Trigger even when the user does not explicitly mention "doca_flow_tune" — typical implicit phrasings include "Flow rule-install rate is low on BlueField", "table sizing looks wrong for this pipe", "tune visualize step is empty", "before/after counters don't move", or "which doca-flow knob does this recommendation hit". Refuse and route elsewhere for measuring baseline numbers (doca-flow-perf, doca-flow-dpa-perf), writing the doca-flow application, DOCA install, or streaming Flow telemetry — those belong to other skills.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this agent when you need to review UniProt annotation rules (ARBA, UniRule) for quality, biological accuracy, and GO annotation appropriateness. This agent performs comprehensive analysis of rule condition sets, evaluates literature support, assesses taxonomic scope, and recommends curation actions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit instructions and memory files loaded on every agent turn. Identify repeated rules, contradictions, outdated content, and material better moved into skills, then receive evidence-backed recommendations ranked by estimated token savings and change risk.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reduce the size of instructions loaded on every turn
• Find conflicting rules across instruction and memory files
• Identify workflow instructions to move into separate skills

Check the state of an agent’s project memory with a dashboard of line counts, topic files, capacity, outdated file references, and duplicates. Get cleanup recommendations or request a one-line status summary.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking how full project memory is
• Finding references to deleted files
• Reviewing memory and rule file sizes

Review Claude Code’s automatically saved memory to identify outdated entries, duplicates, and conflicts with existing instructions. Produces a health report and recommendations for consolidating notes or turning recurring lessons into lasting project rules.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing lessons saved after a major development task
• Finding outdated or conflicting memory entries
• Identifying recurring lessons to turn into rules

MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 31 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Produces a Rule 506(d) bad actor disqualification review for private securities offerings, including a covered persons register, tailored questionnaires mapping to each disqualifying event category, a documented reasonable-care diligence record, and classification analysis of flagged events with remediation or disclosure recommendations. Use this skill when conducting Rule 506(d) diligence, identifying covered persons for a Regulation D offering, drafting bad actor questionnaires, or analyzing potential disqualifying events involving criminal convictions, SEC orders, SRO sanctions, or state regulatory actions. Also trigger when the user mentions bad actor screening, covered persons analysis, Rule 506(d) questionnaire, disqualification waiver, or reasonable care defense. Even if the user just says "bad actor check" or "506(d) diligence," use this skill.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit a dataset or access rule before it joins an identity-graph build (access rules behave like datasets in NQL here). Enumerates failure modes (hub identifiers, high-degree nodes, suspicious values, over-connected identifiers), tests hypotheses in parallel, quantifies damage by rows / edges / entities, and proposes minimal filters ranked by severity. When issues are found, returns a validated `CREATE MATERIALIZED VIEW` NQL the caller can run to produce a graph-ready clean source; if the data passes, says so and recommends it unchanged. Plans and authors the clean-view NQL; does not execute it. Use when: "audit this dataset before the graph build", "find bad edges in <source>", "check identity data quality", "recommend filters for the graph build", "quantify damage from <identifier_type>", "pre-graph DQ". (narrative-identity)

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Turn a decision into a concise brief with one problem, three distinct options, and one recommendation. Compare benefits and drawbacks, then define measurable success criteria and practical steps for carrying out the recommended approach.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing approaches to a technical decision
• Preparing a proposal to share with a team
• Weighing tools or migration strategies

Generate coding agent instruction files from a project's actual code using AgentRC. Capture detected languages, frameworks, and conventions in one shared file or split rules by topic and project area, with a preview before writing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create project instructions for VS Code Copilot
• Refresh agent rules after project changes
• Split monorepo instructions by project area

Review incoming GitHub issues and pull requests, verify claims, and organize evidence alongside existing decisions. Prepare unresolved choices with recommendations and consequences for maintainers, then carry out actions covered by verified authorization without merging changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sorting incoming bug reports and feature requests
• Applying approved rules to duplicate reports
• Preparing evidence and options for maintainer decisions

Monitor Modbus traffic in industrial control networks to identify unauthorized writes, unusual commands, and departures from normal communication. Use packet analysis and intrusion detection rules to investigate suspected controller changes and produce reports with recommended actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating unauthorized changes to PLC registers
• Setting up Modbus intrusion detection rules
• Checking communication patterns after a suspected compromise

Investigate service account misuse by examining unexpected interactive logons, privilege changes, and movement between systems. Correlate endpoint and security logs, distinguish suspicious activity from legitimate operations, and document evidence, risk, and recommended responses.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating unexpected interactive logons by service accounts
• Checking service account access outside its assigned scope
• Tracing suspicious movement between systems after hours

Find repeated engineering tasks and turn them into agent workflows with clear checks, stopping rules, and approval boundaries. Compare published workflows, adapt suitable examples, or review existing ones for weak verification and uncontrolled repetition.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find recurring tasks in code and conversation history
• Compare and adapt published agent workflows
• Review workflows for weak checks and missing stop rules

Review a game design document before implementation. Check missing sections, conflicting rules, formulas, dependencies, and testable success conditions, then report blocking issues and recommended changes. Full mode adds reviews by relevant specialist agents.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check a design document before implementation
• Find formula errors and conflicting system rules
• Rewrite vague success conditions as measurable checks

Create reusable starting configurations that combine an agent’s role, startup context, and source history. The skill guides registry entries, checks whether their sources are current, and manages their progression from initial capture to recommendation or retirement.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create reusable startup context for an agent role
• Refresh an agent workspace from an existing starter
• Check a starter’s source history and freshness

Investigate unexpected LoopX behavior, such as stalled progress or conflicting next steps. Identify whether agent decisions, state reporting, or workflow rules caused the problem, then repair, validate, and record the correction.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating tasks that make unexpectedly little progress
• Resolving stale or contradictory next-step recommendations
• Correcting task priorities and missing follow-up work

Use this skill when the user is invoking doca_flow_dpa_perf on DPA-capable hardware (ConnectX-7 minimum supported, ConnectX-8 recommended, or BlueField-3) to measure rule update / disable rates on the DPA-offloaded DOCA Flow path — picking the active / passive device split, choosing workload-shape axes (burst, queue, completion threshold, workers, hash pipe algo, PSL tables), or reading Kops/sec iteration stats and the optional self-test. Trigger even when the user does not explicitly mention "doca_flow_dpa_perf" or "DPA Provider" — typical implicit phrasings include "how fast can the DPA program path-selector entries", "baseline rule-update rate on ConnectX-8", "tool reports zero ops on my BlueField", "self-test sentinel never shows on tcpdump", or "is my BlueField-2 DPA-capable". Refuse and route elsewhere for the host / DPU-CPU Flow path (doca-flow-perf), Flow pipeline tuning (doca-flow-tune), writing doca-flow / doca-dpa applications, or DOCA install — those belong to other skills.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.