代码评审
自动化代码审查与分析
Rust Ecosystem
takeokunn
This skill should be used when working with Rust projects, "Cargo.toml", "rustc", "cargo build/test/run", "clippy", "rustfmt", or Rust language patterns. Provides comprehensive Rust ecosystem patterns and best practices.
fiftyone-dataset-inference
voxel51
Run ML model inference (YOLO, YOLOv8, CLIP, SAM, Detectron2, etc.) on FiftyOne datasets. Use when running models, applying detection, classification, segmentation, embeddings, or any model prediction task. Also use for end-to-end workflows that include importing data then running inference.
create-slash-commands
glittercowboy
Expert guidance for creating Claude Code slash commands. Use when working with slash commands, creating custom commands, understanding command structure, or learning YAML configuration.
meta-audit
laurigates
Audit Claude subagent configurations for completeness, security, and best practices
draft-pr
benmatselby
Create a draft pull request for the current branch. Summarises the diff, fills in any PR templates, and opens the PR via the gh CLI.
git-log-summary
benmatselby
Provides a summary of the git log for the past period of time. Use when asked to provide a git log summary.
order-management-advisor
JoelLewis
"Advisor order management: order entry, block trading, allocation, order types, pre-trade compliance, custodian routing, model-driven trading, error handling, and audit trail."
account-maintenance
JoelLewis
"Account maintenance operations: address changes, beneficiary updates, re-registration, cost basis management, account restrictions, standing instructions, and lifecycle changes."
post-trade-compliance
JoelLewis
"Post-trade compliance and surveillance: trade surveillance, pattern detection, best execution review, allocation fairness, exception-based monitoring, and regulatory reporting triggers."
workflow-automation
JoelLewis
"Workflow automation for securities operations: BPM concepts, task routing, approval chains, escalation rules, SLA monitoring, and process orchestration patterns."
next-best-action
JoelLewis
"Next-best-action frameworks for advisor workflows: event-driven triggers, prioritization scoring, action queuing, advisor nudges, automated workflows, personalized recommendations."
crm-client-lifecycle
JoelLewis
"Client lifecycle management for RIAs: segmentation models (AUM, revenue, behavioral, strategic importance), household management, multi-generational relationship tracking, service tier SLAs, quarterly/annual review scheduling, lifecycle tracking (prospect→onboarding→accumulation→distribution→estate), engagement analytics (NPS, contact frequency, retention risk scoring), at-risk identification, wallet share, held-away asset consolidation, referral attribution, FINRA Rule 4512 trusted contact, OFAC/enhanced due diligence, CRM platforms (Salesforce, Redtail, Wealthbox, Dynamics)."
order-lifecycle
JoelLewis
"Order lifecycle management: order states, FIX protocol basics, order types, time-in-force, cancel/replace workflows, order validation, and state machine design for trading systems."
account-opening-workflow
JoelLewis
"Account opening workflows: account types (individual, joint JTWROS/TIC, trust, entity, IRA/SEP/SIMPLE/inherited, UTMA, estate), required forms (Form CIP, CRS, W-9, W-8BEN, beneficial ownership, trust/LLC docs, Form 5305), approval workflows with supervisory review, NIGO management, regulatory holds, PEP/enhanced due diligence screening, senior investor protections, KYC/CIP verification, straight-through processing (STP), multi-custodian operations (Schwab, Fidelity, Pershing), account numbering/titling/classification, ACAT coordination, 30-day compliance review, funding verification, billing system integration, FINRA Rule 4512."
backend
atrislabs
Backend architecture policy. Use when building APIs, services, data access, or any backend work. Prevents over-engineering.
wiki
atrislabs
"Local-first project wiki skill. Ingest raw sources into atris/wiki, query the wiki, lint it, and keep the memory sharp. Triggers on: wiki this, ingest this, query the wiki, lint the wiki."
figma-use
dannote
Control Figma via CLI — create shapes, frames, text, components, set styles, layout, variables, export images. Use when asked to create/modify Figma designs or automate design tasks.
error-detective
htlin222
Search logs and codebases for error patterns, stack traces, and anomalies. Use when debugging issues, analyzing logs, or investigating production errors.
sc-analyze
htlin222
Analyze code quality, security, performance, and architecture. Use when user asks to analyze code, review codebase health, or identify issues.
wilma-triage
aikarjal
Daily triage of Wilma school notifications for Finnish parents. Fetches exams, messages, news, schedules, and homework — filters for actionable items, syncs exams to Google Calendar, and reports via chat. Requires the wilma skill and gog CLI (or gog skill from ClawHub) for calendar access.
git-review
tsaol
Review code changes against requirements and original design. Validates implementation correctness, design alignment, code quality, and runs tests. Use before committing or creating a PR.
debug-network
RHEcosystemAppEng
Diagnose OpenShift service connectivity issues including DNS resolution, service endpoints, route ingress, and network policies. Automates multi-step diagnosis: service endpoint verification, pod selector matching, route status, and network policy analysis. Use this skill when services can't communicate, routes return 503/502 errors, or external access fails. Triggers on /debug-network command or phrases like "can't reach service", "route returning 503", "pods can't communicate", "no endpoints".
remediation-verifier
RHEcosystemAppEng
CRITICAL: This skill must be used for remediation verification. DO NOT use raw MCP tools like get_cve or get_host_details directly for verification. Verify CVE remediation success by checking Red Hat Lightspeed CVE status, validating package versions, and confirming service health. Use this skill after executing remediation playbooks to ensure vulnerabilities are properly fixed. This skill orchestrates MCP tools (get_cve, get_cve_systems, get_host_details) to provide comprehensive remediation verification including CVE status checking, package version validation, and service health confirmation. IMPORTANT: ALWAYS use this skill instead of calling verification MCP tools directly.
vm-lifecycle-manager
RHEcosystemAppEng
Manage virtual machine lifecycle operations including start, stop, and restart. Use this skill when users request: - "Start VM [name]" - "Stop the virtual machine [name]" - "Restart VM [name]" - "Power on/off VM [name]" This skill handles VM state transitions safely with user confirmation for each action. NOT for creating VMs (use vm-create) or deleting VMs (use vm-delete).