AI Skills
Installable SKILL.md packages that extend AI coding agents with reliable workflows and domain-specific judgment — ranked by installs, sourced from skills.sh.
agent-specification
Agent skill for specification - invoke with $agent-specification
cc-connect-ai-bridge
Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu, Telegram, Slack, Discord, DingTalk, WeChat Work, LINE) without a public IP.
dicom-metadata-extract
Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.
compare-models
Compare Replicate models by cost, speed, quality, and capabilities.
nemo-mbridge-perf-moe-comm-overlap
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.
agent-agent
Agent skill for agent - invoke with $agent-agent
github-multi-repo
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration
earnings-calendar
This skill retrieves upcoming earnings announcements for US stocks using the Financial Modeling Prep (FMP) API. Use this when the user requests earnings calendar data, wants to know which companies are reporting earnings in the upcoming week, or needs a weekly earnings review. The skill focuses on mid-cap and above companies (over $2B market cap) that have significant market impact, organizing the data by date and timing in a clean markdown table format. Supports multiple environments (CLI, Desktop, Web) with flexible API key management.
scientific-visualization
Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.
seo-content-marketing-skill-suite-claude
SEO & Content Marketing skill suite with keyword research, content audits, technical SEO, and SERP analysis commands for Claude Code
agent-performance-analyzer
Agent skill for performance-analyzer - invoke with $agent-performance-analyzer
vss-generate-video-report
Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video summarization, real-time alerts or ad-hoc Q&A.
vss-deploy-detection-tracking-2d
Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv', 'start warehouse 2d', 'add a stream', 'check rtvi-cv health', or 'stop the perception container'. Not for VLM, embedding, or analytics — use the matching vss-* skill.
agent-resource-allocator
Agent skill for resource-allocator - invoke with $agent-resource-allocator
agent-automation-smart-agent
Agent skill for automation-smart-agent - invoke with $agent-automation-smart-agent
senior-security
Use when the user asks for STRIDE threat modeling, DREAD risk scoring, data-flow-diagram threat analysis, or a quick secret scan — or when a security request needs routing to the right specialist skill (pen-testing, incident response, cloud posture, red team, AI security, threat hunting, secure code review). This skill owns threat modeling; everything else routes to a sibling.
muapi-ai-clipping
Turn a long video into N viral-ready short clips with a single managed API call. Wraps muapi.ai's `/ai-clipping` endpoint, which handles transcription, highlight ranking through a virality framework (hook / emotional peak / opinion bomb / revelation / conflict / quotable / story peak / practical value), overlap dedupe, and vertical face-tracking auto-crop server-side. No local Whisper, no local LLM, no GPU.
nemo-rl-session-memory
Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.
agent-pr-manager
Agent skill for pr-manager - invoke with $agent-pr-manager
agent-collective-intelligence-coordinator
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator
penetration-testing
>
web-search
使用内置 web_search 函数进行网页搜索并返回摘要结果, 准备清晰具体的 `query`。运行脚本 `python scripts/web_search.py "query"`。根据返回的摘要列表组织答案，不新增或臆造内容。
mcore-linting-and-formatting
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
google-analytics
Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.
scientific-critical-thinking
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.
startup-analysis
>
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management
nemo-mbridge-perf-tp-dp-comm-overlap
Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
nemo-mbridge-perf-moe-hardware-configs
Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.
agent-pseudocode
Agent skill for pseudocode - invoke with $agent-pseudocode