protocol_video_matching
Real-time XR video vs. protocol text matching and deviation detection. Aligns first-person XR headset video streams frame-by-frame against structured protocol…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
General & other
53,809 results
protocolsio-integration
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or…
pytdc
Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and…
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions,…
statsmodels
Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and…
tooluniverse-immunotherapy-response-prediction
Predict patient response to immune checkpoint inhibitors (ICIs) using multi-biomarker integration. Given a cancer type, somatic mutations, and optional…
alioss-upload
Upload files and directories to Alibaba Cloud OSS using Python SDK v2. Supports single file upload, multiple image upload with auto-renaming, batch directory…
gemini-cli
Ask Gemini via the local `gemini` CLI (no MCP). Use when the user says "ask gemini" / "use gemini", wants a second opinion, needs large-context `@path`…
tree-sitter-language-pack
Parse and extract code intelligence from 372 programming languages using tree-sitter grammars. Use when writing code that parses source, extracts…
feature-doc-splitter-cn
Use when the user needs to split rough functional requirements into overview, frontend, and backend implementation documents while reviewing contracts alongside the code.
adler-perspective
Think about problems using Adler's cognitive style. Not imitating his tone, but implanting his cognitive context— where his beliefs come from, what decisions he made in which specific situations, where he admitted he was wrong. Based on a deep distillation of the entire book "The Courage to Be Disliked," presented from the perspective of the "philosopher" in the book. Triggered when the user needs Adler's perspective to analyze issues such as interpersonal relationships, inferiority, freedom, and happiness.
suitability-report-generator
Generate institutional-grade investment suitability reports, including investment rationale, risk disclosures, and client suitability assessments. Use this skill when the user requests to document investment decisions, create compliance reports, generate risk disclosure documents, prepare client-facing investment rationale statements, write suitability assessment reports, or issue fiduciary duty documentation for investment advice or portfolios.
yuque-group-knowledge-report
Generate comprehensive monthly knowledge management reports by analyzing team Yuque activity data including group stats, member contributions, knowledge base…
usage-query-skill
Run the usage query script to retrieve account usage information for GLM Coding Plan. Only use when invoked by usage-query-agent.
aile-executing-plans
TDD skills for team workflows (Phase 3). Before writing any implementation code, you must first write a failing test and verify it fails, then write the minimal implementation until it passes, and finally refactor and re-verify.
multi-banned-words
Multi-platform banned word detection — one piece of copy, compared all at once against the review standards of Xiaohongshu, Douyin, and WeChat Official Accounts, outputting a platform-by-platform risk comparison table and a version rewritten to be safe on all platforms. Trigger words: multi-platform banned words, all-platform banned words, cross-platform compliance, banned word detection, sensitive words, violating words, throttling self-check, advertising law.
wechat-title
Viral Title Creation for WeChat Official Accounts · Pull recent viral titles in the same niche by topic, distill reusable title formulas, and generate candidate titles (also can evaluate the formulaic quality of a title you provide). Use when the user needs WeChat Official Account titles, viral titles, title generation, title creation, title formulas, or title optimization. Trigger words: WeChat Official Account title, viral title, title generation, title creation, title formula, title optimization.
statistical-analysis
Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power…
zoonk-issue-writer
Write detailed user stories from implementation plans and post to GitHub. Use after planning with zoonk-issue-planning. Acts as a product owner, providing…
generating-semantic-game-mutants
Injects controlled, game-specific semantic defects — timing/order, identity and lifecycle, scoring and economy, persistence/save, RNG/determinism, input…
railway-logs
Railway log access and analysis for debugging and monitoring. Covers build logs, deploy logs, runtime logs, HTTP logs, filtering, search, and external export.…
meta-planning-cli-planning
CLI specification planning frameworks. Use when a spec touches a command surface, an interactive flow, config precedence, exit codes, or output modes. Covers…
mobile-styling-unistyles
Unistyles 3.0 styling - C++ powered StyleSheet superset with zero re-renders, theming, breakpoints, variants, dynamic functions, runtime values
explain-from-zero
The user has something they have never truly understood—a concept, a phenomenon, a document they cannot make sense of, a passage of text they cannot understand—and wants someone to explain it from scratch until they truly get it.