Loading...
Loading...
Found 7,118 Skills
An intelligent search router based on the opencli command. This skill must be used when users want to search, query, look up or research information, especially when it involves specified websites, social media, technical materials, news, shopping, travel, job hunting, finance or Chinese content.
Open source eBPF-based network monitoring and blocking components for Little Snitch on Linux
Build a complete, production-ready full-stack web application from PRD documents, prototype images, and resource files. Handles the entire pipeline: system design, database schema, seed data, backend API, frontend UI, visual verification against prototypes, and deployment script generation. Use this skill whenever the user: - Provides a PRD (product requirement document) and wants a working app built - Says things like "根据PRD开发", "build from PRD", "implement this product", "把需求文档做成应用", "develop this app from requirements" - Has prototype images + requirements and wants full-stack implementation - Wants to turn product specifications into a running web application - Mentions building an app from wireframes/mockups combined with a requirements doc Trigger this skill even if the user just says "帮我开发" or "build this" with PRD materials present in the working directory.
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources → wiki → schema). Also use when discussing knowledge management strategy, wiki structure decisions, or how to organize distilled knowledge. This is the "theory" skill — other skills handle specific operations (ingesting, querying, linting).
Migrate codebase from try/catch or Promise-based error handling to better-result. Use when adopting Result types, converting thrown exceptions to typed errors, or refactoring existing error handling to railway-oriented programming.
Comprehensive automation for Letterly transcriptions. This skill exports the latest CSV from Letterly, processes "magic" notes into Obsidian markdown with custom metadata, semantically links them using a vector database, and moves them to the final Transcriptions directory. Use when the user asks to "process new letterly transcriptions", "sync letterly", or "import magic notes from letterly".
Use when structuring or refactoring Convex codebases with Domain-Driven Design boundaries, repository abstractions, adapters for external APIs, and transaction-safe workflows.
Apply when improving VTEX IO Node or .NET services for latency, throughput, and resilience: in-process LRU, VBase, stale-while-revalidate, AppSettings loading, request context, parallel client calls, and avoiding duplicate work. Covers application-level performance patterns that complement edge/CDN caching. Use when optimizing backends beyond route-level Cache-Control.
Build diversified portfolios using correlation analysis, efficient frontier construction, and factor-based diversification. Use when the user asks about portfolio variance, correlation effects, the efficient frontier, minimum variance portfolios, diversification ratios, or factor diversification. Also trigger when users mention 'don't put all eggs in one basket', 'how many stocks do I need', 'correlation breakdown in a crisis', 'are my holdings really diversified', 'risk contributions', or ask why diversification fails during market crashes.
Routes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module subsets — one parquet for k-NN mining, one for AnomalyGen (Cosmos SDG) — based on each module's label eligibility. Use as the immediate next step after DEFT gap analysis in a VCN AOI SDA iteration.
Use when building features with **Claude Code** in any codebase and the work should go through a disciplined build → review → test → fix loop. Triggers on "run the build loop", "build the next task", "continue the plan", "build this feature properly", or any request to implement work from a plan file or a direct feature prompt. Builds from the plan (or the prompt if no plan exists), runs Claude Code's `/review` (plus `/security-review` for sensitive surfaces) and fixes every issue found, tests and verifies the feature end to end, fixes anything testing surfaces, and reports back once complete. Repeats until all plan tasks are checked off.
Transforms raw meeting transcripts into high-fidelity, structured meeting minutes with iterative review for completeness. This skill should be used when (1) a meeting transcript is provided and meeting minutes, notes, or summaries are requested, (2) multiple versions of meeting minutes need to be merged without losing content, (3) existing minutes need to be reviewed against the original transcript for missing items, (4) transcript has anonymous speakers like "Speaker 1/2/3" that need identification. Features include: speaker identification via feature analysis (word count, speaking style, topic focus) with context.md team directory mapping, intelligent file naming from content, integration with transcript-fixer for pre-processing, evidence-based recording with speaker quotes, Mermaid diagrams for architecture discussions, multi-turn parallel generation to avoid content loss, and iterative human-in-the-loop refinement.