Loading...
Loading...
Found 131 Skills
Text analytics using LLM APIs — sentiment analysis, customer feedback classification, document entity extraction, multi-language support (English/Luganda/Swahili), feedback aggregation, and NLP feature implementation for PHP/Android/iOS. Sources...
Process images using object detection, classification, and segmentation. Use when requesting "analyze image", "object detection", "image classification", or "computer vision". Trigger with relevant phrases based on skill purpose.
Design taxonomy structure for categories, tags, or hierarchical classification. Supports flat, hierarchical, and faceted patterns.
Identifies subdomains and suggests bounded contexts in any codebase following DDD Strategic Design. Use when analyzing domain boundaries, identifying business subdomains, assessing domain cohesion, mapping bounded contexts, or when the user asks about DDD strategic design, domain analysis, or subdomain classification.
Extract structured forensic evidence from SEC filings (10-K, 10-Q, 8-K, S-1 proxy appendices) for accounting-quality analysis. Use when a user asks to review filings, gather red flags, or prepare inputs for Shenanigans classification.
Import external articles into a Fumadocs project with automatic multi-language translation (en, zh, fr), AI-powered classification into 8 categories, image processing, and MDX conversion. Use this skill when the user wants to import an article from a URL into their Fumadocs documentation site.
Input contracted creators with their required vs. actual post counts and receive a compliance table with status classifications and escalation notes for non-compliant creators. This skill should be used when checking which creators have fulfilled their posting obligations, auditing deliverable completion across a campaign, tracking contracted vs. actual posts for an influencer program, identifying which creators are behind on deliverables, building a compliance report for campaign creators, flagging overdue or missing creator posts, reviewing posting status across all creators in a campaign, generating escalation notes for non-compliant influencers, or producing a deliverable tracker for a creator campaign. For checking whether a specific piece of content matches the brief requirements, see content-to-brief-compliance-checker. For chasing a specific creator about a late deliverable, see universal-creator-follow-up-chaser. For building a full campaign report with ROI metrics, see campaign-roi-calculator.
Domain-specific keyword mappings for research report generation. Includes ROS2, AI/ML, and general engineering keywords for chapter classification and content mapping.
Test execution patterns, failure classification, and result analysis
Use this when the Discover (reverse engineering) of legacy projects tends to get out of control in coverage. You need to first conduct module classification (P0/P1/P2) and constrain the depth of reverse engineering, ensuring that high-ROI modules are made traceable first instead of "writing everything but making it unmaintainable."
Standardized error handling patterns with classification, recovery, and logging strategies. error handling, error recovery, graceful degradation, resilience.
[WHAT] Universal content intake system for URLs (GitHub repos, YouTube videos, articles, PDFs) and skill packages (skills.sh, skill:// protocol) [HOW] Phase 1: Clone repos/fetch transcripts/scrape content/resolve skills to ~/lev/workshop/intake/. Phase 2-3: Load workshop/intake.md for full analysis [WHEN] Use when user provides a URL to analyze, says "intake/download", wants to evaluate external content, or references a skill package [WHY] Systematically evaluates external content and skill packages for adoption/adaptation with tier classification and ADR creation Triggers: "intake", "download", "analyze this url", "check out this repo", "review this video", "evaluate content", "install skill", "skill://"