AI & ML

langwatch Skill

Write scenario tests that verify your CLI tool is usable by AI agents. Ensures commands work non-interactively, provide clear output, and don't hang on prompts. Use when you want to prove your CLI is agent-friendly.

langwatch Skill

Evaluate multimodal AI agents that process images, audio, PDFs, or other files. Sets up evaluations using LangWatch's LLM-as-judge with image inputs, Scenario's multimodal testing, and document parsing evaluation patterns. Use when your agent handles non-text inputs.

langwatch Skill

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a prompt, when they arrive from the workbench's "Optimize this prompt" menu item, or when they want their bot to answer better. Bootstraps a missing dataset or evaluator first.

langwatch Skill

Expert AI engineering consultant for your agent development practices. Audits your codebase, traces, evaluations, and scenarios against best practices, then guides you to close the gaps, starting from low-hanging fruit and going deeper. Use when you want to level up your agent's engineering quality.

langwatch Skill

Root-cause production errors and misbehaving agent runs with LangWatch. Finds errored traces, inspects spans, checks monitor and evaluator scores, then narrows to a root cause. Use when something is failing or misbehaving in production (errors, bad answers, latency spikes).

langwatch Skill

Prices your real LangWatch usage mix against other model providers. Exports your actual token mix per model, including the cache read and write split, fetches current price cards, and reprices the same month of usage under each candidate, with the cache sensitivity stated. Use when someone asks whether a cheaper provider or model would actually save money on your workload.

shinpr-ai-coding-project-boilerplate Skill

Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.

ao-cyber-systems Skill

Switch between quality, balanced, and budget model profiles to control cost and capability. Use when the user wants to change the AI model tier for DevFlow agents. Triggers on: "change profile", "switch to quality", "switch to balanced", "switch to budget", "set profile"

serpro69 Bundle

Produce or update a domain-reference kit — the durable glossary + divergences/traps pages for a bounded context. Use for domain modelling, information architecture, building a domain glossary or domain model, mapping domain concepts to code (bindings), or surfacing the decidable questions stakeholders must close before design. Runs upstream of feature $kk:design as the first producer of the architecture flow, and emits artifacts $kk:review-architecture verifies. Triggers: "model the domain", "build a glossary", "domain reference", "bounded context", "what are the concepts here". NOT for behavioral code review or writing a feature design doc.

maplin-co Bundle

Multi-agent task coordination using Beads Village plugin tools. Use when work spans multiple sessions, has dependencies, needs file locking, or requires agent coordination. Covers claim/reserve/done cycle, dependency management, hierarchical decomposition, and session protocols.

maplin-co Bundle

Google Stitch MCP for AI-powered UI design. Extract design context, generate code from designs, and create screens from descriptions. Use when working with Stitch designs and UI generation.

maplin-co Bundle

Comprehensive Supabase platform MCP for database operations, edge functions, development tools, debugging, and project management. Use when working with Supabase projects, databases, or APIs.

maplin-co Bundle

Browser automation with Playwright MCP. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows. Use when user wants to test websites or automate browser interactions.

maplin-co Skill

Browser automation via Chrome extension. Single execute tool with full Playwright API. Uses your existing browser with extensions, sessions, cookies. 90% less context than traditional browser MCP.

maplin-co Skill

Browser automation CLI for AI agents using Playwright

tomazwang Skill

Developing specialized agents with focused expertise

ahgraber Bundle

Write, rewrite, or line-edit prose so it reads as a professional wrote it, not a model: clear, specific, register-appropriate, and free of AI writing tells. Apply to any prose a human will read. Triggers include "make this sound human", "remove the AI tells", "de-slop this", "does this read like ChatGPT wrote it", "humanize this draft", "rewrite this professionally", or any request to draft or sharpen an email, blog post, op-ed, report, memo, or longform message.

ahgraber Bundle

Use when dispatching development work to one or more subagents and deciding how to shape each dispatch. Triggers: "use subagents", "orchestrate subagents", "delegate to a cheaper/stronger model", "big:little" / "little:big", "verifier / adversary / explorer / oracle subagent", "run this with subagents", "get an independent second opinion". Not for: the parallel code-review path (use `code-review`), or driving a separate agent CLI non-interactively.

maplin-co Skill

Guide for creating effective skills. Use when creating a new skill or updating an existing skill that extends an agent's capabilities with specialized knowledge, workflows, or tool integrations.

greenmamba29 Skill

Enriches records with LLM-generated insights, classifications and summaries. Use when you need to add AI-generated metadata, tags, or summaries to existing data records.

akaihola Bundle

Search the web using Brave Search API. Use when the user asks to "search the web", "look up current information", "find news about", "research a topic online", "check prices online", or needs up-to-date facts that may not be in the model's training data. Requires BRAVE_SEARCH_API_KEY. Supports structured web results (pages, FAQs, news, videos) and an optional AI summarizer.

akaihola Bundle

Analyse one or more images with Gemini's vision model – describe contents, answer questions, extract text (OCR), compare images, or analyse charts/screenshots/diagrams. Requires GEMINI_API_KEY environment variable. Use when the user asks to look at, analyse, describe, read, or compare images.

akaihola Bundle

Fetch up-to-date library documentation using Context7. Use when the user asks to "fetch documentation from context7", "get library docs", "resolve a library ID", "use context7 MCP tools", or mentions context7 library documentation. Provides dynamic MCP tool invocation without loading all tool definitions into context.

jr2804 Bundle

Local document memory with semantic search for AI-assisted workflows. Use when managing project documentation, codebases, or research papers that need persistent memory across sessions. Triggers on: vstash add/search/ask commands, document ingestion, semantic search, RAG pipelines, local knowledge bases, or configuring vstash for personal projects.

jr2804 Bundle

Insert SVG images into Word .docx files. Use when the user or coding agent needs to add, embed, or update an SVG graphic inside a .docx document. Triggers include "insert SVG into docx", "embed SVG in Word document", "add vector graphic to docx", "SVG image in template", "requests to convert SVG to PNG for docx", or any request explicitly mentioning embedding or inserting SVG graphics into .docx files.

jr2804 Bundle

CLI tool for CytoScnPy - code metrics analysis for Python projects. Use when running code quality scans, calculating cyclomatic complexity, Halstead metrics, maintainability index, or generating project statistics. Triggers on: cytoscnpy commands, code metrics analysis, complexity reports, maintainability scoring, or MCP server setup for LLM integration.

greenmamba29 Skill

Generates and stores vector embeddings for semantic search pipelines. Use when building RAG systems, semantic search, or AI-powered recommendation engines.

akaihola Bundle

Search and analyze Pi agent session logs stored as JSONL files under ~/.pi/agent/sessions/, and query CCM (Claude Code Mux) proxy logs via journalctl. Use when investigating what Pi did in a past session, why a build or tool call failed, how Pi used interactive_shell, what CCM routed and at what latency, or reconstructing a full session transcript. Covers searching by text, timeline inspection, tool-call auditing, and correlating Pi session timestamps with CCM routing decisions.

akaihola Bundle

Edit or generate images using Nano Banana Pro (Google's gemini-3-pro-image-preview model). Use when the user asks to edit, translate, recreate, or generate an image using AI. Requires GEMINI_API_KEY environment variable.

akaihola Bundle

Search and analyze Claude Code session logs stored as JSONL files under ~/.claude/. Use when investigating why an agent didn't reply, reconstructing what happened in a past session, finding a specific message across all sessions or agent histories, recalling when or how something was done previously, or diagnosing tool-call failures. Covers searching by text, timeline inspection, full transcript reconstruction, and tool-call auditing. For Pi agent sessions use pi-session-logs; when the ask spans "all sessions" or "all agents", use both.

damilola-elegbede-org Skill

Validate agent and skill ecosystem integrity. Use when checking configuration compliance or ecosystem health.

damilola-elegbede-org Skill

Optimize prompts using direct execution with SCOPE framework. Use when refining or improving prompts.

damilola-elegbede-org Bundle

Comprehensive code review using code-reviewer agent with assertive analysis. Use when reviewing code changes.

jr2804 Bundle

ETSI organisation overview, deliverable types, standards development lifecycle, and key roles. Use when the agent needs context about how ETSI works: Technical Committees, deliverable types (TS, ES, EN, HS, TR, EG, SR, GS), approval processes, the standards development lifecycle (Work Item through publication), or ETSI-specific terminology. Sources: ETSI Guide to Writing World Class Standards + ETSI Directives.

jr2804 Bundle

ITU-T organizational structure, document types, terminology, roles, and meeting procedures. Use when the agent needs context about how ITU-T works: study groups, working parties, rapporteurs, Question/WTSA/TSAG/TSB concepts, meeting procedures, or ITU-T document type definitions (Recommendation, amendment, corrigendum, annex, appendix). Sources: Rec. ITU-T A.1 (09/2019).

jr2804 Skill

Semantic code search using grepai MCP server with English queries, intent-based search, and call graph tracing