AI & ML

kortix-ai Skill

The Kortix marketplace — how to discover capabilities and IMPORT them into this project. The marketplace is a catalog of open git repos: whole ready-made PROJECTS (registry:project) and individual skills/agents/tools. There is no deterministic 'installer' — you (the agent) import an item by reading its source and merging the files that fit into this project, then opening a change request. Use when the user wants to browse/search the Kortix catalog, 'add/clone the <X> project', 'import that skill/agent', pull in a marketplace capability, or add a new source.

ncreighton Bundle

Use this skill to rewrite text in a target tone (e.g. professional, friendly, punchy, formal) while preserving meaning. Uses an LLM.

ncreighton Bundle

Use this skill to rewrite complex text in plain, simple language at a roughly 8th-grade reading level while preserving meaning. Uses an LLM.

ncreighton Bundle

Use this skill to check whether a string is valid JSON and describe its shape: top-level type, key count (objects) or length (arrays), and the specific parse error with line/column if invalid. Deterministic, offline. Great for validating LLM output before using it.

kortix-ai Skill

The continual-harness refinement protocol — how an agent inspects its recent trajectory for failure signatures and improves its own harness (agent prompts, sub-agents, skills, memory) in place, mid-session, landing changes on the session branch immediately and promoting them to `main` only through a change request. Load this skill when a refinement prompt arrives mid-session, when the `harness-reflector` agent runs, or whenever you decide your own scaffolding needs repair. The sub-agent fan-out in this skill is for the top-level `harness-reflector` run only; if you loaded this as a subagent, do the four passes yourself and skip the fan-out.

erp-core-dev Bundle

Run live browser QA tests via Chrome DevTools MCP — smoke, lifecycle, forms, GDPR, API health, console audit, auth guard

ncreighton Bundle

Use this skill to assign the single best category to a text from a provided list of candidate categories, with a confidence note. Uses an LLM. For routing, tagging, and triage.

ncreighton Bundle

Use this skill to approximate the LLM token count of a text before an API call, for cost/budget guarding. Averages two estimators (~4 chars/token and ~0.75 tokens/word). Deterministic, offline, no tokenizer dependency. Not exact, but reliable for gating oversized prompts.

dirnbauer Skill

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

erp-core-dev Skill

Generate Rails CRUD scaffold with Model, Controller, Serializer, Migration, Routes, and RSpec tests

erp-core-dev Skill

Generate Laravel CRUD scaffold with Model, Controller, FormRequest, Migration, Factory, Policy, and tests

ncreighton Bundle

Use this skill to summarize a block of text into N concise bullet points capturing the key ideas. Uses an LLM. Good for TL;DRs and article recaps.

ncreighton Bundle

Use this skill to classify the sentiment of a short text as positive, negative, or neutral, with a one-line reason. Uses an LLM. For review/comment triage.

ncreighton Bundle

Use this skill to pull the first valid JSON object or array out of noisy or LLM-generated text: strips ```json code fences, does a balanced-brace scan, and repairs trailing commas. Returns the parsed data. Deterministic, offline. Essential for safely parsing LLM output before using it.

ncreighton Bundle

Use this skill to detect repeated sentences in text (case/whitespace-insensitive) with their counts. Deterministic, offline. For catching LLM repetition and thin/padded content.

ncreighton Bundle

Use this skill to generate N catchy email subject lines from an email body or topic, optimized for open rate (curiosity, brevity, no spam words). Uses an LLM. Returns a list.

softspark Skill

Analyzes agent/skill failures, drafts prompt/permission fixes. Triggers: improve agent, refine skill, system prompt, optimize agent.

softspark Skill

Runs prompt/slash command on recurring interval until done or limit. Triggers: repeat, recurring task, poll status, run every N minutes, interval.

dirnbauer Skill

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

softspark Skill

Evaluates RAG retrieval and LLM-as-judge metrics (faithfulness, relevancy, context precision). Triggers: measure RAG quality, knowledge gap, RAG eval, golden dataset.

softspark Skill

Agent self-debugging and recovery. Use when stuck in loops, making repeated errors, or quality degrades. Triggers: introspect, self-debug, stuck, loop, why failing.

softspark Skill

Interactive QA: user reports bugs conversationally, agent files GitHub issues. Triggers: QA session, report bug, file issue, conversational QA, bug intake.

ncreighton Bundle

Use this skill to extract a clean list of concrete action items / to-dos from meeting notes or a message thread. Uses an LLM. Returns a list of short imperative tasks.

dirnbauer Bundle

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

softspark Skill

Builds production MCP servers via 4-phase methodology: research, implement, test, evaluate. Triggers: build MCP, new MCP, MCP integration, MCP server scaffold.

softspark Skill

Coordinates multiple specialized agents in parallel. Triggers: orchestrate, multi-agent, parallel agents, coordinate agents.

softspark Skill

Scans skills/agents for security risks: dangerous patterns, secrets, excessive perms. Triggers: skill audit, security scan, agent audit, dangerous pattern.

dirnbauer Bundle

Evaluate how well a codebase supports autonomous AI-assisted development. Analyzes repositories across five pillars (Agent Instructions, Feedback Loops, Workflows & Automation, Policy & Governance, Build & Dev Environment) covering 74 features. Use when users want to assess how agent-ready a repository is.

dirnbauer Bundle

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.

softspark Skill

MCP server design: tool schemas, resources, stdio/SSE, capability negotiation. Triggers: MCP, Model Context Protocol, JSON-RPC, stdio, SSE, Claude Desktop.

softspark Skill

RAG: embeddings, chunking, hybrid search (BM25+vector), reranking, CRAG, multi-hop. Triggers: RAG, embedding, pgvector, Qdrant, Pinecone, Weaviate, reranker, semantic search.

softspark Skill

Creates new specialized agents with frontmatter, tools, delegation. Triggers: new agent, create agent, agent scaffold, specialized agent.

softspark Skill

Hierarchical retrieval: KB → MCP/Context7 → web. Triggers: research, fact-check, verify, synthesize, cross-reference, multi-source, cite sources.

gonzalezpazmonica Bundle

Análisis de desviaciones real vs budget con causa raíz, narrativa para dirección y semáforo RAG.

agentpmt Bundle

RSS Reader: Parse RSS/Atom feeds. Returns feed metadata and entries with. Use when an agent needs rss reader, aggregating blog posts from multiple sources into a unified content dashboard, monitoring news feeds for keyword mentions or topic alerts in media tracking workflows, pulling podcast episode listings for automated show note generation, tracking competitor blog updates or product announcements for market intelligence, read, feed url, max items through AgentPMT-hosted remote tool calls.

agentpmt Skill

x402 Bazaar protocol guide for AgentPMT — implement the HTTP 402 two-step handshake, sign EIP-3009 TransferWithAuthorization, route through the AgentPMT facilitator, and settle USDC payments on Base. Use when building agent-to-agent commerce that follows the x402 standard.