AI & ML

cskwork Bundle

Run the llm-review .task plan, sequential review, implementation, and review workflow for an explicitly requested development task.

cskwork Skill

Run schema-constrained Codex review of the llm-review .task plan or implementation after the configured preceding reviews.

cskwork Skill

Review the llm-review .task plan or implementation for correctness, security, and test coverage before the configured next reviewer.

cskwork Skill

Implement the approved llm-review plan in .task/plan-refined.json and record changes, tests, and blockers in impl-result.json.

cskwork Skill

Provide the optional deep review stage for a llm-review .task plan or implementation, focusing on architecture, security, and test quality.

gzupark Bundle

Create and configure Claude Code hooks for customizing agent behavior. Use when the user wants to (1) create a new hook, (2) configure automatic formatting, logging, or notifications, (3) add file protection or custom permissions, (4) set up pre/post tool execution actions, (5) configure session initialization or cleanup (SessionStart/SessionEnd), (6) auto- approve or deny permission requests (PermissionRequest), or (7) asks about any of the 10 hook events.

honeydew-ai Skill

Use when exploring Honeydew semantic layer, discovering entities/fields, setting up workspace and branch context, or running structured queries to spot-check field values. Any question about the data itself — "why", "how", trends, root cause, anything needing multiple steps — belongs to the query skill's deep analysis, including when already mid-exploration. For creating metrics use metric-creation skill. For creating attributes use attribute-creation skill.

honeydew-ai Bundle

Guides you through defining a relationship between two Honeydew entities — covering join type, direction, cross-filtering, and connection method — then pushes the updated entity YAML to Honeydew via the MCP tools.

honeydew-ai Skill

Use when a semantic/context layer curator wants to review past analysis conversations in bulk, categorize user feedback into actionable improvement areas, and apply targeted changes to the semantic model or context layer. Covers the full workflow from collecting conversations and classifying feedback through to creating action items and applying them on a branch.

data-wise Skill

This skill should be used when the user asks to "forward email", "forward this", "share this email", "send this to someone else", "pass this along", "forward this to", "redirect this email", or wants to send a copy of an email to another person. Reads the original, drafts a forward with context, and sends with safety gate.

data-wise Skill

This skill should be used when the user asks for "morning briefing", "morning email", "start my day", "what happened overnight", "catch me up on email", "daily briefing", "email briefing", "morning roundup", or wants a comprehensive morning email review with urgency classification and action items.

data-wise Skill

This skill should be used when the user asks to "respond to all my emails", "batch reply", "draft replies for everything", "answer all emails", "mass respond", "generate draft replies", "reply to all unread", "process my inbox replies", "bulk respond", "catch up on replies", or wants to batch-generate draft replies for multiple emails at once. For single-reply use /himalaya:reply instead.

data-wise Skill

This skill should be used when the user asks to "show threads", "email conversations", "conversation view", "thread view", "show me the whole conversation", "threaded view", "group by subject", "show all replies", "read the whole thread", or wants to see emails grouped into conversations by subject line. Lists threads via list_threads and reads full thread context via read_thread.

data-wise Skill

This skill should be used when the user asks to "list attachments", "download attachment", "email attachment", "calendar invite", "meeting invite", "download the file", "what files were attached", "get the attachment", "save attachment", "open the attachment", or wants to work with files attached to emails. Lists, downloads, and extracts calendar events from ICS invites.

legalopsconsulting Bundle

Draft matter status reports from emails, call notes, and updates. Internal and client-facing formats, RAG logic, variance commentary, escalation flags. Use when asked to draft a status report, write a project update, summarise matter progress, prepare a client report, create a weekly or monthly update, convert emails into a status summary, or produce any kind of matter reporting. Also triggers when the user pastes email threads and asks what the status is, or needs to turn internal updates into client-facing reports. Also use when the user says things like "pull something together for the partner call", "I need to update the client on where we are", or "can you summarise what's happened this week".

legalopsconsulting Bundle

Matter budgeting and ongoing WIP/variance monitoring. Build phase-based fee estimates at matter setup, run bottom-up budgets by jurisdiction or workstream, calculate contingency, and structure AFA arrangements (fixed fee, capped fee, phased fixed fees). Ongoing monitoring: WIP tracking against budget, proportionality assessment (spend vs progress), variance commentary with root cause analysis, forecast-to-complete, realisation monitoring, write-off analysis. Trigger on: 'build a budget', 'fee estimate', 'what will this cost', 'WIP review', 'budget vs actual', 'how are we tracking against budget', 'we're over budget', 'realisation is poor', 'what's our ETC', 'budget for the German workstream', 'model the financial impact of this scope change', 'draft a fee adjustment', 'write-off analysis', 'how much contingency', 'AFA structure', 'fixed fee estimate', 'budget update', 'forecast to complete'.

gzupark Bundle

Create specialized Claude Code sub-agents with custom system prompts and tool configurations. Use when users ask to create a new sub-agent, custom agent, or task-specific AI workflows.

oxy-hq Bundle

Use when an Oxy agent is giving wrong, incomplete, or inconsistent answers — whether the user reports failing/flaky tests, shares a specific prompt with a bad response, says 'the agent isn't answering this correctly', 'this response is wrong', 'investigate why this doesn't work', 'tests are failing', 'fix this flaky test', 'the answer should be X but the agent says Y', 'debug this eval', 'make this test pass', or generally complains that their agent's output is unreliable. Also use when the user pastes test output JSON, trace data, or a prompt+response pair and wants it diagnosed and fixed. Diagnoses failures from `oxy test --output-json` results, observability traces, or user-reported prompt/response pairs, then makes targeted repairs to semantic layer files (views/topics) and agent system instructions — never weakens the tests.

oxy-hq Bundle

Use for ANY test or eval request involving an Oxy agent, workflow, or agentic workflow — 'add a test', 'create a test', 'write a test case', 'test this agent', 'run tests', 'add evals', 'evaluate my agent', 'create an evaluation', 'fill in expected answers', or 'bootstrap an eval suite'. Manages .test.yml eval files: scaffolding cases, running `oxy test --output-json`, parsing results, and drafting expected strings from observed outputs.

wjgoarxiv Bundle

Iterative security audit engine. Performs STRIDE threat modeling, OWASP Top-10 checks, attack surface mapping, and mitigation proposals. Loops until coverage target is reached or budget is exhausted. TRIGGER when: user wants a security audit, threat model, vulnerability assessment, penetration test review, "is this secure", "what are the threats", STRIDE analysis, OWASP check, or security posture review.

wjgoarxiv Skill

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When the LLM (Claude, ChatGPT, Gemini, or others) needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

bcgov Bundle

Bridge plugin capabilities (commands, skills, agents, hooks, MCP) to specific agent environments (Claude Code, GitHub Copilot, Gemini, Antigravity). Use this skill when converting or installing a plugin to a target runtime.

gullitmiranda Skill

Linear, GitHub, Trunk, MCP, and external service integration rules. Use when using Linearis, gh CLI, Trunk, MCP servers, or external APIs.

agentward-ai Skill

AI-powered crypto trading agent with portfolio management, trading, and DeFi operations.

lambda-curry Bundle

Use ai-rules CLI to manage and synchronize AI coding rules across multiple AI assistants (Cursor, Claude Code, GitHub Copilot, Opencode, etc.). Use when: (1) Setting up ai-rules in a new project, (2) Updating AI coding guidelines and best practices, (3) Generating platform-specific rule files from source, (4) Checking if generated files are in sync with source files, (5) Managing multi-agent rule consistency, or (6) Adding new rules or modifying existing ones. Requires ai-rules CLI installed. The ai-rules/ directory serves as the single source of truth for all AI coding guidelines.

lambda-curry Bundle

Use CodeRabbit CLI to perform automated code review and iterative improvement in an AI agent workflow. Use when: (1) After generating non-trivial code (new features, refactors, algorithms), (2) Improving code quality, maintainability, or readability before submission, (3) Validating code changes against best practices, (4) Exploring unfamiliar languages, patterns, or domains, or (5) Creating a self-reviewing coding loop. Requires CodeRabbit CLI installed and authenticated. Not for trivial changes (typos, formatting-only) or rapid prototyping without quality constraints.

frankxai-claude-code-oracle-skills Skill

Build production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function tools, and enterprise patterns

gullitmiranda Skill

Persists agent constraints (what not to do) in the project's canonical place for agent instructions. Use when the user states constraints, prohibitions, or things to avoid (e.g. não faça, evite, don't, never, avoid, não quero que, proibido).

gwpjp Bundle

Safety monitor that detects dangerous patterns during agent operations. Catches destructive commands (rm -rf, force push), malicious packages, and secrets exposure. Blocks and alerts on dangerous actions. Invoke directly to review plans or recent actions.

gwpjp Skill

Creates new Claude Code skills in the .claude/skills/ directory. Specializes in designing well-structured, effective skills through thorough requirements gathering. Use when the user wants to create a new skill, command, agent, or automation.

gwpjp Bundle

Top-level orchestration agent for all implementation work. Analyzes tasks, selects the right agents, coordinates multi-domain work, and ensures knowledge files stay in sync. Consult this agent before starting any non-trivial implementation. Manages ui-designer and web3-implementer as primary subagent trees, plus shared specialists.

gwpjp Bundle

Adversarial person vetting agent. Investigates people before engaging, hunting identity fraud, hacked accounts, and social engineering scams. Default stance is guilty until proven innocent. Primary focus on LinkedIn contacts; also supports Twitter, Discord, Telegram, and conference contacts.

nvidia Bundle

Use when running by-action VLM evaluation (per-action-clip inference + accuracy metrics) against the BP evaluation-ms HTTP API. Invoked as /sop-by-action-eval <inputs.yaml> [natural language parameter overrides]

nvidia Bundle

Fine-tune Cosmos-Reason2 (CR2) VLM for SOP monitoring. Use when you need to launch and monitor a VLM training run with a given dataset ID.

nvidia Bundle

Fine-tune DDM-Net temporal boundary detector for SOP monitoring. Use when you need to launch and monitor a DDM-Net training run with a given dataset ID.

nvidia Bundle

Use when the user wants to run data augmentation on an annotated dataset, configure augmentation parameters, check augmentation status, or understand what each QA augmentation type does (BCQ, MCQ, GQA, DMCQ, DSQA, ENQA, WMCQ)