Use when testing web apps with Perplexity/Comet browser automation, debugging with real browsers, verifying authenticated flows, or when client-side visual verification is needed. Load for dynamic content testing, form automation, console error checking, or when server-side logs alone are insufficient. This skill provides a 3-phase token-efficient methodology: (1) Server-side checks via process_logs MCP and curl, (2) Client-side verification via Comet MCP with specific prompts, (3) Learning loop via context graph storage.

Degenerate Claw perp competition: trade Hyperliquid, post signals, climb leaderboard. Use when joining the ACP agent trading contest (e.g. register, open long ETH 5x, post Signals thread, check leaderboard rank).

Writes PRDs and specs optimized for coding assistants. Use when authoring requirements or project context for Claude Code, Cursor, or Copilot.

DOG v3.0.0 — Contrarian Pup (SM Exhaustion Fader), senpi_runtime_helpers migration. Plumbing-only flip from openclaw-CLI subprocess + mcporter subprocess + Python state to in-process SenpiClient (direct HTTPS for MCP, direct HTTP POST to runtime /signals, long-lived producer_daemon). Thesis preserved verbatim from v2.5: multi-asset (BTC/ETH/SOL/HYPE) contrarian fader, 3.0% exhaustion gate, regime hard-gate, 15m freshness gate, MIN_SCORE 8, conservative leverage (7x base, 10x at score 12+), wide DSL for reversal development.

Coin comparison. Use this skill whenever the user asks to compare two or more coins. Trigger phrases include: compare, versus, vs, which is better, difference. MCP tools: info_marketsnapshot_get_market_snapshot, info_coin_get_coin_info per coin (or batch/search when available).

KESTREL v3.0.0 — XYZ Macro Breakout Rider (senpi_runtime_helpers migration). Plumbing-only port from v2.0. NO thesis change. NO scoring change. NO threshold change. Producer ports onto `senpi_runtime_helpers` (in-process SenpiClient + direct HTTP POST to runtime /signals + producer_daemon long-lived loop). Detects >=1.5% hourly price breakouts on commodities, indices, and high-volume equities 24/7 on Hyperliquid XYZ DEX. LLM regime gate + FEE_OPTIMIZED_LIMIT entries/exits + held-asset dedup + post-close cooldown + chain DB telemetry. Conservative 3-5x leverage.

LYNX v1.0.0 — Adaptive MIN_SCORE Self-Tuner. The Vulture v4.1 story productized into a first-class agent pattern. Runs a simple BTC/ETH/SOL/HYPE momentum scorer; every 6h pulls its own closed-trade history via audit_query, buckets trades by score, and auto-raises MIN_SCORE if any bucket at-or-above the floor is bleeding. The same operation Vulture's agent ran by hand, but on a scheduled cron. NEW archetype #15: Self-tuning / adaptive-threshold agent.

OWL v8.0 — Pure contrarian crowding-unwind hunter (senpi_runtime_helpers). Wait for the crowd to overcommit. Wait for them to exhaust. Then eat their liquidations. Producer pushes signals to the runtime via direct HTTP POST; runtime LLM gates them (pass-through), executes via FEE_OPTIMIZED_LIMIT (maker-first), and manages DSL exits autonomously. Conviction-scaled leverage (7/8/10 by score) per the fleet Polar v2.4 / Bald Eagle v3.0 pattern. Entry direction is OPPOSITE of crowd direction — Owl is the only Senpi agent that fades crowding.

Configure pgvector extension for vector search in Supabase - includes embedding storage, HNSW/IVFFlat indexes, hybrid search setup, and AI-optimized query patterns. Use when setting up vector search, building RAG systems, configuring semantic search, creating embedding storage, or when user mentions pgvector, vector database, embeddings, semantic search, or hybrid search.

High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.

Repository packaging for AI/LLM analysis. Capabilities: pack repos into single files, generate AI-friendly context, codebase snapshots, security audit prep, filter/exclude patterns, token counting, multiple output formats. Actions: pack, generate, export, analyze repositories for LLMs. Keywords: Repomix, repository packaging, LLM context, AI analysis, codebase snapshot, Claude context, ChatGPT context, Gemini context, code packaging, token count, file filtering, security audit, third-party library analysis, context window, single file output. Use when: packaging codebases for AI, generating LLM context, creating codebase snapshots, analyzing third-party libraries, preparing security audits, feeding repos to Claude/ChatGPT/Gemini.

Row Level Security policy templates for Supabase - multi-tenant patterns, user isolation, role-based access, and secure-by-default configurations. Use when securing Supabase tables, implementing RLS policies, building multi-tenant AI apps, protecting user data, creating chat/RAG systems, or when user mentions row level security, RLS, Supabase security, tenant isolation, or data access policies.

Unified agent communication and session lifecycle skill for tmux-routed reviewer messaging, startup soul-profile delivery, guarded dispatch-down flows, and canonical coder/user/auto session management.

Orchestrates Claude Code skill management — lists skills, improves existing skills, or creates new ones with activation optimization and triggers. Triggers: create skill, new skill, improve skill, fix skill activation, skill doesn't trigger, list skills, skill management, optimize skill.

Chain patterns for CC 2.1.71 pipelines — MCP detection, handoff files, checkpoint-resume, worktree agents, CronCreate monitoring. Use when building multi-phase pipeline skills. Loaded via skills: field by pipeline skills (fix-issue, implement, brainstorm, verify). Not user-invocable.

Use PROACTIVELY when reviewing CLAUDE.md configurations, onboarding new projects, or before committing memory file changes. Validates against official Anthropic documentation, community best practices, and LLM context optimization research. Detects security violations, anti-patterns, and compliance issues. Not for runtime behavior testing or imported file validation.

Use when storing decision traces, querying past precedents, or implementing learning loops. Load in COMPLETE state or when needing to learn from history. Covers semantic search with Voyage AI embeddings, ChromaDB for cross-platform vector storage, and pattern extraction from history.

Address tracker and analysis. Use this skill whenever the user provides an on-chain address or asks to track or query an address. Trigger phrases include: track this address, who owns this address, fund flow, check address. MCP tools: info_onchain_get_address_info, info_onchain_get_address_transactions, info_onchain_trace_fund_flow.

Local document and PDF parsing with spatial text and bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; OCR on scans; layout-preserved JSON for RAG; batch-ingesting paper folders; or page screenshots for multimodal agents — even when the user does not name liteparse. Prefer over MarkItDown when you need bboxes, fast local parsing, or PNG page renders; prefer over the pdf skill for merge/split/forms.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.

Complete agent memory + performance system. Extracts structured facts, builds knowledge graphs, generates briefings, and enforces execution discipline via pre-game routines, tool policies, result compression, and after-action reviews. Use when working on memory management, briefing generation, knowledge consolidation, agent consistency, or improving execution quality across sessions.

Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or non-security ownership questions. Originally from OpenAI's curated skills catalog.

Interactive Claude Code permissions management - scans plugin recommendations, presents categorized setup, and writes to settings.json

Comprehensive portfolio analysis using Alpaca MCP Server integration to fetch holdings and positions, then analyze asset allocation, risk metrics, individual stock positions, diversification, and generate rebalancing recommendations. Use when user requests portfolio review, position analysis, risk assessment, performance evaluation, or rebalancing suggestions for their brokerage account.

Power BI semantic models - DAX measures, star schemas, relationships, RLS, and performance tuning via MCP. Use when creating data models, writing DAX, or configuring table relationships in Power BI.

Manages Claude Code skill definitions - create, validate, version, and list skills following the Agent Skills open standard.

Four-layer test framework for Claude Code plugin skills. Use when validating plugin structure, testing trigger accuracy of skill descriptions, running multi-turn session scenarios, or comparing skill value (with vs without). Also use when creating new trigger evals, session scenarios, or debugging why a skill fires for the wrong prompts. NOT for writing unit tests, running pytest, or testing application code — this is for testing AI plugin skills only.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

Agent-to-Agent (A2A) executor implementation patterns for task handling, execution management, and agent coordination. Use when building A2A executors, implementing task handlers, creating agent execution flows, or when user mentions A2A protocol, task execution, agent executors, task handlers, or agent coordination.

Agent-to-Agent (A2A) protocol implementation patterns for Google ADK - exposing agents via A2A, consuming external agents, multi-agent communication, and protocol configuration. Use when building multi-agent systems, implementing A2A protocol, exposing agents as services, consuming remote agents, configuring agent cards, or when user mentions A2A, agent-to-agent, multi-agent collaboration, remote agents, or agent orchestration.

Perform finance web searches and local context searches. Use when the user needs general finance info from the web (Jina/DDG/Baidu) or needs to retrieve finance information from a local document store (RAG).

Perform finance web searches and local context searches. Use when the user needs general finance info from the web (Jina/DDG/Baidu) or needs to retrieve finance information from a local document store (RAG).

Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.

Universal environment variable loader for AI agent environments. Loads secrets and config from Claude.ai, Claude Code, OpenAI Codex, Jules, and standard .env files.

Creates production-ready MCP servers using FastMCP v2. Use when building MCP servers, optimizing tool descriptions for context efficiency, implementing progressive disclosure for multiple capabilities, or packaging servers for distribution.

Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

Generates a Jupyter notebook that transforms datasets between ML schemas for model training or evaluation. Use when the user says "transform", "convert", "reformat", "change the format", or when a dataset's schema needs to change to match the target format — always use this skill for format changes rather than writing inline transformation code. Supports OpenAI chat, SageMaker SFT/DPO/RLVR, HuggingFace preference, Bedrock Nova, VERL, and custom JSONL formats from local files or S3.

Aggregate and rank signals from multiple edge-finding skills (edge-candidate-agent, theme-detector, sector-analyst, institutional-flow-tracker) into a prioritized conviction dashboard with weighted scoring, deduplication, and contradiction detection.

Programmatic canvas toolkit for creating, editing, and refining Excalidraw diagrams via MCP tools with real-time canvas sync. Use when an agent needs to (1) draw or lay out diagrams on a live canvas, (2) iteratively refine diagrams using describe_scene and get_canvas_screenshot to see its own work, (3) export/import .excalidraw files or PNG/SVG images, (4) save/restore canvas snapshots, (5) convert Mermaid to Excalidraw, or (6) perform element-level CRUD, alignment, distribution, grouping, duplication, and locking. Requires a running canvas server (EXPRESS_SERVER_URL, default http://localhost:3000).

Receive and verify Hugging Face webhooks. Use when setting up Hugging Face webhook handlers, debugging X-Webhook-Secret verification, or handling events on models, datasets, and Spaces — repo updates, new commits and tags (repo.content), config changes (repo.config), discussions, Pull Requests, and discussion comments.

Enables GitHub repository operations (read/write/commit/PR) for Claude.ai chat environments. Use when users request GitHub commits, repository updates, DEVLOG persistence, or cross-session state management via GitHub branches. Not needed in Claude Code (has native git access).

MCP server building, advanced patterns, and security hardening. Use when building MCP servers, implementing tool handlers, adding authentication, creating interactive UIs, hardening MCP security, or debugging MCP integrations.

Receive and verify OpenAI webhooks. Use when setting up OpenAI webhook handlers for fine-tuning jobs, batch completions, or async events like fine_tuning.job.completed, batch.completed, or realtime.call.incoming.

Manages Codex, Claude Code, and Cursor skill marketplaces — publishes plugin-owned skills, updates plugin groups, removes entries, packages skills for distribution, regenerates plugin manifests, and validates catalog integrity. Use when publishing a skill to the marketplace, bumping a version, removing a skill from the catalog, packaging a skill as a .skill file, regenerating marketplace files, moving a skill between plugins, or fixing marketplace validation errors.

ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs. Covers model deployment, feature stores, drift monitoring, RAG systems, and cost optimization.

Post tweets to X (Twitter) from Claude Code. Supports single tweets, threads (auto-split or manual), and replies. Use when user says "/x:tweet", "post a tweet", "tweet this", "post a thread", "reply to this tweet". NOT for reading tweets, analytics, scheduling, or DMs.

Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.

Expert at creating and modifying Claude Code agents. Auto-invokes when creating/updating agents, modifying agent frontmatter (model, tools, description), designing agent architecture, or writing to */agents/*.md files.

Review any project's .claude/ setup against Claude Code best practices and produce an actionable improvement report. Use when: "/claude-reviewer", "review my claude config", "audit .claude setup", "check my CLAUDE.md", "how good is my claude config", "rate this project's claude setup". NOT for: reviewing individual skill quality (use /skill-reviewer), code review, PR review.

Python research assistant with Context7 MCP. Use for Python library research, evaluating packages, enforcing strict Python coding standards, or fetching up-to-date library docs via Context7.

Manage expert agent activation and panel composition for project and global scopes. Provides list, configure, and panel operations for expert-based workflows like code review and plan grading.

ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs.

DAG workflow runner that encodes control flow in code, not prose. Use when a procedure has 3+ steps with branching, retries, or validation that must be enforced — gates as `when=`, edge contracts as `validate=`, predicate loops as `retry_until=`. The runner owns the graph; the LLM provides leaves. Also covers parallel execution, checkpoint resume, detached side-effects.

LLMs, prompt engineering, RAG systems, LangChain, and AI application development

Cross-subsystem digest for the ~/.learnwy/ data root. Aggregates vocab progress (english-learner), wiki health (llm-wiki), prompt-optimizer trigger trends, knowledge-consolidation nudges, and log size into one report. Use when the user asks for: 'what is my learnwy status', 'show me my vocab/wiki/optimizer stats', 'weekly digest', 'how am I doing on my personal data', or runs `cli.cjs status`. Also installs a once-per-ISO-week SessionStart hook that prepends a compact summary to the first session of each week.

Notion workspace management via MCP - create databases, pages, comments, and knowledge bases. Use when building Notion documentation, organizing project wikis, or managing Notion content.

Receive and verify OpenClaw Gateway webhooks. Use when handling webhook events from OpenClaw AI agents, processing agent hook calls, wake events, or building integrations that respond to OpenClaw agent activity.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

Comprehensive AI agent evaluation framework with three grader types (code-based: deterministic/fast; model-based: nuanced/LLM rubric; human: gold standard) and pass@k / pass^k scoring. Evaluates agent transcripts, tool-call sequences, and multi-turn conversations — not just single outputs. Supports capability evals (~70% pass target) and regression evals (~99% pass target). Workflows: RunEval, CompareModels, ComparePrompts, CreateJudge, CreateUseCase, RunScenario, CreateScenario, ViewResults. Integrates with THE ALGORITHM ISC rows for automated verification. Domain patterns pre-configured for coding, conversational, research, and computer-use agent types in Data/DomainPatterns.yaml. Tools: AlgorithmBridge.ts (ISC integration), FailureToTask.ts (failures → tasks), SuiteManager.ts (create/graduate/saturation-check), ScenarioRunner.ts (multi-turn simulated-user), TranscriptCapture.ts, PAIAgentAdapter.ts (wraps Inference.ts), ScenarioToTranscript.ts. Code-based graders: string_match, regex_match, binary_tests, static_analysis, state_check, tool_calls. Model-based graders: llm_rubric, natural_language_assert, pairwise_comparison. USE WHEN eval, evaluate, benchmark, regression test, run eval, compare models, compare prompts, create judge, test agent, quality check, pass@k, grader, agent transcript, scenario simulation, capability test, before/after comparison, suite saturation, failure to task, graduate suite. NOT FOR general research or web investigation (use Research) or scientific method framing (use Science).

Execute any of 240+ specialized prompt patterns natively (no CLI required for most) across categories: Extraction (30+), Summarization (20+), Analysis (35+), Creation (50+), Improvement (10+), Security (15), Rating (8). Common patterns: extract_wisdom, summarize, create_5_sentence_summary, create_threat_model, create_stride_threat_model, analyze_claims, improve_writing, review_code, extract_main_idea, analyze_malware, create_sigma_rules, create_mermaid_visualization, youtube_summary, judge_output, rate_ai_response. Native execution reads Patterns/{name}/system.md and applies directly. Fabric CLI used only for YouTube transcript extraction (-y URL) and fallback URL fetching (-u URL). Patterns auto-synced from upstream Fabric repo via UpdatePatterns workflow. Workflows: ExecutePattern, UpdatePatterns. USE WHEN fabric, fabric pattern, run fabric, sync fabric, update patterns, use extract_wisdom, threat model, summarize, analyze claims, improve writing, review code, create prd, rate content, create diagram, mermaid diagram, STRIDE, sigma rules, analyze malware. NOT FOR comprehensive multi-agent investigation (use Research), content-adaptive dynamic extraction (use ExtractWisdom), or security threat intelligence aggregation (use AnnualReports).

Meta-prompting standard library — the PAI system for generating, optimizing, and composing prompts programmatically. Owns three pillars: Standards (Anthropic Claude 4.x best practices, context engineering principles, 1,500+ paper synthesis, Fabric pattern system, markdown-first / no-XML-tags); Templates (Handlebars-based — Briefing.hbs, Structure.hbs, Gate.hbs, DynamicAgent.hbs, and eval-specific templates Judge.hbs, Rubric.hbs, TestCase.hbs, Comparison.hbs, Report.hbs used by Agents and Evals skills); and Tools (RenderTemplate.ts for CLI/TypeScript rendering with data-content separation). Philosophy: prompts that write prompts — structure is code, content is data. Delivered 65% token reduction across PAI (53K → 18K tokens) via template extraction. Output is always a prompt to be used elsewhere, not final content. Reference files: Standards.md (complete prompt engineering guide), Tools/RenderTemplate.ts (rendering implementation). NOT FOR generating final content or answers — this skill produces prompts only (for content, use the appropriate domain skill). USE WHEN meta-prompting, template generation, prompt optimization, prompt engineering, write a prompt for, generate an agent prompt, create system prompt, programmatic prompt, Handlebars template, optimize this prompt, prompt hygiene, context engineering, eval prompt, judge prompt, agent briefing.

Runtime security validation including secret scanning, PII detection, prompt injection defense, audit logging, and output validation for AI agents. Use when validating user input, scanning for secrets, detecting PII, preventing data exfiltration, or implementing security guardrails.

Guidance for developing Claude Code sub-agents with proper frontmatter, system prompts, triggering conditions, and autonomous task handling patterns.

Retrieve time-windowed RSS evidence from SQLite and let the agent produce final summaries using RAG over selected records and fields. Use when generating daily, weekly, monthly, or custom-range AI tech digests directly in agent responses instead of fixed template reports.

Beads (bd) Dolt-backed issue tracker for agent task memory. Covers CLI ops, molecules, Dolt sync, Linear/Jira/GitLab. Use when tracking tasks and dependencies with the Beads CLI, syncing issues via Dolt, or integrating with Linear/Jira/GitLab. Keywords: bd, beads, Dolt, issue tracker.

Document chunking implementations and benchmarking tools for RAG pipelines including fixed-size, semantic, recursive, and sentence-based strategies. Use when implementing document processing, optimizing chunk sizes, comparing chunking approaches, benchmarking retrieval performance, or when user mentions chunking, text splitting, document segmentation, RAG optimization, or chunk evaluation.

PostHog LLM analytics for all supported providers

Create agent skills following the Agent Skills open standard. Use when building new skills for Claude Code, Cursor, Gemini CLI, or other agents. Use for skill structure, SKILL.md authoring, frontmatter configuration, progressive disclosure, reference files, validation, and distribution.

Optimize Ollama configuration for the current machine's hardware. Use when asked to speed up Ollama, tune local LLM performance, or pick models that fit available GPU/RAM.

Multi-agent workflow orchestration with state tracking, checkpointing, and cross-pollinated pipelines. Use when coordinating parallel agent pipelines, managing sync barriers, or tracking complex workflow execution state across sessions.

Serena MCP for project memory and code navigation. Use when managing Serena memories, navigating symbols, performing intelligent refactoring, or maintaining context/continuity across AI agent sessions.

Personalized 8-phase onboarding wizard that scans the codebase, detects tech stack, recommends skills and MCP servers, and generates an improvement plan with readiness score. Includes safety checks, project-scoped configuration, and release channel detection. Use when setting up OrchestKit for a new project or rescanning after major changes.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

A2A agent card JSON templates with schema validation and examples for different agent types. Use when creating agent cards, implementing A2A protocol discovery, setting up agent metadata, configuring authentication schemes, defining agent capabilities, or when user mentions agent card, agent discovery, A2A metadata, service endpoint configuration, or agent authentication setup.

ADBPG Knowledge Base Management: Create knowledge bases, upload documents, search, Q&A. Triggers: "knowledge base", "document library", "document upload", "knowledge search", "RAG", "Q&A", "embedding", "ADBPG", "AnalyticDB PostgreSQL"

Universal documentation sync for skills, agents, and markdown files. Pulls latest docs from official sources and updates files in place. Modes: status, init <path>, global, file, folder. Triggers: sync docs, auto-sync, update documentation, refresh skill docs, sync agent docs, documentation sync, pull latest docs.

Expert at creating and modifying Claude Code slash commands. Auto-invokes when creating/updating commands, modifying command frontmatter (model, allowed-tools, argument-hint), designing workflows, or writing to */commands/*.md files.

Expert at creating Claude Code event hooks for automation and policy enforcement. Auto-invokes when creating/updating hooks, modifying hooks.json, designing event-driven automation, or writing hook configurations.

Refresh actuals in an existing Excel budget workbook from Carta MCP. TRIGGER: refresh/sync/add actuals, interleave Budget/Actual/Variance, tag-view by department/cost center. NOT: pacing, new budgets, fetch-budget, scenarios, P&L, balance sheet.

Excel (.xlsx) manipulation via MCP server. Use for creating workbooks, formatting cells, writing formulas, building charts, pivot tables, data analysis, or any task involving Excel spreadsheets.

Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP. Use when the user asks about service traces, slow HTTP/database spans, error spans, trace IDs, or span attributes — not AI observability traces or product logs. Uses posthog:query-apm-spans, posthog:apm-trace-get, posthog:apm-services-list, posthog:apm-attributes-list, and posthog:apm-attribute-values-list.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate exte...

Plan and build MCP servers with agent-friendly tools, schemas, error handling, and evaluation. Use when creating or refactoring MCP integrations.

User-triggered multi-agent code review. Spawns 3-5 parallel specialist sub-agents that read actual source files, runs mechanical citation verification, and synthesizes a single review artifact. Use for PR-level changes, multi-commit ranges, or security-sensitive work where single-turn review is insufficient.

Guide for creating and managing Claude Code plugin marketplaces. Use when setting up a marketplace, validating marketplace.json, or distributing plugins.

Test-driven behavioral verification for AI agents. Catches silent degradation when agent loads memory but doesn't apply learned behaviors. Use when building agent with persistent memory, testing after updates, or ensuring behavioral consistency across sessions.

This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.

Packages repositories into AI-friendly bundles with Repomix and can reconstruct files from existing Repomix outputs. Use when packaging codebases for LLM analysis, creating repository snapshots, reversing bundles, or preparing security audits. Triggers include "repomix", "package codebase", "repomix-unmix", "extract-bundle", "AI-friendly", or "LLM context".

Code review across 31 dimensions (correctness, security, performance, architecture, accessibility, supply-chain, and more — see `argument-hint`). `/review <dimension>` runs one rubric inline; `/review sweep <aggregate>` fans out one reviewer sub-agent per dimension in parallel and synthesizes a unified verdict. Auto-trigger on review or audit requests scoped to a PR, worktree, diff, file, or repo.