Consult peer LLM for alternative perspectives when you need second opinion, peer review, or fresh take on technical decisions; useful for validating approaches or exploring alternative solutions

Retrieve a snapshot of market sector performance using Octagon MCP. Use when analyzing sector-wide metrics including revenue, EBITDA, net income, market cap, and enterprise value for companies within a specific sector and exchange.

Use when creating new skills, optimizing existing skills, or auditing skill quality. Guides skill development following Claude Code official best practices.

Search the Agent Skills Catalog to find skills by keyword, vendor, or category.

Claude Code skills (Agent Skills) configuration reference. Use when creating skills, understanding skill activation, SKILL.md format, user-invoked vs model-invoked skills, or skill best practices.

Delegate work to builtin or custom subagents with single-agent, chain, parallel, async, forked-context, and intercom-coordinated workflows. Use for parallel codebase discovery, debug-and-fix, refinement, and multi-step tasks where a single parent agent stays in control while specialist subagents contribute locate, analyze, pattern-find, research, debug, or simplify passes.

This skill MUST be invoked when the user says "sync CLAUDE.md", "update agent instructions", "propagate constitution changes", "CLAUDE.md sync", or "constitution alignment". SHOULD also invoke when user mentions "agent instructions" updates.

ERC-8004 on-chain agent validation management — request and respond to validations, and query validation status, summaries, and paginated lists by agent or validator.

Technical reference for implementing subagents. Use when asked about frontmatter fields, system prompt structure, or subagent file format. Provides essential specs with references for details.

Use when auditing an agent codebase against the 12-Factor Agents methodology, reviewing LLM-powered system architecture, or assessing agentic app compliance. Triggers on "analyze agent architecture", "12-factor audit", "how compliant is this agent", or "evaluate this LLM app". Also applies when comparing frameworks or planning agent improvements. Not for quick checklists — this performs deep per-factor codebase analysis with file-level evidence.

# agent.run

This skill should be used when the user asks to "create an agent team", "run a multi-agent team", "coordinate multiple Claude sessions", "use agent teams", or wants to parallelize work across multiple Claude Code instances.

Add an `Assisted-by: <agent-name>/<model-id>` git trailer to commits made during an AI-assisted coding session. Trigger on any `git commit` activity visible in the session — either commits you make yourself, or commits the user makes outside your tool calls that surface in the conversation — even without an explicit request. Also trigger when the user explicitly asks to tag existing commits in a branch (e.g. "add assisted-by to commits in this branch").

Retrieve real-time commodity price quotes using Octagon MCP. Use when checking current commodity prices, analyzing day ranges, comparing to moving averages, and tracking precious metals, energy, and agricultural commodity prices.

Navigate privacy regulations (GDPR, CCPA), review DPAs, and handle data subject requests. Use when reviewing data processing agreements, responding to data subject access or deletion requests, assessing cross-border data transfer requirements, or evaluating privacy compliance.

Create a new memory rule following Claude Code best practices for project instructions, coding standards, and workflow guidelines. This skill should be used when users want to create CLAUDE.md rules, .claude/rules/ files, or memory instructions for Claude Code.

Create, update, validate, and canonicalize Claude Code skills. USE WHEN user wants to create a new skill OR modify an existing skill OR validate skill structure OR fix skill format OR migrate legacy skills.

Guide for creating effective skills following best practices. Use when creating or updating skills that extend agent capabilities.

This skill should be used when the user asks for a "full security audit", "exhaustive audit", "comprehensive security review", or invokes /appsec:full-audit. Launches every framework, every tool, and every red team agent, producing a dated report file.

Retrieve industry-specific P/E ratios using Octagon MCP. Use when comparing company valuations to specific industry peers, analyzing sub-sector valuations, and understanding niche market valuations beyond broad sector averages.

Retrieve a daily overview of industry performance using Octagon MCP. Use when analyzing daily price movements, average changes, and performance trends for specific industries within an exchange.

Guides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniques like LoRA and QLoRA.

Génère automatiquement un compte-rendu de réunion en français à partir d'une transcription Teams (.vtt) et optionnellement d'un rapport de présence (.csv). Propose ensuite optionnellement de créer des issues de suivi GitLab/GitHub à partir du compte-rendu. Agnostique par défaut, avec un mode enrichi auto-détecté pour le projet hexagone-monorepo. À utiliser quand l'utilisateur dépose un ou deux chemins de fichiers Teams dans le prompt et demande la génération d'un compte-rendu.

Convert a local AGENT.md into a Claude Code optimized agent. Audits one agent against Claude Code runtime behavior, creates a per-agent DAG rewrite plan with source-backed guardrails, and optionally rewrites the frontmatter and system-prompt body so the agent is thinner, more role-specific, and better aligned with Claude's agent runtime. Use when the user says "convert this agent to Claude", "normalize this AGENT.md", "thin this agent", or "rewrite this persona for Claude Code".

Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.

Delegate work to builtin or custom subagents with single-agent, chain, parallel, async, forked-context, and intercom-coordinated workflows. Use for advisory review, implementation handoffs, and multi-step tasks where a single agent should stay in control while other agents contribute context, planning, or execution.

Create reviewed Codex goal setup packages for long-running /goal work. Use when the user wants to turn an idea, backlog, project mission, or vague objective into durable goal files under a project goals slug folder, with Plannotator review gates for brief, narrative plan with acceptance criteria, verification, blockers, and the final /goal prompt.

Debug and inspect PostHog implementations on any website. Use this skill when a user wants to understand how PostHog is implemented on a page, troubleshoot tracking issues, verify configuration, check what events are being sent, or audit a PostHog setup. Works with Chrome DevTools MCP and Playwright MCP to inspect live websites.

Retrieve consensus price targets for any stock using Octagon MCP. Use when you need the average, median, high, and low analyst price targets to evaluate upside/downside potential and analyst agreement.

Techniques and templates for creating optimal prompts following Anthropic conventions

Iterate on RAG systems with structured evals instead of eyeballing. This skill should be used when the user is tuning a RAG pipeline — changing retrieval prompts, swapping models, adjusting chunking, or debugging poor answers — and wants a cheap, ranked set of experiments with cost tracking and structured feedback on the stack. Also use when the user asks "how do I know if my RAG is working?", "this RAG eval is burning money", or "what should I try next on retrieval?".

Generate an optimized shopping list from the current meal plan, grouped by store, and send it to Telegram and Discord. Triggers on: /shopping list, /shopping send, /shopping optimize [budget], 'send shopping list', 'what do I need to buy', 'shopping for the week', or after meal planning is complete.

SIWA (Sign-In With Agent) authentication for ERC-8004 registered agents.

Guidelines for creating AI agent skills. Use when writing new skills, documenting coding patterns, or reviewing skill files. Triggers when creating or modifying files in the skills/ directory.

Re-inject Synapse A2A initial instructions after context has been cleared. Use this skill when the agent has lost its identity, A2A communication protocol, or configuration after /clear or context reset, when synapse send/reply commands stop working, or when the agent no longer recognizes its SYNAPSE_AGENT_ID. Triggered by /synapse-reinst command.

Creates educational Teams channel posts for internal knowledge sharing about Claude Code features, tools, and best practices. Applies when writing posts, announcements, or documentation to teach colleagues effective Claude Code usage, announce new features, share productivity tips, or document lessons learned. Provides templates, writing guidelines, and structured approaches emphasizing concrete examples, underlying principles, and connections to best practices like context engineering. Activates for content involving Teams posts, channel announcements, feature documentation, or tip sharing.

Weaviate vector database for semantic search, hybrid queries, and AI-native applications. Use for embeddings storage, similarity search, RAG pipelines, and multi-modal retrieval.

Git worktree management for isolated parallel prompt execution. Use when creating isolated environments for prompt comparison or managing worktree lifecycle. Provides creation, cleanup, and orphan detection scripts.

Implement retrieval-augmented generation systems. Use when building knowledge-intensive applications, document search, Q&A systems, or need to ground LLM responses in external data. Covers embedding strategy, vector stores, retrieval pipelines, and evaluation.

Use when the user is NEW to Claude Code agent teams or asks high-level questions about what they are, when to use them, or how they compare to subagents. Triggers: "how do agent teams work", "what are agent teams", "agent teams vs subagents", "should I use a team for this", "are agent teams enabled". Do NOT trigger for choosing a specific team blueprint (route to `team-blueprints`) or managing an active team (route to `team-coordination`). This skill is the onboarding / discovery entry point only.

Orchestrate the full spec-driven development lifecycle through four phases (Specify, Plan, Implement, Validate). Supports three rigor levels and lightweight mode for small changes. Use when user says "spec driven development", "SDD workflow", "specify then implement", "spec first development", "write spec then build", or "develop with specification". Do NOT use for writing specs only (use spec-writer) or for validating existing code against specs (use spec-validator agent directly).

Use this skill to review an existing command-line tool against the agent-CLI contract and safety model — before extending it, before trusting it in an autonomous loop, or as a quality gate. Triggers on "audit this CLI", "review this tool for agents", "is this CLI safe for agents", "check the agent CLI against best practices", "contract review", "safety review of the CLI". Produces a findings report graded against the invariants and the guarded-mutation model. Read-only.

Retrieve market capitalization data for multiple companies at once using Octagon MCP. Use when comparing valuations across peers, screening by market cap, or analyzing a portfolio's composition by company size.

Optimizes Claude Code memory in 4 interactive steps - removes duplicates, migrates to rules/CLAUDE.md, compresses, validates with cleanup

Build integration tests for MCP tool collections. Reads .discover.json and creates test setup, builders, helpers, and test files per collection. Use after running '/build-tools'.

Detects MSBuild projects with conflicting OutputPath or IntermediateOutputPath. Only activate in MSBuild/.NET build context. USE FOR: builds failing with 'Cannot create a file when that file already exists', 'The process cannot access the file because it is being used by another process', intermittent build failures that succeed on retry, missing outputs in multi-project builds, multi-targeting builds where project.assets.json conflicts. Diagnoses when multiple projects or TFMs write to the same bin/obj directories due to shared OutputPath, missing AppendTargetFrameworkToOutputPath, or extra global properties like PublishReadyToRun creating redundant evaluations. DO NOT USE FOR: file access errors unrelated to MSBuild (OS-level locking), single-project single-TFM builds, non-MSBuild build systems. INVOKES: binlog MCP server tools (overview, projects, evaluations, properties, double_writes); falls back to dotnet msbuild binlog replay + grep when the MCP is unavailable.

# Claude Code Expert Skill

Claude Code CLI configuration guide for Codex. Use when users ask about: claude code config, ~/.claude/settings.json, claude plugins, claude agents, claude skills, claude hooks, claude mcp servers, or integrating tools with Claude Code.

Analyze code changes for security vulnerabilities using LLM reasoning and threat model patterns. Use for PR reviews, pre-commit checks, or branch comparisons.

Analyze codebase and create/update .conventions/ directory with gold standards, anti-patterns, and checks. Use this skill when the user asks to 'set up conventions', 'create coding standards', 'extract patterns from the codebase', 'document how code should be written', 'create gold standards', 'establish code style', or wants to ensure consistent code quality across the project. Also use when starting work on a new codebase that lacks a .conventions/ directory — conventions are the foundation for all agent-teams code quality.

Create and improve Claude Code skills using a structured checkpointflow workflow with test-driven iteration. Use this skill whenever the user wants to create a skill, make a skill, build a skill, improve an existing skill, test a skill with evals, benchmark skill quality, optimize a skill description, or turn a conversation into a reusable skill. Also triggers on "skill for X", "automate this as a skill", "package this as a skill", and similar phrases.

Deep exploration and synthesis workflow using Agent Teams with dynamic planning and hub-and-spoke coordination. Use when asked for "deep analysis", "deep understanding", "analyze codebase", "explore and analyze", or "investigate codebase".

Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis

System safety and control-plane skill that prevents agent deadlocks and freezes. Provides non-LLM control commands to inspect task state, flush message queues, cancel long-running work, and recover safely without restarting the container. Use when implementing or operating long-running tasks, sub-agents, benchmarks, background monitors (e.g., Moltbook, PNR checks), or when the system becomes unresponsive and needs immediate recovery controls.

Retrieve ESG benchmark comparison metrics by sector using Octagon MCP. Use when comparing ESG performance across industries, analyzing sector-level sustainability benchmarks, identifying ESG leaders and laggards by industry, or referencing frameworks like MSCI, S&P Global, CDP, and CSRD.

Helps users discover agent skills from the open skills ecosystem. Use when users ask "how do I do X", "find a skill for X", "is there a skill that can...", or want to extend agent capabilities. This skill searches for and evaluates candidate skills, then presents findings to the user for them to review and decide whether to install.

Cold, methodical diagnostician for when you're stuck in agent-assisted app development. Call the fixer when: (1) You're in a loop with a coding agent and things keep getting worse, (2) Your project has accumulated so many agent-generated changes you've lost the thread, (3) Builds are broken and you can't figure out why, (4) You've tried multiple approaches and none are working, (5) You need someone to cut through confusion and give you a clear path forward. Triggers on: "I'm stuck", "nothing is working", "help me fix this", "I'm going in circles", "the agent keeps breaking things", "I've lost track of what's happening", "can you take a look at this mess", or any expression of frustration with agent-assisted development. The fixer does not commiserate — it diagnoses, intervenes, and unblocks.

Create, route, and inspect GitHub issues from Claude Code or Codex with gh CLI-backed defaults for DiversioTeam/monolith, repo-local execution repos, and project-board hydration.

Fetch the current top Hacker News stories and return agent-friendly structured results. Use this whenever the user explicitly asks about Hacker News or HN, and also when they ask for today's developer, startup, YC, or tech-community hot stories where Hacker News is a strong default source.

Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when evaluating contract risk, assessing deal exposure, classifying issues by severity, or determining whether a matter needs senior counsel or outside legal review.

Claude Code MCP (Model Context Protocol) server configuration reference. Use when adding MCP servers, configuring external tools, or integrating third-party services.

Optimizes Claude Code memory files in 4 interactive steps: removes duplicates, migrates rules to CLAUDE.md/rules files, compresses remaining entries, validates with cleanup. Typical reduction: 30-50% on token count.

Guide for Phoenix web applications. Use when building Phoenix apps, implementing LiveView, designing contexts, setting up channels, or integrating Tidewave MCP dev tools.

Run a comprehensive multi-agent PR review on code changes. Use when the user asks to review a PR, review code changes, review a branch, run a code review, or check code before merging. Supports git diff comparisons, specific file review, and directory-level review. Orchestrates 7 specialized agents (architecture, code quality, bugs, security, tests, performance, acceptance) in parallel and produces an aggregated report with verdict.

Retrieve analysts' price target summary for any stock using Octagon MCP. Use when evaluating analyst sentiment, upside/downside potential, consensus expectations, and tracking target trends over time.

Read and search GitHub repository documentation via gitmcp.io MCP service. **WHEN TO USE:** - User provides a GitHub URL - User mentions a specific repo in owner/repo format - User asks "what does this repo do?", "read the docs for X repo", or similar - User wants to search code or docs within a repo

Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.

Extract and summarize risk factors from SEC filings using Octagon MCP. Use when analyzing Item 1A risk disclosures, categorizing business risks, identifying new or material risks, and comparing risk profiles across companies or time periods.

Retrieve sector P/E ratios using Octagon MCP. Use when comparing company valuations to sector benchmarks, analyzing sector valuations across exchanges, and understanding market-wide valuation trends.

Claude Code settings configuration reference. Use when configuring Claude Code behavior, understanding settings hierarchy, or customizing project/user settings.

Manages and edits the terminal/shell environment: zsh config, aliases, tmux, sesh session manager, starship prompt, Ghostty terminal, yabai window manager, and GNU Stow dotfile management. Make sure to use this skill whenever the user mentions "zsh config", "shell alias", "dotfiles", "tmux config", "starship prompt", "ghostty", "sesh", "yabai", "add to my dotfiles", "update my shell", stow a package, or anything about configuring their terminal or shell environment — even if they just say "how do I add this to my config".

Reviews and validates agent skills against best practices. Triggers on "review this skill", "check my skill", "validate skill", "is this skill well-written", or when creating/editing skills.

Use this skill to propose changes via the Spec PR process. It uses the Gemini CLI to generate high-quality draft specifications and to analyze PR feedback, accelerating the spec-driven development workflow. Triggers include "create spec" or "propose change".

Retrieve the latest stock grades and ratings from top analysts and financial institutions using Octagon MCP. Use when tracking analyst upgrades, downgrades, rating changes, and institutional sentiment over time.

Create a single well-formed GitLab issue at any time — bugs found in production, features requested by stakeholders, technical debt noticed during development, chores that need doing. Follows the same issue standards as plan-sprint, always. Works in Claude Cowork and Claude Code.

Build and run a Twitter/X agent with a distinct personality and automated workflows

Extract a validated learning from the current session, store it in the central agent learnings file, and sync the resulting Learnings section into the agent definitions used by the supported CLIs. User-only maintenance workflow for durable agent guidance.

Create a new CMS collection in Webflow with specified fields and relationships. Use when setting up blog posts, products, team members, portfolios, or other content types with custom fields.

Use when setting up or improving agent instructions in AGENTS.md, CLAUDE.md or other coding agents instructions files.

Write social media posts for X (Twitter) and LinkedIn that avoid AI tells, pass platform algorithms, and drive engagement. Use when drafting posts, threads, or content for X or LinkedIn.

Decision guide for choosing the right specialized agent for each task type

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

Orchestrate multiple Claude agents working in parallel on a shared codebase with task locking, conflict avoidance, and autonomous work loops. Use when user says "run parallel agents", "orchestrate agents", "multi-agent workflow", "coordinate agents on shared codebase", "parallelize this work", or "run multiple agents simultaneously". Key capabilities include task decomposition, lock-file coordination, git worktree isolation, and branch-per-agent strategies. Do NOT use for single-agent task execution (use task-runner agent instead) or for learning about testing patterns (use test-driven-autonomous-dev instead).

Analyze an existing CLAUDE.md against all 7 Claude Code source leak findings and produce a detailed gap report showing which limitations are mitigated, partially addressed, or completely unaddressed. Use when the user says "fixclaude analyze", "analyze claude md", "check claude md coverage", "audit claude directives", or "what's missing from my claude md".

Browser automation for authenticated web apps using Chrome DevTools MCP. Use when navigating PowerSchool, filling forms, downloading reports, or automating any browser task requiring login. Triggers on: browser control, navigate website, PowerSchool, fill form, download report, automate browser.

Generate templated responses for common legal inquiries and identify when situations require individualized attention. Use when responding to routine legal questions — data subject requests, vendor inquiries, NDA requests, discovery holds — or when managing response templates.

Apply Olshansky's personal style to docs, code, blog posts, or presentations using template-driven rules. Invoke manually via /cmd-olshanskify — pick a content type, point at the target, and the agent rewrites or proposes edits that match the canonical style guide in templates/.

Retrieve market capitalization data for a single company using Octagon MCP. Use when you need the current market value, valuation context, or size classification for any publicly traded stock.

Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.

Review contracts against your organization's negotiation playbook, flagging deviations and generating redline suggestions. Use when reviewing vendor contracts, customer agreements, or any commercial agreement where you need clause-by-clause analysis against standard positions.

Patterns and best practices for Lakebase Provisioned (Databricks managed PostgreSQL) for OLTP workloads. Use when creating Lakebase instances, connecting applications or Databricks Apps to PostgreSQL, implementing reverse ETL via synced tables, storing agent or chat memory, or configuring OAuth authentication for Lakebase.

Creative exploration during quiet hours. Turns idle heartbeat time into freeform thinking — hypotheticals, future scenarios, reflections, unexpected connections. Use when you want your agent to do something meaningful during low-activity periods instead of just returning HEARTBEAT_OK. Outputs written to files for human review later (like remembering dreams in the morning).

Retrieve ESG ratings and scores using Octagon MCP. Use when analyzing Environmental, Social, and Governance ratings, MSCI ESG ratings, Sustainalytics risk ratings, industry ESG rankings, and sustainability metrics for any public company.

Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning

Create agents for financial analysis, investment research, and portfolio management. Covers financial data processing, risk analysis, and recommendation generation. Use when building investment analysis tools, robo-advisors, portfolio trackers, or financial intelligence systems.

Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin