Delegate coding to OpenAI Codex CLI (features, PRs).

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.

Use only when pr-review-resolver asks Codex to fix one selected PR review issue with bounded owned files. This resolver-managed worker edits code and reports validation results, but never updates PR review comments or .pr-review-cache state.

Recover Codex and Claude sessions from tmux cockpit panes, CX SAVE snapshots, codex-cockpit history, and recent Codex logs without overwriting the useful restore source first.

Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.

Collaborative multi-agent fix workflow using codex, gemini-cli, and an independent subagent. Use when the user asks to "collab fix", "multi-agent fix", or wants several AI tools to jointly analyze and fix a bug or task with cross-review.

Migrate and sync vector database collections across environments

APC Mini MK2 color palette reference with velocity values and custom RGB via SysEx. Use when user asks about "color", "velocity value", "RGB", "palette", "brightness", "LED color", or needs to set specific colors on the APC Mini MK2.

Run shell commands bare — no decorative echo headers ("=== X ==="), no echo-then-cmd chains, no trailing "echo done". Use the Bash tool's description field for any narration. Triggers any time you're about to issue a Bash command.

Create a git commit with clear, conventional commit messages. You MUST read this when the user wants to commit staged changes, write a commit message, or finalize code changes with proper conventional commit format since it describes how to follow the user's specific requirements.

Git commit workflow. Use this skill whenever the user says "commit", "save changes", "check in", or otherwise wants to commit code. Always use this skill instead of running git commands directly.

Write commit messages and split large changes into small, ordered, atomic commits. Use when the user asks to commit changes, write a commit message, split a change into commits, or asks "how should I commit this". Enforces the `type(component): message` title format and the `git commit -s -m` signed-off command.

Create git commit messages based on current staged changes. Has support for git emoji messages.

Use when creating git commits, staging changes, or writing commit messages. Provides Angular conventional commit format guidelines, atomic commit principles, and strategies for splitting multi-concern changes into logical commits.

[DEPRECATED] Persistence logic has been merged into comp-scout-scrape. This skill remains for reference only.

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.

Create a competitive analysis brief for one or more competitors or a feature area

Analyzes tasks and assigns complexity scores (1-10) with a hard ceiling of 3 for atomic tasks, flagging anything above for further decomposition

Use when writing or reviewing Jetpack Compose UI tests, screenshot tests, previews, semantics assertions, fake image loading, keyboard input, focus assertions, interaction state (hover/pressed/focused), or tests for plain state-driven UI composables.

Extract patterns from git history and session files, recommend artifacts (skill/rule/hook/agent) based on frequency thresholds

Create computed columns in Glide - Math, If-Then-Else, Relations, Rollups, Lookups, Templates. Use when adding calculations, formulas, lookups, or linking tables with relations.

Understand SpacetimeDB architecture and core concepts. Use when learning SpacetimeDB or making architectural decisions.

Guides users through configuring Content Security Policy (CSP) in Tauri v2 applications to prevent XSS attacks and enhance security by restricting resource loading.

Guides developers through configuring HTTP headers security in Tauri v2 applications, covering security headers, custom headers, and CORS configuration for secure cross-origin resource handling.

Create detailed content briefs. Use when: keyword targets, outline, structure, voice guidelines, SEO requirements.

Content brief template and creation methodology for SEO-optimized content. Use when preparing briefs for writers or planning new content pieces.

Create content for artists and record labels — short-form videos, images, captions, lipsync clips, and more. Use when the user asks to create content, make a video, generate an image, produce a TikTok or Reel, create a promotional clip, add captions, or create visual content for an artist. Also use when iterating on content quality — regenerating images, trying different audio, adjusting text, or upscaling for higher quality.

Obsidian content curation and quality specialist. Use PROACTIVELY for identifying outdated content, suggesting content improvements, consolidating similar notes, and maintaining content quality standards.

Identify content gaps between your site and competitors. Use when the user says "content gaps", "what am I missing", "competitor content", "content opportunities", "topics I should cover", "content gap analysis", or asks about finding topics and keywords their site doesn't cover but competitors do.

When the user wants to create, optimize, or audit a giveaway, contest, or promotional campaign page. Also use when the user mentions "giveaway," "contest," "sweepstakes," "promo," "Gleam," "Woobox," or "viral campaign." For sitewide page planning, use website-structure.

Analyze current session context and token usage from OpenCode SQLite database

Automatically generates skills from Context7 MCP documentation responses

Find handoff documents and continue work on a previous task with full context. Companion to the `handoff` skill.

>

Generates semantic commit messages following the Conventional Commits specification with proper types, scopes, breaking changes, and footers. Use when users request "write commit message", "conventional commit", "semantic commit", or "format commit".

Use this skill when the user needs to improve conversion rates, reduce funnel drop-off, optimize signup flows, or increase trial-to-paid conversion. Covers funnel analysis, friction reduction, behavioral psychology, social proof, and A/B testing strategies.

Reduces LLM costs and improves response times through caching, model selection, batching, and prompt optimization. Provides cost breakdowns, latency hotspots, and configuration recommendations. Use for "cost reduction", "performance optimization", "latency improvement", or "efficiency".

Measure and optimize the cost/quality curve — which model, prompt, and settings give the best quality per dollar. Covers Pareto analysis, break-even thresholds, and when to spend more vs less. Use this skill when optimizing LLM spend, picking a default model for a feature, or deciding whether a premium model is worth it. Activate when: cost vs quality, model selection, eval cost, Pareto frontier, cheaper model, premium model tradeoff.

Build counter-narrative playbooks. Use when: competitor rebrand, new category claim, aggressive campaign, price change response.

Offer to cover someone else's on-call shift. Lists upcoming shifts on a team or schedule and creates an override placing you on the chosen one after explicit confirmation. Write action - never executes without confirming.

Scrape websites at scale using Scrapy, a Python web crawling and scraping framework. Use when: (1) Crawling multiple pages or entire sites, (2) Extracting structured data from HTML/XML, or (3) Building automated data pipelines from web sources.

Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.

Design and write a `BaseIOSchema` input/output pair for an Atomic Agents agent or tool — docstrings, field descriptions, validators, error variants. Use when the user asks to "create a schema", "design the input/output schema", "define an `IOSchema`", "write a `BaseIOSchema`", "model the agent's output", or runs `/atomic-agents:create-atomic-schema`.

Create a new slash command following best practices. Use when establishing new CLI commands, documenting reusable command patterns, or building automated command templates.

Create a new Claude Code slash command with proper YAML frontmatter structure. Use when the user wants to add a custom slash command to a plugin. Handles command file creation with description, argument hints, allowed tools, and all advanced features.

Create handoff documentation for work-in-progress sessions. Use when handing off work to another agent to supplement history compaction and and progress summarization.

Create a new Claude Code plugin with proper directory structure and manifest. Use when the user wants to create a new plugin from scratch. Sets up plugin.json, directory structure, and optional components.

create a pull request with standardized description template

Create pull requests using GitHub CLI with proper templates and formatting

Create or update pull requests with conventional commits. Use when user says "create a PR for these changes", "submit this for review", "open a pull request", "push these changes and create a PR", "I'm ready to submit this work", or "create PR and link to issue

Create publication-quality visualizations with Python

Creates a new git worktree for parallel development. Use when the user wants to work on something in a separate worktree, start parallel work, or isolate changes.

Scan your project for exposed credentials, API keys, and secrets before running OpenClaw skills. Prevents accidental exfiltration.

Guides n8n credential setup through Computer Use browser tools. Use when a user needs OAuth apps, API keys, client IDs, client secrets, or other credential values from an external service console.

Use when building a val that runs on a schedule — periodic jobs, recurring tasks, polling, cron jobs, monitoring, alerting. Covers the interval handler signature, cron expressions, the UTC timezone constraint, and the `lastRunAt` pattern for detecting new items since the previous run.

Schedule management with staggering, quiet hours, and wake-up override. Validates schedules, prevents collisions, and gates delivery during quiet hours.

Internal helper agent. Invoked by orchestrator agents via Task tool. Internal helper for cross-page accessibility pattern detection, severity scoring, and scorecard generation. Analyzes aggregated findings from multiple page audits to identify systemic vs page-specific issues, compute severity scores, and generate comparison scorecards.

Coordinate a multi-repo refactor by fanning out subagents per repo, gathering changes onto a single feature branch named cook/refactor-<slug>-<short-sha>, and pushing for review. Pairs with the branch-guard PreToolUse hook to make pushes to main physically impossible.

Security pattern for managing cryptographic keys throughout their lifecycle. Use when integrating cryptography requiring key generation, storage, distribution, or usage. Provides guidance on key confidentiality, integrity, configuration protection, and key information handling. Foundation for Cryptography as a service and Self-managed cryptography patterns.

SpacetimeDB C#/.NET client SDK reference. Use when building C# clients that connect to SpacetimeDB (console, desktop, or any .NET app).

When the user wants to run CTV, OTT, or streaming TV ads. Also use when the user mentions "CTV ads," "connected TV," "OTT advertising," "streaming ads," "TV ads," "Hulu ads," "Roku ads," "YouTube TV ads," or "programmatic TV." For paid mix, use paid-ads-strategy.

Creative-writing session lead and entry point. Activate this to get a creative partner that brainstorms, drafts, critiques, revises, and maintains your story's knowledge base. Built for Claude.ai, where there are no subagents: it runs every mode of the work in one conversation. Load alongside the craft skills (writing-principles, prose-writing, scene-construction, prose-critique). Use at the start of any story session.

Transform product requirements into technical architecture blueprints with technology stack decisions, API contracts, and data models. Use when moving from requirements to implementation, evaluating technology stacks, or designing system components.

Set up Cyrus end-to-end — install prerequisites, configure authentication, create integrations (Linear, GitHub, Slack), add repositories, and launch. Run this once to get Cyrus running as a background agent.

Create D3.js charts and interactive data visualizations. Use when building bar charts, line charts, scatter plots, pie charts, force-directed graphs, geographic maps, or any custom data visualization.

Start your day with a prioritized sales briefing. Works standalone when you tell me your meetings and priorities, supercharged when you connect your calendar, CRM, and email. Trigger with "morning briefing", "daily brief", "what's on my plate today", "prep my day", or "start my day".

Use this skill when the user asks to "generate dark mode", "create dark theme", "add dark mode support", "convert to dark mode colors", "generate dark color palette", or wants to automatically generate dark mode variants for their components with intelligent color inversion and accessibility preservation.

Collect coverage using the coverage packge and create an LCOV report

Replace the usage of `expect` and similar functions from `package:matcher` to `package:checks` equivalents.

Guidelines and best practices for refactoring consecutive prints, single-line string concatenations, and complex output blocks into triple-quoted multi-line string literals (''' or """) in Dart.

Optimize Dart code for performance, type safety, and runtime error prevention. Use when profiling hot paths, enforcing sound typing, handling null safety, or debugging type mismatches and runtime failures.

Run Dart tooling workflows for static analysis, dependency conflict resolution, and test migration to package:checks. Use when fixing analyzer errors, resolving pub dependency conflicts, or modernizing test assertions.

Generate and open the harness run dashboard. Reads .harness/*.json state files, builds a self-contained HTML file, and opens it in the browser. Use when the user asks to see the dashboard, check run status, or view experiment history. For live monitoring during a run, suggest /loop 30s /harness:dashboard.

Profile and explore datasets to understand their shape, quality, and patterns before analysis. Use when encountering a new dataset, assessing data quality, discovering column distributions, identifying nulls and outliers, or deciding which dimensions to analyze.

Design data governance policy — stewardship, quality standards, access control, lifecycle, lineage + metadata catalog, change + issue management. Aligns with GDPR / CCPA / sector regulations.

Plan data migration. Source + target analysis, mapping rules, strategy selection (big-bang / phased / parallel / strangler), cutover plan, rollback, validation, downtime management, CDC.

Security pattern for input validation and sanitization. Use when implementing input handling, preventing injection attacks (SQL, XSS, command), ensuring data integrity, or processing data from untrusted sources. Addresses "Entity provides unexpected data" problem.

Create and manage database migrations safely with rollback support. Use when modifying database schema, adding indexes, or managing database changes.

Query performance tuning, EXPLAIN analysis, index strategies, slow query detection, and connection pool management.

Query database safely with parameterized statements

Generate PDF documents from HTML and upload to Unity Catalog volumes. Use for creating test PDFs, demo documents, reports, or evaluation datasets.

Guidance for feature engineering, feature discovery, feature importance analysis, and understanding DataRobot's automated feature engineering capabilities. Use when working with feature engineering, feature discovery, or analyzing feature importance in DataRobot.

Sets up DataRobot for local development including Python SDK, dr-cli, Agent Assist, and all required dependencies. Use when the user has not yet worked with DataRobot on this machine and wants to deploy agents to DataRobot, build an agent from scratch, or connect to DataRobot's APIs from a new project.

Log management - search, archives, metrics, and cost control.

Monitor management - list, search, file-based create, and alerting best practices.

DDD component architecture for Vue/Nuxt projects — folder structure, naming conventions, translation keys, and component organisation. Use when creating components, choosing file paths, naming files, structuring translations, or organising domain folders.

Multi-agent debate with 3-phase workflow. Optional --deep mode for feedback loop.

Use this skill when debugging code with AI assistance. Activate when the user has a bug, error, unexpected behavior, needs to understand why code isn't working, wants to analyze stack traces, or is troubleshooting issues in their application.

Systematic debugging methodologies for hard bugs. Covers rubber ducking, code tracing, hypothesis testing, logging strategies. Use when stuck on bugs that resist quick fixes.

Systematic debugging: stack trace analysis, log-based diagnosis, bisecting regressions, memory leak detection, and profiling.

Generate compelling cases FOR a decision - advocacy grounded in rigorous analysis

Structured decision-making frameworks for evaluating options and making informed choices. Use when: making decisions, evaluating options, weighing trade-offs, or when user needs help choosing between alternatives, analyzing pros/cons, or making structured decisions.

Post-decision analysis - review outcomes against predictions, identify lessons, update patterns