Set up Fastlane for iOS/macOS app automation

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Semantic code search using natural language queries. Use when users ask "where is X implemented", "how does Y work", "find the logic for Z", or need to locate code by concept rather than exact text. Returns file paths with line numbers and code snippets.

Discover available Jira fields for a project and issue type. Use when the user needs to find field names, see what fields are available, or discover custom field values before creating or updating tickets.

Update fields on an existing Jira ticket. Use when the user wants to modify a ticket's summary, description, assignee, priority, labels, or custom fields.

Install all 22 rules to ~/.claude/rules/workbench/. Self-destructs after running.

Automatic history search — checks past sessions before web research, planning, and debugging, siblings deepen coverage

Manage memories - search, view, update, delete, rename projects

You must use this when analyzing claims, evaluating evidence, or Identifying logical fallacies in research.

Plan a date — find real events, restaurants, and activities personalized to your relationship

Real-time serial log monitoring for ESP32 and microcontrollers. Capture device output to a file and monitor logs in real-time. Use when debugging embedded devices, investigating crashes, or monitoring device behavior.

Archive completed milestone and prepare for next version

HuggingFace hf CLI: search/download/upload models, datasets.

improve a CLAUDE.md file using <important if> blocks to improve instruction adherence

improve a CLAUDE.md file using <important if> blocks to improve instruction adherence

Spawn a Claude worker to handle a GitHub issue. Fetches issue details, creates a feature branch, and works autonomously. Use when you want to delegate an issue to a worker.

This skill should be used when the user asks to "take a screenshot", "screenshot my screen", "click on my screen", "control my Mac", "automate my desktop", "type on my computer", "press keys", "move mouse", or discusses local desktop automation and screen capture.

Twitter/X automation with advanced stealth and anti-detection

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

# ralph-start

Patterns for AI agents to improve themselves. Learned from actionbook and accomplish-ai. Auto-install tools, create skills, maintain systems.

Explain the science behind the neurochemical optimization framework

Generates metadata for research documents and specifications including date/time, git commit, branch, and repository info. Use when creating research documents, handoffs, or any documentation that needs timestamp and git metadata.

Verify project configuration before using other skills/agents. Creates .claude/project.json if missing.

Systematically gather, score, and format client testimonials. Use when someone needs social proof, wants to collect feedback, needs to turn happy clients into public advocates, or asks for help requesting or drafting a testimonial.

Show token economics comparing usage with turbo-search vs without. Demonstrates actual savings from search-first approach.

Apply modern Go syntax guidelines based on project's Go version. Use when user ask for modern Go code guidelines.

Use when interacting with Backlog project management service - creating issues, listing pull requests, managing projects, checking notifications, or any Backlog operation via CLI

Virus-Monitoring für Wien (Abwasser + Sentinel)

Use when interacting with Google Sheets via the agentio CLI.

Injects learned coding preferences and patterns from AgentMind into the current conversation. Activates automatically when Claude works on coding tasks, providing learned instincts about user's preferred tools, code style, and workflows.

# Bias Prevention Skill

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode". (gstack)

Configure token budget limits, auto-compact settings, and view current budget status (model-aware — supports Opus 4.7 1M context tier)

Build repo-wide context before any modification. File inventory, module map, dependency manifests, hot-path identification. Read-only.

Surface @context annotations before editing a file. Shows critical constraints, tradeoffs, and risks sorted by priority. Use when about to modify unfamiliar or complex code, or when the user asks what constraints apply to a file.

Configure Cortex settings with presets

# DEI Practices

Generates accurate Mermaid diagrams from codebase analysis. Activated when the user needs architecture maps, dependency graphs, flow charts, or entity-relationship diagrams.

Turn acceptance criteria into a runnable Smithers eval suite (JSONL cases + rubric) and wire it to `smithers eval`. Use when a workflow's quality must be measured and regression-tested — not "looks good" once, but a repeatable check that fails when the model OR the harness regresses.

Generate a curated changelog from the most important commits in the current PR

Safely introduce external Git repositories as reference materials. Responsible for managing the `_reference` directory, ensuring external code is read-only and does not pollute the project's version control.

Git workflow patterns for multi-environment deployments with GitHub. Applied automatically for branch management and release workflows.

Use this skill when the user mentions "gitlab issues", "list issues", "show issues", "my issues", "milestone", "sprint", "create issue", "update issue", "assign issue", or wants to manage GitLab issues.

Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety". (gstack)

After implementation is complete and tests pass, sync confirmed details back to Intent. Captures finalized interfaces, data structures, naming conventions, and architecture decisions. Use after development is done and user confirms the implementation.

Manage Jira issues on self-hosted/enterprise instances using Personal Access Tokens (PAT). Use this skill when working with Jira that uses SSO/SAML authentication where Basic Auth fails.

Verify and validate JSON Web Tokens (JWTs) by checking signatures, expiration, claims, and structure. Use when the user wants to verify, validate, or check a JWT — e.g. "verify this token", "is this JWT valid", "check the signature", "validate this token against my JWKS", "is this token expired". Supports HMAC, RSA, and ECDSA with secrets, PEM keys, or JWKS endpoints.

Techniques for defining the product's objects, relationships, states, and vocabulary independently of any interface — the most load-bearing layer

Search, browse, create, and delete Apple Notes. Use when user asks about notes, wants to find something in notes, create a new note, or delete notes.

Fetch npm package source code for implementation analysis. Use when types/docs aren't enough and you need to understand HOW a library works internally.

Semantic code search. Use alongside grep - grep for exact strings, osgrep for concepts.

Use when the user says "/plan-execute", "plan execute", "implement plan", or "execute plan" and provides a finalized plan file path to carry out. Claude orchestrates, Codex writes code, Claude reviews, and Codex fixes issues until the quality bar is met.

This skill should be used when the user asks for analysis based on past decisions, "what patterns have worked", "should we adopt X given our history", "what aligns with our conventions", or needs recommendations grounded in accumulated project knowledge.

Automatically wraps verbose commands (pytest, ruff, builds) with silent execution for context-efficient output. Use this proactively when running tests, linters, formatters, or build commands to minimize context usage while preserving error information.

Spec-driven feature development workflow. Triggers on build/create/add/implement/develop intent.

Start the Wasp dev server and set up full debugging visibility. This includes running the server (with access to logs), and connecting browser console access so Claude can see client-side errors. Essential for any development or debugging work.

Use Syntax::Keyword::Assert for zero-cost assertions in Perl

Sync Telegram messages to local storage. Use when user asks to sync, pull, fetch, or download Telegram messages.

VoltAgent architectural patterns and conventions. Covers agents vs workflows, project layout, memory, servers, and observability.

VoltAgent architectural patterns and conventions. Covers agents vs workflows, project layout, memory, servers, and observability.

# Volunteer Engagement

Consolidates ideas into strategic themes by deduplicating and grouping. Use this whenever a list of ideas emerges from the conversation that could benefit from organising.

Localize Xcode .xcstrings files. Use when the user asks to "localize", "translate strings", "add translations", or mentions .xcstrings files. Supports scoped translation by file, folder, target, or string pattern.

Use this skill when the user wants to create Angular applications, generate Angular components/services/modules, or automate Angular development workflows. Handles scaffolding complete Angular apps with routing and guards, generating individual Angular artifacts, setting up project structure, and initializing git repositories with Angular best practices.

Synchronize project documentation after track completion. Use when a track reaches completed status and product, tech-stack, or guidelines documents may need updates.

Use when making architectural choices, adding entities, choosing patterns, or resolving non-obvious technical trade-offs in a project that may have a DECISIONS.md file

A simple demonstration skill that greets users and provides helpful information

Query float.db for full context on a file or folder. Use when user mentions a path, asks about folder context, says "what do we know about X?", or BEFORE modifying any unfamiliar code. Proactive use prevents mistakes.

Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module. Use when asked to "freeze", "restrict edits", "only edit this folder", or "lock down edits". (gstack)

Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"

Automates Git commit creation with Conventional Commits. Use when user wants to commit changes. (project)

Set up a Julia development workflow with Revise hot-reloading

Store and export type constraints for Type::Tiny, Moose, Data::Checks, and more

MANDATORY for all sessions. Use when starting ANY conversation, making decisions, learning something, or ending work. This skill MUST be followed - not optional.

# Pivot Analysis Skill

Control the user own Chrome browser via Playwriter extension with Playwright code snippets in a stateful local js sandbox via playwriter cli. Use this over other Playwright MCPs to automate the browser — it connects to the user's existing Chrome instead of launching a new one. Use this for JS-heavy websites (Instagram, Twitter, cookie/login walls, lazy-loaded UIs) instead of webfetch/curl. Run `playwriter skill` command to read the complete up to date skill

Creates publication-quality scientific plots. Use when making plots, figures, or visualizations. Applies tueplots TMLR styling, LaTeX rendering, no titles.

Validate whether a problem is worth solving before building anything. Use when asked to validate a problem, assess problem-solution fit, decide whether to build something, or evaluate if a problem is real. Scores problems on frequency, intensity, willingness to pay, and existing workarounds.

# ralph-iterate

Save the current work session to persistent memory for future context. Summarizes accomplishments, tracks files modified, and stores learnings for cross-session continuity.

End the current session with comprehensive summary of work done. Use when completing significant work or stopping for the day.

Take a list of projects and their related documentation, and organize them into the SRED format for submission.

A template skill that demonstrates the SKILL.md format. Use this as a starting point for creating new skills.

Use when the animation domain is unclear or spans multiple contexts—provides general-purpose Disney animation principle guidance.

Upgrade JavaScript dependencies using npm-check-updates, then run post-upgrade checks to ensure nothing is broken.

Conducts multi-turn iterative deep research on specific topics within a codebase with zero tolerance for shallow analysis. Use when the user wants an in-depth investigation, needs to understand how something works across multiple files, or asks for comprehensive analysis of a specific system or pattern.

Use when implementing reduced motion alternatives, vestibular-safe animations, WCAG compliance, or designing for users with motion sensitivity.

Operate the btca CLI for local resources and source-first answers. Use when setting up btca in a project, connecting a provider, adding or managing resources, and asking questions via btca commands. Invoke this skill when the user says "use btca" or needs to do more detailed research on a specific library or framework.

Clean up old tasks from the queue

Smart commit creation with conventional commits. Use when user says "commit" or requests committing changes. Handles staged file detection, suggests splits for multi-concern changes, and applies proper commit format without emoji prefixes.

Help define company values and culture for a minimalist business. Use when someone is setting up their company culture, preparing to hire, or wanting to codify what their company stands for.

Use before EVERY git commit - no exceptions. Enforces pre-commit quality checks, atomic commits, and conventional commit format to prevent hook failures and maintain clean history

Use when working on Unity game development - provides expert validation, asset generation, and performance profiling

Instructions on how to author git commits

Deep brainstorming and idea exploration