Convert Claude Code commands (.claude/commands/*.md) to standard Agent Skills (skills/*/SKILL.md). Use when migrating slash commands to portable skill format, creating skills from existing commands, or standardizing command definitions across AI runtimes.

Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.

>

terminal-session

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, troubleshooting repository issues, or when initializing a new repository according to our companies specific guidelines.

Make sure to ALWAYS use this skill when working with python code! Help designing, structuring, and maintaining Python projects, including virtualenvs, packaging, SQLite (sql3) usage, documentation of bug fixes, and clear commenting practices.

Rigorous build process with worktree isolation, structured phases, quality gates, layered testing, observability, and self-improvement. Use for any substantial build task. Structurally enforced via stop hook.

Schedule recurring agent tasks using cron expressions. Use when the user asks to run something on a schedule, check something periodically, automate a recurring task, set up a cron job, or wants work to happen while they're away. Trigger words: schedule, recurring, cron, every hour, every day, run daily, periodic, automated.

Expose the organized knowledge base through a readable frontend experience. Use when a user wants to browse the knowledge base visually as a lightweight site instead of reading raw Markdown files directly. Supports building viewers for specific data paths (e.g., individual books) or the entire knowledge base.

Turn a crawler-produced Tapestry artifact into a source-appropriate structured feed. Use when a user wants a rigorous feed entry, normalized text output, or source-specific organization rather than a loose free-form summary.

Implements Syncfusion .NET MAUI Color Picker (SfColorPicker). Use when implementing color picker functionality, color selection UI, palette mode, spectrum mode, or alpha slider configuration in .NET MAUI applications. Covers inline rendering, popup customization, color changed events, localization, and liquid glass effect.

Implements Syncfusion .NET MAUI DockLayout (SfDockLayout) for arranging and docking child elements in defined areas. Use this for creating docking layouts, positioning UI elements at edges (top/bottom/left/right), building dashboard layouts, or arranging multi-region interfaces. Covers dock positioning, edge positioning, and spacing between docked elements.

Implements Syncfusion .NET MAUI Rotator (SfRotator) control for displaying image carousels, slideshows, or rotating content. Use this for image galleries, product showcases, testimonial sliders, banner rotators, or scenarios requiring automatic or manual navigation through visual content.

>

Executes code snippets by saving them to a temporary file and running them via bash commands (e.g., node, python, go run) to test logic or compute results.

Reads, parses, and generates documents in various formats like Markdown, PDF, docx, CSV, or HTML. Uses bash commands to invoke document conversion tools like pandoc or python scripts.

Downloads files, images, or media from URLs using curl, wget, or python scripts. Can handle bulk downloads and save them to a specified directory.

Organizes, categorizes, and renames files in a directory based on user instructions. Uses bash commands to move, copy, or rename files.

Searches for files by name, extension, size, or content using powerful system tools like grep or find.

Fetches top news, recent articles, or RSS feeds from the web using curl, wget or custom scripts to provide the user with the latest information on a given topic.

Create Claude Code skills with best practices, structure, validation, and testing. Use when designing or refining skills, prompts, references, or supporting files.

Wait for a specified duration, then execute a Bash command.

This skill should be used when the user asks about Effect-TS patterns, services, layers, error handling, service composition, or writing/refactoring code that imports from 'effect'. Also covers Effect + Next.js integration with @prb/effect-next.

>

- **Decision:** Ship / no-ship for a new prompt + retrieval policy governing the customer-support reply drafting assistant.

**System**: An AI-powered customer-support reply drafting agent that retrieves relevant Knowledge Base (KB) articles via a retrieval policy, then generates a draft reply to the customer inquiry.

Run an internal dogfooding program: scenario map, routines, triage spec, ship/no-ship gate.

**Account:** [Unspecified enterprise account]

**Scenario:** Prospects agree there's pain but keep stalling, asking for "more time" or "send info."

Design/redesign org structure and operating model: current-state map, target blueprint, transition plan.

- **Company profile:** 300-person enterprise SaaS company

Plan under uncertainty: uncertainty map, hypotheses + experiments, buffers + triggers, cadence.

Define a product problem: problem statement, JTBD, alternatives, evidence, metrics. See also: writing-prds (solution spec).

Build product taste via a Taste Calibration Sprint (benchmarks, critique notes, hypothesis log).

Right-size scope for a fixed timebox: minimum lovable slice, cut list, scope-creep guardrails. See also: managing-timelines (deadline plans).

Plan, run, and synthesize usability tests: test plan, tasks, script, findings, recommendations.

Turn an idea into a demo-ready prototype using AI-assisted vibe coding.

Write a decision-ready PRD for cross-functional alignment. See also: writing-specs-designs (build-ready spec).

Create a build-ready spec + design doc (user flows, prototype brief, acceptance criteria). See also: writing-prds (decision-level PRD).

**Selected:** Spec & Design Doc Pack **with Prototype Brief emphasis**

Increase successful invites (defined as: invitee downloads the app and completes onboarding) by shipping a low-friction, high-conversion invite flow within 4 weeks.

Generate comprehensive trigger tests for agent skills to validate proper activation behavior. Creates test cases for all 4 trigger types.

Certify a skulto build for Homebrew prod release. Runs three passes — unit/lint/cross-compile, clean-slate CLI walkthrough, and security audit — then produces a certification summary.

Execute implementation plans one phase at a time with strict quality enforcement, test verification, and conventional commit generation.

Use when starting significant features, epics, or complex tasks. Creates multi-phase implementation plans with parallelizable phases, poker estimates, TDD-first acceptance criteria, and quality gates. Detects tech stack from CLAUDE.md/AGENTS.md (bypassing internet research if complete) or via codebase scan.

Local verify-commit-push wrapper for Codex. Use only when the user explicitly says `/cp` or clearly asks to finish the current work by running the relevant local checks, staging intended files explicitly, committing on the current branch, and pushing. This workflow may commit directly to `main` or `master` when that is the repo's chosen operating model.

Frontend design mode for strong visual direction, UI polish, redesigns, landing pages, and production-grade interface work, including shadcn-based surfaces. Use when the user says `/fd` or explicitly asks for better design, styling, layout, visual quality, or UX polish.

Explicit extra-research mode. Use only when the user says `/re` or clearly asks for a research-heavy pass before coding. This skill should bias Codex toward more source-checking and justification without replacing its normal orchestration.

Persistent verification mode. Use when the user explicitly says `/test` or clearly wants exhaustive test, QA, and fix loops before signoff, especially when they want you to keep grinding while they are away. Bias Codex toward running the relevant existing test stack, browser or desktop verification, and diagnosis repeatedly until the requested surface is verified or a real blocker remains.

>-