RohiRIK/skills

آخر نشاط مصدر مسجل: ١٧ أكتوبر ٢٠٢٦ في ١٩:٢٥

آخر تحديث لفهرس SkillsMP: ٢ نوفمبر ٢٠٢٦ في ١٨:٠٢

skills مجمعة: ٤١

نجوم GitHub: ١
تفرعات GitHub: ١

التثبيت بمساعدة مساعد ذكي

انسخ هذا الطلب إلى المساعد الذكي الذي تستخدمه.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/RohiRIK/skills.

ملف README للمستودع

مصدر ملف README للمستودع: README.md

قراءة الملف الأصلي

عرض ملف README كاملًا

![Skills](assets/cover.png) # Skills [![Skills](https://img.shields.io/badge/skills-41-blue?style=flat-square)](https://github.com/RohiRIK/skills) [![License](https://img.shields.io/badge/license-MIT-green?style=flat-square)](LICENSE) > _Powered by caffeine and life's questionable coffee-cup choices._ ☕️ My everyday [Agent Skills](https://docs.claude.com/en/docs/agents-and-tools/agent-skills) — a personal library for Claude Code, opencode, and other AI coding tools. Each folder under [`skills/`](skills) is a self-contained skill package with its own `SKILL.md` and any supporting workflows, references, or scripts. ## Skills in this repo | Skill | What it does | |---|---| | [`AdaptiveExplainers/`](skills/AdaptiveExplainers) | Choose and verify text, diagrams, interactive HTML, or video; generated HTML defaults to `~/Downloads`. | | [`Agy/`](skills/Agy) | Delegate a coding, refactor, PR-review, or image task to the Antigravity CLI (`agy`) as an autonomous worker, then monitor and report. | | [`Art/`](skills/Art) | Generate images, diagrams, and visual output. Use for any visual artifact. | | [`BackendDesign/`](skills/BackendDesign) | Reference for API design, database schema, and server architecture. | | [`Build/`](skills/Build) | Implement plan tasks one at a time with compile and commit gates. | | [`CodingStandards/`](skills/CodingStandards) | Language coding standards — TS, Python, Bash, PowerShell, Swift, Rust. | | [`CodebaseOnboarding/`](skills/CodebaseOnboarding) | Analyze an unfamiliar repo → architecture map, entry points, conventions, starter CLAUDE.md. | | [`ContextBudget/`](skills/ContextBudget) | Audit Claude Code context-window consumption and produce prioritized token-savings recommendations. | | [`CreateMcp/`](skills/CreateMcp) | Build a Model Context Protocol (MCP) server with the official SDK — tools, resources, prompts, transport, security. Scaffold, connect, debug. | | [`CreatePlugin/`](skills/CreatePlugin) | Package a project as one shared AI-agent plugin with thin Hermes, Claude, OpenClaw, Pi, OpenCode, and MCP adapters. | | [`CreateCLI/`](skills/CreateCLI) | Shared base for TypeScript CLI generation (3 tiers: parseArgs / Commander / oclif, Bun-only, gated by Verify); routes to the Agent or Human contract. | | [`CreateCLI-Agent/`](skills/CreateCLI-Agent) | Generate a production-ready TypeScript CLI for autonomous agents: JSON contract, non-interactive, semantic exits. | | [`CreateCLI-Human/`](skills/CreateCLI-Human) | Generate a production-ready TypeScript CLI for human operators: TTY UX, prose help, optional JSON. | | [`CreateHook/`](skills/CreateHook) | Generate lifecycle hooks for AI agent runtimes — Claude Code, OpenCode, OpenClaw, Hermes Agent. | | [`CreateSkill/`](skills/CreateSkill) | Build and maintain skills in canonical structure. | | [`DataReportBuilder/`](skills/DataReportBuilder) | Turn a raw Excel/CSV dataset into a two-layer stakeholder report — plain-language Summary + untouched Raw Data. bun + ExcelJS engine. | | [`DockerPatterns/`](skills/DockerPatterns) | Reference for Docker and Docker Compose local-dev patterns. | | [`Email/`](skills/Email) | Write, reply to, rewrite, and localize emails in English and Hebrew: brief-first workflows, 23 native bilingual templates, tone and culture rules, an AI-tell and calque lint, RTL-safe HTML rendering. Drafts only, never sends. | | [`FrontendDesign/`](skills/FrontendDesign) | Reference for React and Next.js component design patterns. | | [`FrontendAesthetics/`](skills/FrontendAesthetics) | Anti-slop pipeline — DesignBrief before code, SlopAudit gate after, Redesign protocol; craft library of font pairings, OKLCH palettes, banned tells. | | [`GitWorkflow/`](skills/GitWorkflow) | Reference for git branching, commit conventions, merge vs rebase, and conflict resolution. | | [`GitHubOps/`](skills/GitHubOps) | Manage a GitHub repo via the gh CLI — hygiene, changelog, commit/push, PRs, releases, branch cleanup. | | [`Hygiene/`](skills/Hygiene) | Audit `~/.claude` for git, skill, code, and rules hygiene issues. | | [`Iterate/`](skills/Iterate) | Bounded PLAN→ACT→VERIFY→REFLECT iteration toward a goal, with a state file and hard exit conditions (`/iterate`). | | [`MacPluginPlaybook/`](skills/MacPluginPlaybook) | Phased playbook to build or port a native SwiftUI macOS menu bar app: research, scaffold, test-first logic, screenshot-driven UI, settings + onboarding, audit, PR. Includes lessons from a real build. | | [`ModelUpgrade/`](skills/ModelUpgrade) | Re-tune the library for any model, the one you use or a new release: a dated generations ledger, `tuned-for` stamps, a dated-prompt scanner, and keep / reprompt / replan / retire verdicts per skill. | | [`OpenCode/`](skills/OpenCode) | Delegate a coding/refactor/PR-review task to the OpenCode CLI as an autonomous worker. | | [`Orchestrate/`](skills/Orchestrate) | Decompose a spec into a dependency DAG, run units in parallel via delegation, review each in a separate context. | | [`Pi/`](skills/Pi) | Delegate a coding/refactor/PR-review task to the Pi (pi.dev) CLI as an autonomous worker. | | [`Prompting/`](skills/Prompting) | Vendor-agnostic prompt-engineering standard library for authoring prompts, skills, agents, rules. | | [`Reflect/`](skills/Reflect) | Self-rate the just-finished output on five axes with evidence, then fix small gaps in place. | | [`Research/`](skills/Research) | Research a question at three depths (quick / standard / deep) by delegating to Agy/OpenCode/Pi + web search, then synthesize cited findings. | | [`Robinhood/`](skills/Robinhood) | Reverse-engineer local Pro/feature gates, explain enforcement, and build explicitly authorized, exact-build test copies with scope and integrity checks. | | [`SecurityReview/`](skills/SecurityReview) | Audit code for vulnerabilities and secrets. | | [`SkillForge/`](skills/SkillForge) | Audit the whole skill library for agentic readiness and instrument it with telemetry in bulk. | | [`SocialPost/`](skills/SocialPost) | Write, rewrite, repurpose, and localize posts for LinkedIn, X, Facebook, Instagram, Threads, Bluesky, Mastodon, WhatsApp, Telegram, TikTok, and YouTube in English and Hebrew: native bilingual templates, a dated platform facts table, exact per-platform counters, and a lint for AI tells, bait, fake formatting, and RTL layout. Drafts only, never posts. | | [`Spec/`](skills/Spec) | Explore code + memory, then write acceptance criteria before planning. | | [`SuperwhisperLocalModels/`](skills/SuperwhisperLocalModels) | Superwhisper local operations: inspect, rebuild, and verify exact-build local-model test copies on Apple Silicon, preserving the installed app. | | [`Test/`](skills/Test) | Single TDD entry point for test-first features and bug fixes; runs `FeatureTdd` or `ProveIt`. | | [`Verify/`](skills/Verify) | Six-phase quality gate (build→type→lint→test→secret→diff) ending in a READY / NOT READY verdict (`/verify`). | | [`Workflows/`](skills/Workflows) | Index of composed skill chains — which skills to run, in what order, for a full job. Routes a task to the right chain; full steps in [`workflows/`](workflows). | ## Install ### 🪄 Let your AI do it (recommended) Paste this to any coding AI (Claude Code, Cursor, Copilot, opencode…) and let it drive the wizard: ```text ☕️ Be my Skills install wizard. Pour a coffee, then: 1. Fetch the install guide — curl -fsSL https://raw.githubusercontent.com/RohiRIK/skills/main/INSTALL-AI.md (or: gh api --header "Accept: application/vnd.github.raw+json" repos/RohiRIK/skills/contents/INSTALL-AI.md) 2. Ask me which tool I'm on and which skills I want — don't install all by default. 3. Run ONLY the commands for my picks, then verify. Go. 🚀 ``` ### Quick (Mac / Linux) ```bash git clone https://github.com/RohiRIK/skills.git ~/rohi-skills cd ~/rohi-skills && ./install.sh ``` `install.sh` symlinks every skill into `~/.claude/skills/` (and the opencode path if present), idempotently. ### Manual / other tools See [INSTALL-AI.md](INSTALL-AI.md) — covers Claude Code, opencode, Cursor, VS Code + Copilot, and Windsurf on Mac and Windows. ## Docs - **[showcase.md](showcase.md)** — visual gallery: a hero image per skill. - **[CLAUDE.md](CLAUDE.md)** — auto-loaded by Claude Code; repo layout + conventions. - **[workflows/](workflows)** — composed skill chains, one document per workflow, two families: **build & ship** (ship-fast, spec-to-ship, research to build/report/buy, onboard, build-cli/mcp, ui/api-feature, security/context/hygiene passes) and **maintain the library** (new-skill, canonicalize, fix-trigger, autonomous-loop, batch-build, library-audit, model-upgrade, release). - **[AGENTS.md](AGENTS.md)** — brief for non-Claude-Code AI tools. - **[INSTALL-AI.md](INSTALL-AI.md)** — full install guide for all supported tools. - **[CHANGELOG.md](CHANGELOG.md)** — notable changes to the library. ## For AI agents fetching this repo - **[llms.txt](llms.txt)** — AI-discovery index: project summary, how to consume the repo, every skill grouped by category with one-line descriptions. - **[skills.json](skills.json)** — machine-readable manifest (name, path, category, effort, tier, tuned_for, workflows, description) — parse this instead of opening every `SKILL.md`. Both are generated from each skill's frontmatter — regenerate after adding or editing a skill. ## Adding a skill 1. Create a folder under `skills/` named after the skill. 2. Add a `SKILL.md` with `name`, `description`, `category`, `effort` frontmatter. 3. Add a row to the table above. 4. Run `./gen-manifest.sh` to regenerate `skills.json` + `llms.txt`. Folders here use TitleCase to match the live `~/.claude/skills` layout; the `name:` field inside each `SKILL.md` is what drives activation.

جارٍ تحميل ملف README للمستودع…

Skills في هذا المستودع

التصنيف قيد الانتظار

skill

المهنة

الوصف

آخر تحديث

art

غير مصنف

Generates images, diagrams, and visual output. USE WHEN producing any visual artifact — illustration, diagram, chart, thumbnail, card. NOT FOR in-app chart components (use the dataviz skill).

لغة النص الأصلي: الإنجليزية

2026-10-17

reflect

غير مصنف

Self-rate the just-finished output on five axes with evidence, then fix any gap scored ≤3. USE WHEN a non-trivial task finishes — 3+ files, a multi-step workflow, or 3+ debug attempts.

لغة النص الأصلي: الإنجليزية

2026-10-17

securityreview

غير مصنف

Audits code for vulnerabilities and secrets. USE WHEN reviewing code for security issues.

لغة النص الأصلي: الإنجليزية

2026-10-17

createcli-agent

غير مصنف

Generate a production-ready TypeScript CLI for autonomous agents (JSON contract, non-interactive, semantic exits). USE WHEN create an agent CLI, tool for LLM/automation, or wrap an API for agents. NOT FOR human-first interactive CLIs (use CreateCLI-Human),…

لغة النص الأصلي: الإنجليزية

2026-10-16

createcli-human

غير مصنف

Generate a production-ready TypeScript CLI for human operators (TTY UX, prose help, optional JSON). USE WHEN create a CLI for people, interactive command-line tool, or wrap an API for humans. NOT FOR agent-first CLIs (use CreateCLI-Agent), agent skills (use…

لغة النص الأصلي: الإنجليزية

2026-10-16

createcli

غير مصنف

Generate a production-ready TypeScript CLI; shared base that routes to CreateCLI-Agent or CreateCLI-Human. USE WHEN create a CLI, command-line tool, or wrap an API. NOT FOR agent skills (use CreateSkill) or Python.

لغة النص الأصلي: الإنجليزية

2026-10-16

contextbudget

غير مصنف

Audit Claude Code context-window consumption across agents, skills, MCP servers, and rules, and produce prioritized token-savings recommendations. USE WHEN context feels bloated or you want to cut token usage.

لغة النص الأصلي: الإنجليزية

2026-10-16

createskill

غير مصنف

Create, validate, and improve individual skills. USE WHEN create/validate/improve a skill or a skill isn't triggering. NOT FOR TypeScript CLI generation (use CreateCLI) or whole-library audits (use SkillForge).

لغة النص الأصلي: الإنجليزية

2026-10-16

prompting

غير مصنف

Vendor-agnostic prompt-engineering standard library. USE WHEN authoring or refining a prompt, system message, skill, agent instruction, or rule file.

لغة النص الأصلي: الإنجليزية

2026-10-16

skillforge

غير مصنف

Audit the whole skill library for agentic readiness and instrument it with telemetry in bulk. USE WHEN auditing skills for autonomy, finding agentic gaps, or adding execution logging across skills. NOT FOR creating a single skill (use CreateSkill) or…

لغة النص الأصلي: الإنجليزية

2026-10-16

workflows

غير مصنف

Index of composed skill chains: which skills to run in what order for a full job. USE WHEN combining skills or asked 'what's the workflow for X'.

لغة النص الأصلي: الإنجليزية

2026-10-16

modelupgrade

غير مصنف

Re-tune skills for any model, current or named: judge relevance and fit, then reprompt, replan, or retire. USE WHEN switching models, a model ships, or skills feel dated.

لغة النص الأصلي: الإنجليزية

2026-10-16

adaptiveexplainers

غير مصنف

Choose and verify text, diagrams, interactive HTML, or video when explaining a topic, system, investigation, or decision.

لغة النص الأصلي: الإنجليزية

2026-10-16

createhook

غير مصنف

Generate lifecycle hooks for AI agent runtimes (Claude Code, OpenCode, OpenClaw, Hermes Agent). USE WHEN writing, wiring, or debugging an event hook, plugin hook, or agent automation trigger.

لغة النص الأصلي: الإنجليزية

2026-10-16

createplugin

غير مصنف

Package a project as an AI-agent plugin with Hermes, Claude, OpenClaw, Pi, OpenCode, and MCP adapters. USE WHEN porting workflows across agent hosts. NOT FOR standalone CLIs (use CreateCLI).

لغة النص الأصلي: الإنجليزية

2026-10-16

email

غير مصنف

Use when drafting, replying to, reviewing, or localizing email. Apply owner language policy, native templates, tone rules, and lint. Drafts only; never sends. NOT FOR social posts (use SocialPost).

لغة النص الأصلي: الإنجليزية

2026-10-16

hygiene

غير مصنف

Audit ~/.claude for git, skill, code, and rules hygiene issues. USE WHEN auditing the Claude config, checking harness health, or cleaning up skills/hooks/rules.

لغة النص الأصلي: الإنجليزية

2026-10-16

iterate

غير مصنف

Bounded multi-pass loop: improve mode (one change per pass, Verify + Reflect, inline or wake-driven) or analysis mode (--lenses, read-only). USE WHEN iterate, refine, keep improving, or explore deeper.

لغة النص الأصلي: الإنجليزية

2026-10-16

macpluginplaybook

غير مصنف

Phased playbook to build or port a native SwiftUI macOS menu bar app. USE WHEN starting or porting a macOS menu bar plugin. NOT FOR one view's styling (use MacUX).

لغة النص الأصلي: الإنجليزية

2026-10-16

agy

غير مصنف

Delegate a coding, refactor, PR-review, or image task to the Antigravity CLI (agy) as an autonomous worker. USE WHEN delegating such a task to agy/Antigravity, or running the agy CLI.

لغة النص الأصلي: الإنجليزية

2026-10-15

backenddesign

غير مصنف

Reference for API design, database schema, and server architecture. USE WHEN designing an API, modeling a schema, or structuring a backend service.

لغة النص الأصلي: الإنجليزية

2026-10-15

build

غير مصنف

Implements plan tasks one at a time with compile and commit gates. USE WHEN building from a plan.

لغة النص الأصلي: الإنجليزية

2026-10-15

codebaseonboarding

غير مصنف

Analyze an unfamiliar codebase and produce an onboarding guide — architecture map, entry points, conventions, starter CLAUDE.md. USE WHEN joining a new project or onboarding a repo.

لغة النص الأصلي: الإنجليزية

2026-10-15

codingstandards

غير مصنف

Language coding standards (TS, Python, Bash, PowerShell, Swift, Rust). USE WHEN writing, reviewing, or scaffolding code.

لغة النص الأصلي: الإنجليزية

2026-10-15

createmcp

غير مصنف

Build a Model Context Protocol (MCP) server with the official SDK — tools, resources, prompts, transport, and security. USE WHEN creating, scaffolding, connecting, or debugging an MCP server.

لغة النص الأصلي: الإنجليزية

2026-10-15

datareportbuilder

غير مصنف

Turn a raw Excel/CSV dataset into a two-layer report — plain-language summary plus untouched raw data. USE WHEN someone shares a spreadsheet wanting a report, analysis, summary, or breakdown.

لغة النص الأصلي: الإنجليزية

2026-10-15

dockerpatterns

غير مصنف

Reference for Docker and Docker Compose local dev patterns. USE WHEN writing a Dockerfile or compose file, or containerizing local dev.

لغة النص الأصلي: الإنجليزية

2026-10-15

frontendaesthetics

غير مصنف

Visual direction and anti-slop gate — typography, color, motion. USE WHEN building any page/dashboard/UI, redesigning, design direction, or looks templated/AI-made. NOT FOR component logic or performance (use FrontendDesign).

لغة النص الأصلي: الإنجليزية

2026-10-15

frontenddesign

غير مصنف

Reference for building React/Next.js components, hooks, state, and performance. USE WHEN building components, hooks, state, or optimizing renders. NOT FOR visual styling, typography, or color (use FrontendAesthetics).

لغة النص الأصلي: الإنجليزية

2026-10-15

githubops

غير مصنف

Manage a GitHub repo via the gh CLI — hygiene, changelog, commit/push, PRs, releases, branch cleanup. USE WHEN clean up the repo, update the changelog, commit/push, open a PR, or cut a release. NOT FOR git branching/merge theory (use GitWorkflow).

لغة النص الأصلي: الإنجليزية

2026-10-15

gitworkflow

غير مصنف

Reference for git branching strategies, commit conventions, merge vs rebase, and conflict resolution. USE WHEN choosing a branching model, resolving conflicts, or setting commit conventions. NOT FOR running gh repo operations like push/PR/release (use…

لغة النص الأصلي: الإنجليزية

2026-10-15

opencode

غير مصنف

Delegate a coding, refactor, or PR-review task to the OpenCode CLI as an autonomous worker. USE WHEN delegating such a task to OpenCode, or running the opencode CLI.

لغة النص الأصلي: الإنجليزية

2026-10-15

orchestrate

غير مصنف

Decompose a spec into a dependency DAG, build units in parallel via delegation, review each in a separate context. USE WHEN orchestrating multi-unit or parallel work, or landing a spec.

لغة النص الأصلي: الإنجليزية

2026-10-15

pi

غير مصنف

Delegate a coding, refactor, or PR-review task to the Pi (pi.dev) CLI as an autonomous worker. USE WHEN delegating such a task to Pi, or running the pi CLI.

لغة النص الأصلي: الإنجليزية

2026-10-15

research

غير مصنف

Research a question at three depths (quick / standard / deep multi-agent fan-out), then synthesize cited findings. USE WHEN researching a topic, gathering sources, comparing options, or getting a cross-provider second opinion.

لغة النص الأصلي: الإنجليزية

2026-10-15

socialpost

غير مصنف

Write, rewrite, repurpose, localize, and review social posts in English and Hebrew. USE WHEN drafting or checking a post, tweet, thread, caption, or comment (פוסט). NOT FOR email (use Email).

لغة النص الأصلي: الإنجليزية

2026-10-15

spec

غير مصنف

Explores code and project memory, then writes acceptance criteria. USE WHEN defining what to build before planning.

لغة النص الأصلي: الإنجليزية

2026-10-15

test

غير مصنف

Runs test-first development for features and bug fixes. USE WHEN writing tests first, testing a new feature, or fixing a bug with a failing test.

لغة النص الأصلي: الإنجليزية

2026-10-15

verify

غير مصنف

Run a build/type/lint/test/secret/diff gate ending in a READY / NOT READY verdict. USE WHEN verifying changes, before commit or PR, or as a quality gate.

لغة النص الأصلي: الإنجليزية

2026-10-15

robinhood

غير مصنف

Reverse-engineer local app feature gates and build scoped test copies. USE WHEN investigating Pro locks or local-model restrictions. NOT FOR cloud authorization or supported Superwhisper rebuilds (use SuperwhisperLocalModels).

لغة النص الأصلي: الإنجليزية

2026-10-14

عرض ٤٠ من أصل ٤١ skills مجمعة.