Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
DCE-safe require() patterns and edge runtime constraints. Use when writing conditional require() calls, guarding Node-only imports (node:stream etc.), or editing define-env-plugin.ts / app-render / st
in the skill textediting define-env-plugin.ts / app-render / stream-utils for edge builds. Covers if/else branching for webpack DCE, TypeScript definite assignment, the NEXT_RUNTIME vs real feature flag distinction
OfficialSkillMIT★ 143k in collectionNo key
Intelligent Git Flow branch creator that analyzes git status/diff and creates appropriate branches following the nvie Git Flow branching model.
OfficialSkillMIT★ 40k in collectionNo key
How to add or modify Next.js experimental feature flags end-to-end. Use when editing config-shared.ts, config-schema.ts, define-env-plugin.ts, next-server.ts, export/worker.ts, or module.compiled.js.
in the skill texttime injection, runtime env plumbing, and the decision between runtime env-var branching vs separate bundle variants. # Feature Flags Use this skill when adding or changing
OfficialSkillMIT★ 143k in collectionNo key
Develop AI-powered applications using Genkit in Python. Use when the user asks about Genkit, AI agents, flows, or tools in Python, or when encountering Genkit errors, import issues, or API problems.
in the skill textmain()) ``` ## Agents (Beta) Multi-turn chats with history, typed state, human approval, branching, and background work. Start here: Agents . ```python chat = agent.chat() res = await chat.send('Hello
OfficialSkillApache-2.0★ 21k in collectionNo key
Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, valida
in the skill textpreview **agent** API for persistent, multi-turn conversations (sessions, snapshots, interrupts, branching, background execution). It is a **beta** API: server APIs come from `genkit/beta` and the
OfficialSkillApache-2.0★ 21k in collectionNo key
For complex tasks, break operations into clear, sequential steps. It is often helpful to give Claude an overview of the process towards the beginning of SKILL.md:
in the skill textrun fill_form.py) 5. Verify output (run verify_output.py) ``` ## Conditional Workflows For tasks with branching logic, guide Claude through decision points: ```markdown 1. Determine the modification type: **Creating
OfficialInstructionsApache-2.0★ 19k in collectionNo key
Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows, or integrate LLMs into Dart/Flutter applications.
in the skill texthas an **agent** API for persistent, multi-turn conversations (sessions, snapshots, interrupts, branching, background execution, custom state, artifacts, and multi-agent delegation). The agent/session/snapshot APIs are
OfficialSkillApache-2.0★ 21k in collectionNo key
Squad branching model: dev-first workflow with insiders preview channel
OfficialSkillMIT★ 5.4k in collectionNo key
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring
in the skill textfor every auto-research campaign. Start or resume a session record before branching, then checkpoint after forming the plan, before and after meaningful edits or long
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Set up, repair, or migrate to Cloudflare Turnstile bot verification in an existing frontend and backend, including server-side Siteverify.
in the skill textagent. Run the wizard below by invoking the scripts under `scripts/` and branching on their JSON output. The scripts hold the deterministic logic (API calls, retry/error
OfficialSkillApache-2.0★ 3.1k in collectionNo key
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
in the skill textcontrol over agent orchestration | Quick prototyping → LangChain agents | | Building complex workflows with branching/loops | Simple stateless workflows → LangChain direct | | Require human-in-the-loop, persistence | Batteries-included
OfficialSkillMIT★ 1.3k in collectionNo key
Perform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Covers security, performance, testing, and
in the skill textuser paths Verify tests cover actual requirements and edge cases. Avoid excessive branching or looping in test code. ### Long-Term Impact Flag for senior engineer review
OfficialSkillApache-2.0★ 1.1k in collectionNo key
INVOKE THIS SKILL when routing a LangGraph agent with a decision model (TypeSafe Jev, SemIf) instead of an LLM, or when auditing an existing agent for LLM calls that only produce a routing decision. C
in the skill textreplaces the common pattern of prompting an LLM, parsing its text, and branching on the result. - **`Noul(instructions=...)`** — binary question, returns a probability of yes - **`Choice
OfficialSkillMIT★ 1.3k in collectionNo key
Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to
in the skill textplan. ## Principles - **One question at a time.** Each question should resolve a branching decision in the plan. Avoid generic or out-of-domain questions. - **Surface constraints
OfficialSkillApache-2.0★ 918 in collectionNo key
A framework-agnostic, git-native standard for defining AI agents
in the skill textOpenAI, LangChain, CrewAI, and AutoGen. **gitagent** fixes that. - **Git-native** — Version control, branching, diffing, and collaboration built in - **Framework-agnostic** — Export to any framework with adapters
SkillMIT★ 3.0kNo key
A visual workspace for game narratives and NPCs. Build worlds, arrange scenes and characters, edit branching dialogue, review AI drafts, and rehearse stories. Collaborate with your own AI through bili
SkillMIT★ 61No key
A Pokémon-style adventure built with Codex, featuring AI-generated maps, NPCs, branching saves, and multiplayer. The adventure never ends.
SkillMIT★ 183No key
Use codec-owned storage-type hooks for control-plane type behavior
in the skill textAdding enum-specific fields to `SqlSchemaIR` - Framework-level enum abstractions or codecId branching in shared SQL layers - Treating missing type parameters as a successful match when
OfficialRuleApache-2.0★ 415 in collectionNo key
Avoid tautological tests that only restate fixture input
in the skill textshape passed by the test itself. ## Rule - Prefer assertions that validate transformation, branching, integration behavior, error handling, or side effects. - Do not add tests that only
OfficialRuleApache-2.0★ 415 in collectionNo key
Never branch on target - use adapters instead
in the skill texttarget-agnostic code. This covers two forms of the same mistake: **branching** on a `target` value, and embedding **target-named constants, helpers, or data** in framework/core
OfficialRuleApache-2.0★ 415 in collectionNo key
Run Claude Code dynamic workflows on a local Codex (GPT) backend, plus an interactive run viewer
in the skill textGPT-5 agents instead of Claude subagents. The runtime holds the loop, branching, and intermediate results, so your context only sees the final answer — and you
SkillMIT★ 326No key
Wire the Prisma Next runtime — `db.ts` setup using `postgres<Contract>(...)` from `@prisma-next/postgres/runtime`, `sqlite<Contract>(...)` from `@prisma-next/sqlite/runtime`, or `mongo<Contract>(...)`
in the skill textfrom `@prisma-next/middleware-telemetry`; lints and budgets), `DATABASE_URL` config, per-environment branching, switching between Postgres, SQLite, and Mongo façades. Use for db.ts, postgres(), sqlite(), mongo
OfficialSkillApache-2.0★ 415 in collectionNo key
Public 12ui design skills, Codex plugin, and API contracts
in the skill textfinishes. Your agent never draws in the conversation. Drawing, editing, branching and Build this need no 12ui account: branching plans and draws the new screens with
SkillMIT★ 2Few starsNo key
Agent Skill for Git workflow best practices - branching, commits, PR workflows | Claude Code compatible
SkillLink only★ 53
Isolated databases for every AI agent branch. Build, test, and migrate in parallel. Production stays untouched.
in the skill textcleanup, with persistent design/demo environments skipped - Dry-run provisioning and a committed branching architecture doc as the project's source of truth The result: agents can
SkillMIT★ 15No key
A curated collection of custom AgentSkills and token-saving MCP servers for extending the capabilities of AI coding assistants like Claude Code.
in the skill texttoo. ## Available Skills | Skill | Command | Description | | ------- | ------- | ----------- | | git-workflow | `/git-workflow` | Guided Git workflow: branching, commits, PRs, and conflict resolution | | code-review | `/code-review` | Thorough code review covering correctness
SkillMIT★ 10No key
Agent skills for agentic coding tools. Extremely opinionated. Updated (almost) daily.
in the skill textimplementation-ready design document. | skill | | |-------|-| | `sparring` | Socratic inquiry in rounds, with branching exploration | | `sota` | current expert recommendation grounded in brief web research | | `design` | divergent exploration with
SkillCC0-1.0★ 11No key
Repo-local skill switchboard for agent skill libraries
in the skill textpublishing runs only from `v*.*.*` tags or a manual workflow dispatch. ### Git Branching Model - `main` is the protected release branch. - `dev` is the protected integration branch
SkillApache-2.0★ 2Few starsNo key
Branching conditional workflow execution tree builder
SkillLink only★ 9
An executable, no-code SDLC graph that carries a feature from spec to PR — with explicit nodes, guards, bounded retry loops, and durable state. No framework. No SDK. No runtime to install. Your coding
in the skill textThe basic workflow - Where it stops for you - What each gate catches - Branching strategy changes the topology - Watching a run live - When something goes wrong - What
SkillMIT★ 16No key
🎮 34 production-grade Claude Code skills for indie game development — studio agents, workflow skills, engine specialists, genre packs, and CI validation. From concept to launch.
in the skill texttuning | | 5 | **Narrative Director** | Crafts story architecture, dialogue systems, lore bibles, and branching narratives | | 6 | **Art Director** | Establishes visual style, asset pipelines, UI art direction, and
SkillMIT★ 45No key
58 agent skills for software engineering: architecture, code review, debugging, CI/CD, data, and security.
in the skill textwithout changing behaviour. | 2026-09-06 | ### Repo hygiene | Skill ID | Title | Description | Reviewed | |:---------|:------|:------------|:---------| | `branching-strategy` | Branching Strategy | Design the branching and release model: trunk-based
SkillMITFew starsNo key
Who stands behind it
Who stands behind it