A project-management guide for coordinating work from project setup through planning and execution. It includes role definitions, plan checking, and guidance for choosing skills in different situations.
Use for plan reviews and checkpoint reviews during implementation. Pass -Tier to select model preference: high-risk uses Opus 4.6 first, medium uses Sonnet 4.6 first. Supports relaxed cadence after 2 consecutive clean reviews.
Execute a PRD autonomously using Amp's native features. Converts PRD to JSON, creates branch, implements stories, commits, and tracks progress. Triggers on: execute this prd, run amp-ralph on, implement this prd, start autonomous execution.
Turn docs/PRD.md into docs/PLAN.md — an ordered, checkbox build plan with architecture, risk gates, and a test list. Use after /spec, before any code. The plan survives session compaction; conversation context does not.
A skill defining how to write a PRD, or product requirements document. A PRD describes what a product or feature should do so developers can review and build it.
Bootstrap a new repo into Katala OS agent-context style — AGENTS.md inheriting the global baseline, cross-OS .gitattributes, shared pre-commit hook via core.hooksPath, optional hash-locked CONSTITUTION + manifest.lock.json + verify.sh, NEEDSREVIEW.md. Use when the operator asks to "start a new repo", "scaffold an…
Guides users through rules-first feature implementation from idea to production code. Validates specs, tasks, and implementation against project rules at every step. Use when building features, implementing specs, creating implementation plans, breaking down specs into tasks, or when user says "help me build"…
Bootstrap a NEW project from scratch using Ivan's preferred stack and conventions, then write production-ready first feature code. Triggered when Ivan describes what he wants to build ("napravi mi novi projekat za X", "treba mi nova app", "novi monorepo", "scaffold a Next.js app", "new project for ...", "start a new…
Founder-minded senior product engineer and SaaS architect skill. Use when building, planning, architecting, validating, designing, testing, securing, deploying, or monetizing modern SaaS products, micro-SaaS, web apps, AI agents, Web3/Base applications, agent commerce, or Telegram bots/Mini Apps. Always active when…
Repository harness for agentic software development. Use when the user wants a repo to follow Harness Engineering or harness-first coding practices, asks to bootstrap or maintain AGENTS.md, architecture docs, execution plans, verification loops, repo-local automation, or requests harness-first setup for future…
Use GovernSpec to work with local-first AI task contracts. Trigger when a repository contains govern.yaml, .govern.yaml, kind GovernSpec, or kind GovernPack; when Codex needs to validate or inspect a task contract; compile contracts to AGENTS.md, prompts, OpenAI structured outputs, MCP plans, or generic skill bundles…
Use when the user wants to turn repeatable office work into a workflow, script, or automation scenario and you need a proper spec before implementation.
A guided game-design workshop that turns a game idea into an initial design plan. It asks structured questions, then creates a game design document, a prototype checklist, and a critical analysis.
High-seniority project manager agent. Plans work, decomposes requests into high-quality tasks with clear acceptance criteria, selects the next unblocked task for other agents, and validates completion vs requirements. Only Project-Manager defines/edits task entries; other agents must not create tasks.
Use when a Codex repository relies on OpenSpec proposals and the work is moving from approved change to implementation in an isolated git worktree. Covers bootstrapping repositories with owf init, inspecting lifecycle state, starting implementation worktrees, applying migration rules, and cleaning up after merge. Do…
Pick the app profile (A=Python / B=HTML+JS) via a plain-language decision tree and set the spec flags. Trigger: starting a new app in sdd.schema: reasons mode, or when the profile is undecided.
Turn a repository into a compact, evidence-backed ontological index: a durable map of system purpose, containers, components, responsibilities, interfaces, data, and important code paths. Use the result to compress repository context and retrieve the source locations that explain how a part of the system works.
Use when preparing XMUM graduate application materials, official document requests, application timelines, language planning, recommendation logistics, and privacy-safe checklists.
A guide for documenting and testing an existing software feature or page by studying how its code already works. It creates requirement, design, and test documents that describe the current behavior rather than an imagined future version.
Interview one clear question before planning/building ideas, features, codebase maps, specs, UI flows, prototypes, or final plans.
★not rated 2 1mo agoA31 tokens
archived
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: