Ipollowork Maintainable Code logo

Ipollowork Maintainable Code

CommunityPopular
Devin-AXIS
ipollowork-maintainable-code

Mandatory iPolloWork code-change gate for modern, minimal, performant, reuse-first implementation and clean repository ownership. Use whenever AI creates, edits, deletes, or refactors application code, server code, packages, scripts, tests, dependencies, schemas, routes, UI, or generated-file workflows. Reuse existing code before creating files, keep one source of truth, prevent parallel implementations and junk directories, justify every new file or dependency, and audit the current change before completion.

Overview

PublisherDevin-AXIS
RepositoryiPolloWork
Skill nameipollowork-maintainable-code
Stars
6.9K
Forks
1.1K
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Devin-AXIS on GitHub. Read the source before you install it.

Installation

Install the Ipollowork Maintainable Code AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Devin-AXIS/iPolloWork/tree/main/.codex/skills/ipollowork-maintainable-code
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Devin-AXIS/iPolloWork.git /tmp/iPolloWork
mkdir -p .claude/skills
cp -r /tmp/iPolloWork/.codex/skills/ipollowork-maintainable-code .claude/skills/ipollowork-maintainable-code
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ipollowork Maintainable Code in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ipollowork Maintainable Code on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ipollowork Maintainable Code is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

iPolloWork Maintainable Code

Treat this as the repository's single code-quality Skill. Implement changes with the smallest coherent diff, modern platform patterns, bounded runtime cost, and one clear owner. Search and reuse before creating anything.

Non-Negotiable Outcomes

  • Modern: use the current repository stack and supported platform APIs; do not add legacy wrappers or compatibility layers without a real supported consumer.
  • Minimal: solve the requested job with the fewest concepts, files, dependencies, states, and routes that remain clear.
  • Performant: keep network, database, filesystem, bundle, render, and memory work bounded; optimize measured or structurally obvious hot paths.
  • Reusable: extend compatible components, hooks, services, schemas, types, and utilities before creating parallel versions.
  • Owned: keep one source of truth and place behavior in the narrowest existing owner.
  • Clean: do not create convenience directories, one-off design notes, duplicate implementations, generated source artifacts, or abandoned replacement files.

Required Workflow

  1. Find the repository root. Read AGENTS.md, the owning package manifest, the real entrypoint, and nearby implementations.
  2. Read references/repository-boundaries.md before adding a file, directory, dependency, API, table, or cross-package import.
  3. Define a change budget before editing: intended behavior, owning module, expected files touched, and whether any new file, directory, dependency, route, table, or persistent state is truly required. Default every category to zero.
  4. Search before creating anything:
    • Search component names, visible labels, route names, event names, type names, and distinctive behavior with rg.
    • Search apps/app/src/components/ui, apps/app/src/components, the target domain, apps/server/src, packages/types, and packages/ui as relevant.
    • Inspect exports and call sites, not just filenames.
  5. State the reuse decision: reuse unchanged, extend compatibly, extract for real multiple consumers, or create as the last choice. For each new file or dependency, record why no existing owner can absorb the change.
  6. Implement locally. Remove the replaced path in the same change; do not leave old, new, v2, fallback, or dead compatibility copies behind.
  7. Add focused tests at the owning layer. Do not duplicate server business logic, contracts, state, or validation in the desktop app.
  8. Run the narrow package checks, inspect the complete diff, then run:
powershell
node .codex/skills/ipollowork-maintainable-code/scripts/audit-changes.mjs
  1. Resolve every error. Fix warnings or give a concrete ownership/performance reason for keeping the exception.

Creation Gate

  • Add a file only when it has a distinct owner and responsibility that would make an existing file less coherent. A long file alone is not a reason to split it.
  • Add a directory only for a real subsystem or package with multiple cohesive files and a stable owner. Never create a directory to hold one small feature, one handoff, one report, or one Markdown note.
  • Do not add a new top-level directory without explicit user approval and a repository-level architectural reason.
  • Do not create new, old, v2, copy, backup, temp, tmp, misc, notes, drafts, handoff, or tdd-summary paths to avoid integrating with the current owner.
  • Do not create a design, plan, QA, summary, or TODO Markdown file for each small feature. Update an existing durable document only when future maintainers need information that code, tests, types, or comments cannot express.
  • Add a dependency only when the platform, current dependency graph, and local utilities cannot meet the requirement cleanly. Account for bundle/runtime cost, maintenance, license, and existing transitive capability.
  • Do not create a generic abstraction for one caller. Extract only after two real consumers need meaningful shared behavior or centralization prevents contract/security drift.

Reuse Decision

SituationAction
Existing API/component/helper meets the needImport and reuse it
Existing implementation differs only by presentation or configurationAdd typed props/options without changing existing defaults
Two real call sites need the same non-trivial behaviorExtract to the nearest shared owner
Similar-looking code has different domain rules or is unlikely to be reusedKeep it local; do not force an abstraction
No compatible implementation exists after searchingCreate one in the narrowest correct owner

Do not copy a component and rename it, create *V2, *New, *Copy, or duplicate a helper to avoid understanding its API. Do not add a generic abstraction for a single trivial use.

Modernity And Simplicity

  • Use typed boundaries, functional React, explicit async/error states, semantic controls, and current repository primitives.
  • Avoid any, broad type assertions, duplicated derived state, prop-to-state mirroring, hidden global state, and fallback branches that types or control flow make impossible.
  • Prefer composition and typed options over copied components or mode-heavy forks. Preserve existing defaults when extending shared code.
  • Delete obsolete code, exports, dependencies, flags, tests, and documentation when their supported path is removed.
  • Keep compatibility only for a named active format, client, or migration window. Document the removal condition beside the boundary.

Performance Gate

  • Keep lists and APIs paginated and bounded. Select only needed fields and avoid N+1 queries, request loops, and repeated filesystem scans.
  • Keep React subscriptions narrow. Derive values instead of synchronizing copies, avoid effects for pure computation, and lazy-load genuinely heavy optional surfaces.
  • Do not add caching or memoization without a clear owner, invalidation rule, and demonstrated reuse or cost.
  • Do not move server-owned data or heavy processing into the browser. Keep network and filesystem work out of render paths and short transactions free of network calls.
  • For a hot or high-volume path, record the relevant measurement, query plan, bundle effect, or complexity argument. Do not claim a performance improvement from code shape alone.

Frontend Rules

  • Reuse primitive controls from apps/app/src/components/ui.
  • Put app-wide composed UI in apps/app/src/components.
  • Put feature-specific UI, hooks, state, and behavior in apps/app/src/react-app/domains/<domain>.
  • Move UI to packages/ui only when more than one application genuinely consumes it.
  • Keep domain internals private. Share a stable public API or move truly cross-domain logic to a neutral owner instead of deep-importing another domain.
  • Use server APIs for server-owned behavior. Never reproduce filesystem, persistence, authorization, or orchestration logic in the client.
  • Put cross-process request/response contracts in packages/types; do not maintain separate client and server copies.

Server And Generated Files

  • Add thin HTTP handlers to apps/server/src/routes; put reusable business behavior in the existing owning service/extension module.
  • Reuse path guards from apps/server/src/paths.ts, including safe workspace-relative normalization and root containment helpers.
  • Never construct user-controlled filesystem paths with unchecked path.join or string concatenation.
  • Runtime exports, uploads, captures, renders, audio, images, and generated HTML must not be written under apps/server/src or another source directory.
  • Preserve the current session layout: <workspace>/design/<session-id>/... for design/PPT/web sessions and <workspace>/video/<session-id>/... for video sessions.
  • Put artifact kinds such as assets, renders, audio, captures, and exports below the owning session directory when appropriate.
  • Centralize directory creation and path resolution in one owning service. Routes and UI should pass identifiers, not invent disk paths.

Platform And Repository Safety

  • Keep Electron lifecycle and native integration in apps/desktop; do not leak shell-specific behavior into app domains.
  • Keep headless runtime orchestration in apps/orchestrator; do not create a second orchestration path in the UI or server.
  • Keep OpenCode external. Use its supported API, SDK, CLI, plugin, and configuration surfaces; do not fork or silently modify its internals.
  • Keep names consistently iPolloWork and ipollowork; do not introduce alternate product spellings in code, paths, docs, or user-facing text.
  • Do not commit secrets, credentials, local caches, build output, generated runtime artifacts, or commercial-only code.

Verification By Risk

  • TypeScript or UI: run the owning package typecheck and focused tests.
  • Server or plugin: run focused unit tests and the relevant package test.
  • Build or runtime boundary: build the affected package and start the real development entrypoint.
  • Observable UI: verify the actual browser/Electron flow using the repository experience-proof rules in AGENTS.md.
  • Dependency or OpenCode change: record old/new versions and verify startup, configuration, and the affected loading path.
  • Database or high-volume query: verify migrations, constraints, rollback/rejection behavior, bounded results, and the relevant query plan when representative data exists.

Completion Standard

  • No existing reusable implementation was missed.
  • No unjustified file, directory, dependency, route, table, state store, or abstraction was added.
  • No client/server contract was duplicated.
  • No runtime artifact was added to a source tree.
  • New files have one clear owner and do not create a parallel architecture.
  • Runtime work is bounded and no obvious N+1, request loop, broad subscription, or heavy eager import was introduced.
  • Existing behavior remains the default when extending shared code.
  • Replaced code and stale documentation were removed instead of retained as alternate versions.
  • Focused tests, package checks, git diff --check, and the maintainability audit pass; any unverified runtime surface is stated explicitly.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ipollowork Maintainable Code AI skill do?

Mandatory iPolloWork code-change gate for modern, minimal, performant, reuse-first implementation and clean repository ownership. Use whenever AI creates, edits, deletes, or refactors application code, server code, packages, scripts, tests, dependencies, schemas, routes, UI, or generated-file workflows. Reuse existing code before creating files, keep one source of truth, prevent parallel implementations and junk directories, justify every new file or dependency, and audit the current change before completion.

Why use Ipollowork Maintainable Code on TypingMind?

Because you install it once and use it with any model. Ipollowork Maintainable Code is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ipollowork Maintainable Code in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Devin-AXIS/iPolloWork/tree/main/.codex/skills/ipollowork-maintainable-code. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ipollowork Maintainable Code?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ipollowork Maintainable Code?

As many as you like. As long as a model supports skills, you can use Ipollowork Maintainable Code with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ipollowork Maintainable Code AI skill free?

It is published on GitHub by Devin-AXIS. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇