Project logo

Project

Organization
AlpacaLabsLLC
project

Initialize or inspect a project, maintain sourced current facts and record durable decisions. Use for project context or remember-this requests; other record types retain their owners.

Overview

PublisherAlpacaLabsLLC
Repositoryskills-for-architects
Skill nameproject
Stars
386
Forks
81
Bundled files
11
LicenseMIT
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.

  • 11 bundled files

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

  • Open source

    Published by AlpacaLabsLLC on GitHub. Read the source before you install it.

Installation

Install the Project 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/AlpacaLabsLLC/skills-for-architects/tree/main/skills/project
  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/AlpacaLabsLLC/skills-for-architects.git /tmp/skills-for-architects
mkdir -p .claude/skills
cp -r /tmp/skills-for-architects/skills/project .claude/skills/project
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Project 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 Project 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 Project 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.

/as:project

Before acting, read the host contract, this component's declaration (skill:project), and applicable workspace semantics. Load only the required modes from the shared catalog.

Use the host adapter for native invocation. Apply the native workspace operations with the host’s own tools and ordinary task-specific code. Operation names identify semantic scope, not function calls or a dispatcher. No Arch Studio runner, executable download or reconstructed helper is required. Resolve canonical context before existing-workspace edits; fresh setup validates its explicit target and ancestor boundary instead. Existing exact authorization persists; ask only for material missing information or missing permission.

Own PROJECT.md current facts and documents of kind decision. The agreement skill owns only its bounded Agreement section in PROJECT.md; studio owns synchronized registered status. Decision reasoning is not duplicated into the fact manifest.

Before changing records

Before persistent changes, follow the native mutation sequence: Inspect → Prepare → Verify preparation → Apply → Verify result → Complete. Inspect pending work first. Finish and verify preparation before the first canonical write: separately reread every saved original and prepared file, check its complete actual bytes, establish durable saving, and inspect actual permissions, ownership and ACLs. Merely writing recovery files does not finish verification. Apply only that verified set. Mark complete only after fresh readback validates the entire affected result and its relationships. Read-only requests and inline drafts need no publication sequence.

Fresh setup prepares the entire declared project tree with retained identities. A fact edit affects PROJECT.md only. A decision registration affects the complete decision document plus DOCUMENTS.csv. Used-vocabulary renames include the manifest, every relocated document/referring file and its register changes; determine the complete set before applying any part. Studio-owned synchronized status includes both manifests.

Fresh setup

Use project.init after confirming the exact target, immutable Project ID, display name, Type, advisory Kind/Status, client/code and Created date. Display name and Folder ID are distinct from Project ID. Ask for the firm's phases, scopes, originators and applicable stage vocabulary; defaults are proposals, not external normative codes. Standalone projects carry their template/stages in PROJECT.md; registered projects use STUDIO.md's template/stages. A valid standalone project remains valid and does not require studio creation.

The new shape is Format version 3, Document model 1. Preview the exact generated files; setup creates PROJECT.md, empty CSV registers, host instructions/skill roots and immutable folder identity, with no prose scaffold folders. It does not initialize Git, accounts or storage. No old-format converter exists. Existing live workspaces are not silently transformed. Inside a studio, studio orchestrates initialization and registration without recursive routing.

project.status reports identity and document verification; statuses and project Kind are advisory, not permission gates. Follow the receive-owned native document verification specification for the document findings; a missing capability is reported separately from observed identity. Use documents.query for decisions and dated records, tasks.list for actions and invoice.status for ledger facts. Do not infer complete state from missing/unreadable evidence.

Facts and decisions

For project.facts (remember/update), distinguish sourced facts, choices and unresolved information. Preview each destination and preserve provenance/date. Record only confirmed changes. Approval to save a source does not approve promoting all its statements.

For project.decision (record-decision), capture one choice, context, actual options, deciders, proposed/decided status, rationale, consequences and exact sources. Allocate the next permanent decision number from registered decision records, without renumbering or reusing historical IDs. Prepare the authored Markdown with the bundled decision template; resolve its confirmed coordinates and register via documents.register, kind decision. Preserve unknowns and proposal status.

For supersession, receive a new decision document with supersedes referencing the original ID; preserve original bytes/history. Do not infer supersession from a later date alone. Query kind decision for listing; there is no separate path-based decision index.

Vocabularies

project.vocab lists/adds/renames project phase, scope or originator values. Confirm unknown values; never invent them. A used value requires coordinated placement/link updates rather than an in-place manifest rename. Stage vocabulary belongs to studio (or the standalone manifest). An explicit request may create an empty phase folder; ordinary vocabulary edits do not precreate content directories.

Tasks, time, invoices, minutes, site reports and plans retain their corresponding owners. Use stable registered document IDs plus item anchors for provenance. Every durable mutation is read back; raw conversation is not archived merely because a fact/decision is saved.

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 Project AI skill do?

Initialize or inspect a project, maintain sourced current facts and record durable decisions. Use for project context or remember-this requests; other record types retain their owners.

Why use Project on TypingMind?

Because you install it once and use it with any model. Project 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 Project in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/project. 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 Project?

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 Project?

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

Is the Project AI skill free?

Yes. It is published on GitHub by AlpacaLabsLLC under the MIT license. 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 👇