Receive logo

Receive

Organization
AlpacaLabsLLC
receive

Register received or authored project documents by confirmed coordinates, preserve their filenames and provenance, and find or verify registered documents. Use for filing a supplied file/package or locating documents by kind, date, source or revision.

Overview

PublisherAlpacaLabsLLC
Repositoryskills-for-architects
Skill namereceive
Stars
386
Forks
81
Bundled files
6
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.

  • 6 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 Receive 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/receive
  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/receive .claude/skills/receive
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Receive 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 Receive 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 Receive 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:receive

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

Use the host adapter and available native tools or ordinary task-specific code. Operation names identify the semantic work in the workspace model, not installed functions or a script API. Resolve canonical context before durable work. No Arch Studio runner, package installation or executable reconstruction is required. Existing exact authorization persists; ask only for material missing information or missing permission.

Own the semantic procedure that writes DOCUMENTS.csv; other authored-record skills apply the same specification directly without a nested skill invocation or installed library. Classification is harness judgment. Native tools compute and verify paths, identities, hashes, collisions and publication/recovery evidence under the workspace contract.

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.

The affected set for registration is the complete destination file/package plus DOCUMENTS.csv; retain source originals and destination absence as guards. A move includes the destination, original path, every referring file requiring a rewrite, and DOCUMENTS.csv. Metadata-only updates change only DOCUMENTS.csv. Include all affected originals/preparations before any member is published; referenced sources remain read guards, not additional write targets.

Receive

  1. Resolve one new-model project and, when applicable, its explicitly registered studio. Ask for missing phase, stage, scope, originator, document date and kind, proposing evidence-based defaults. Previously confirmed coordinates need no repeated question. Dates preserve known precision; never use arrival date as an unknown issue date.
  2. For files, use the actual accessible source. For a mailbox attachment or expiring download, the host acquires the authorized original to scratch, preserving message/download identity and expiry in source; no mailbox capability is implied by this skill. If unavailable, give a bounded handoff or use a supplied disk file. A URL-only source is provenance, not a locally received file.
  3. Resolve placement under documents.resolve using confirmed coordinates and kind. The firm template owns placement. With an empty template, ask for the intended project-relative folder. Never rename received files. A folder/package retains its internal tree, including empty directories; an archive may remain a registered archive or be safely extracted by the host and received as a package. Sidecars and a sheet index are separate registered documents only when actually produced from available evidence; parsing is not invented by registration.
  4. Preview registration when its exact intent is not already authorized: source path, destination, coordinates, metadata, duplicate hashes and any explicit supersedes ID. Apply the receive-owned native registration procedure within existing authorization; a preview neither allocates an identity nor proves write access. Registration copies from the source; it does not erase the original. Differing content at the destination is a collision requiring a distinct explicit revision, never silent overwrite.
  5. Read back the row and actual file. Report document ID, relative path, hash, provenance and any unperformed content/visual inspection.

Find, move and inspect

  • documents.query filters by ID/kind/coordinates, arrival date (since), change ID, source type or expiry. latest selects the latest unsuperseded match using document date; it does not certify substantive approval or current-code applicability. Report ambiguity in the selection scope before relying on one result.
  • documents.move requires ID, current expected SHA-256 and confirmed new coordinates. It preserves ID and source filename, updates supported relative Markdown links and affected hashes/history, and never overwrites a target. A necessary rewrite of issued/accepted bytes refuses before mutation; do not reseal terms. Unrelated existing drift remains unresolved; a changed document that needs a link rewrite blocks the move. Preview first when the exact destination is not already authorized. Reopen moved outputs and inspect relevant links.
  • documents.update changes explicit status/provenance/title/notes without changing identity, bytes or revision relationships. Revised content is received as a new document with supersedes.
  • documents.verify reports unreceived files, missing files, changed hashes, duplicate hashes, expired sources and template/vocabulary findings. Findings remain explicit; do not repair by guessing.
  • Before multi-file publication, preserve the exact prior/prepared set and discoverable pending recovery evidence. documents.recover inspects actual state and resumes or restores only with fresh conflict guards; never replay a backup blindly. Cooperating locks do not exclude external editors. Verify actual staged bytes and access metadata before complete-file publication, then reread the entire affected set.

A document spanning phases remains one row at its primary confirmed phase, with other phases in notes, unless the original is physically split. Received evidence does not silently promote project facts, decisions, tasks, time or commercial acceptance.

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 Receive AI skill do?

Register received or authored project documents by confirmed coordinates, preserve their filenames and provenance, and find or verify registered documents. Use for filing a supplied file/package or locating documents by kind, date, source or revision.

Why use Receive on TypingMind?

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

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

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 Receive?

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

Is the Receive 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 👇