Version Aware Docs logo

Version Aware Docs

Community
Firstp1ck
version-aware-docs

Ground coding or configuration advice in the exact installed dependency version, enabled flags, source, and relevant documentation passage. Do not use for version-independent local code.

Overview

PublisherFirstp1ck
Repositorypi-coding-agent-forge
Skill nameversion-aware-docs
Stars
93
Forks
22
Bundled files
3
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.

  • 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 Firstp1ck on GitHub. Read the source before you install it.

Installation

Install the Version Aware Docs 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/Firstp1ck/pi-coding-agent-forge/tree/main/pi-extension-small-modal-reliability/skills/version-aware-docs
  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/Firstp1ck/pi-coding-agent-forge.git /tmp/pi-coding-agent-forge
mkdir -p .claude/skills
cp -r /tmp/pi-coding-agent-forge/pi-extension-small-modal-reliability/skills/version-aware-docs .claude/skills/version-aware-docs
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Version Aware Docs 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 Version Aware Docs 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 Version Aware Docs 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.

Version-aware documentation

Use the documentation and source that match the dependency the project actually has installed. Another major version, a generic web snippet, or a model recollection is not a substitute for exact version evidence.

When to Use

Should trigger

  • “Configure this installed framework feature according to the project’s current version.”
  • “Update code that depends on a CLI option or runtime API whose behavior changed across releases.”
  • “Use the library’s installed type signatures to repair this version-sensitive integration.”

Should not trigger

  • “Explain a version-independent language construct.”
  • “Repair a purely local function whose implementation and callers are already in the repository.”
  • “Write documentation that does not make a dependency-version claim.”

Invocation Design

  • Invocation mode: model-invoked when an external versioned contract affects a coding/configuration decision.
  • Leading concept: exact installed version before advice.
  • Completion criterion: version, enabled flags when applicable, source locator, and supporting passage are recorded or the result stays unknown/escalates.

Inputs and Assumptions

Identify the dependency, manifest and lockfile locations, package manager, installed source/types or binary, relevant feature flags, expected API/CLI/schema behavior, and the specific decision the evidence must support. Treat manifests, lockfiles, installed source, upstream documentation, and model summaries as distinct sources.

Portable Workflow

  1. Inspect the manifest and lockfile for the dependency declaration and resolved version.
    • Completion criterion: the selected package and exact resolved version are known.
  2. Inspect installed source, types, local help, or version-matched bundled documentation.
    • Completion criterion: a relevant signature, option, or behavior passage is available.
  3. If local evidence is insufficient, locate official versioned documentation or the exact source tag.
    • Completion criterion: the external source is authoritative for the resolved version, not merely similar.
  4. Record the version, enabled feature flags, source locator, and exact relevant passage.
    • Completion criterion: another reviewer can trace the advice to the selected version.
  5. Apply only advice consistent with that evidence; reject cross-major assumptions.
    • Completion criterion: unsupported or conflicting advice is marked unknown, blocked, or escalated.

Safety and Side Effects

Do not install, upgrade, downgrade, regenerate locks, or change dependency declarations merely to obtain documentation. Do not infer resolved versions from a manifest range alone. Do not use an old major-version example as compatibility proof. If manifest, lockfile, installed source, or source passage disagree, stop and surface the conflict.

Scripts, References, and Dependencies

No installation or live query is required. Read version evidence before recording a version-sensitive conclusion.

Verification

Verify that package name and exact version agree across manifest/lock/source evidence, feature flags are stated when relevant, the source passage supports the concrete claim, and the final patch/check uses the same versioned contract. A local-only change should say dependency evidence was not required rather than fabricate a record.

Pi Adapter

  • Resolve an ordinary/queued instruction pause with /reliability input confirm before proceeding; expanded template or skill text is not raw-input authority.

  • Match the actual resolved installed package root, not a copied or decoy manifest. Linked/symlinked, virtual-store, and unsupported layouts remain unknown. A claimed passage must match the inspected source bytes.

  • Read the manifest, optional lockfile, installed source/types, and relevant documentation passage through normal host tools before recording evidence.

  • Call reliability_evidence action record-dependency with the exact package/version, manifest path, source kind/ID, and passage IDs. Add lockfilePath only when the lock is available and supported; it is optional, never invented.

  • A supplied manifest or lockfile must be a real non-symlink workspace JSON file no larger than 2 MiB. The lock reader recognizes supported npm packages or legacy dependencies entries. For a large, unsupported, or unavailable lockfile, use a bounded host parser or omit the optional lock path and report the resulting limit; do not claim a resolved lock version.

  • The coding completion gate requires passing behavior validation and valid dependency evidence for each external package it detects in changed static imports, not merely contracts named by a declared coding criterion. Dynamic, alias, unreadable, deleted, and non-code changes receive exact-diff local-only review instead of an unproven exemption.

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 Version Aware Docs AI skill do?

Ground coding or configuration advice in the exact installed dependency version, enabled flags, source, and relevant documentation passage. Do not use for version-independent local code.

Why use Version Aware Docs on TypingMind?

Because you install it once and use it with any model. Version Aware Docs 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 Version Aware Docs in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Firstp1ck/pi-coding-agent-forge/tree/main/pi-extension-small-modal-reliability/skills/version-aware-docs. 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 Version Aware Docs?

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 Version Aware Docs?

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

Is the Version Aware Docs AI skill free?

Yes. It is published on GitHub by Firstp1ck 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 👇