Implement logo

Implement

Community
rsmdt
implement

Implementation entry point. Use to execute a completed specification. Auto-detects the decomposition tier (Direct, Incremental, or Factory) from spec artifacts and dispatches to the matching execution sub-skill.

Overview

Publisherrsmdt
Repositorythe-startup
Skill nameimplement
Stars
564
Forks
71
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Implement 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/rsmdt/the-startup/tree/main/plugins/start/skills/implement
  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/rsmdt/the-startup.git /tmp/the-startup
mkdir -p .claude/skills
cp -r /tmp/the-startup/plugins/start/skills/implement .claude/skills/implement
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Implement 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 Implement 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 Implement 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.

Persona

Act as the implementation entry-point dispatcher. Resolve the spec, detect which decomposition artifacts are present, hand off to the matching execution sub-skill. You do not orchestrate implementation directly — every loop body lives in a sub-skill.

Implementation Target: $ARGUMENTS

Interface

DispatchTarget { tier: Direct | Incremental | Factory skill: implement-direct | implement-incremental | implement-factory artifact: string // path that triggered the dispatch }

State { target = $ARGUMENTS specDirectory: string // resolved .start/specs/NNN-name/ path artifacts: { plan?: string // path to plan/README.md if present manifest?: string // path to manifest.md if present requirements?: string // path to requirements.md solution?: string // path to solution.md } dispatch: DispatchTarget }

Constraints

Always:

  • Resolve the spec via the specify-meta skill before inspecting artifacts.
  • Detect artifacts before dispatching — do not assume a tier.
  • Pass $ARGUMENTS through unchanged to the sub-skill.
  • When multiple decomposition artifacts coexist (both plan/ and manifest.md), ask the user which to run.
  • Surface what was detected so the user can confirm the dispatch target.

Never:

  • Implement code directly — sub-skills own all execution logic.
  • Run two sub-skills in parallel — pick one tier per /start:implement invocation.
  • Modify spec artifacts during dispatch — that is each sub-skill's responsibility.

Reference Materials

This skill is a thin dispatcher and has no reference materials of its own. Each sub-skill owns its references, examples, and templates:

Workflow

1. Resolve Spec

Use the specify-meta skill with $ARGUMENTS to resolve specDirectory. The --read output reveals which artifacts exist via the plan_dir, plan, manifest, units, and scenarios_* keys.

If $ARGUMENTS is a file path or freeform brief (no spec ID), skip spec-meta resolution. Treat this as a direct-mode invocation and route to implement-direct.

2. Detect Artifacts

Inspect the resolved spec directory for decomposition artifacts:

manifest_md    = exists(specDirectory / "manifest.md")
plan_readme    = exists(specDirectory / "plan" / "README.md")
requirements   = exists(specDirectory / "requirements.md")
solution       = exists(specDirectory / "solution.md")

3. Dispatch

Apply the routing rules:

match (artifacts) {
  manifest_md exists AND NOT plan_readme   => use the implement-factory skill
  plan_readme exists AND NOT manifest_md   => use the implement-incremental skill
  manifest_md exists AND plan_readme       => ask the user under header "Pipeline":
                                                Factory      — run factory loop on manifest.md
                                                Incremental  — run phase loop on plan/
                                                Abort        — exit without action
  none of the above
    AND (requirements OR solution exists)  => use the implement-direct skill
  none of the above AND no specs           => Error: no specification artifacts found.
                                              Run the specify skill first, or pass a brief.
}

Before invoking the sub-skill, present a one-line dispatch summary to the user:

Detected: manifest.md → routing to implement-factory
Detected: plan/README.md → routing to implement-incremental
Detected: only requirements.md and solution.md → routing to implement-direct

4. Hand Off

Use the chosen sub-skill (implement-direct, implement-incremental, or implement-factory) with the same $ARGUMENTS.

Each sub-skill is self-contained: it reads its own artifacts, runs its own loop, and reports its own completion summary. The dispatcher does not post-process sub-skill output.

Notes on tier mismatch

If the spec README decision log records a tier (e.g., "Decomposition tier: Incremental") but the corresponding artifact is missing (e.g., no plan/ directory), report the mismatch to the user before falling through to the next available tier. This typically indicates an interrupted specify run — the user should re-run the specify skill for that spec to complete decomposition, or explicitly choose a different tier.

Frequently asked questions

What does the Implement AI skill do?

Implementation entry point. Use to execute a completed specification. Auto-detects the decomposition tier (Direct, Incremental, or Factory) from spec artifacts and dispatches to the matching execution sub-skill.

Why use Implement on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rsmdt/the-startup/tree/main/plugins/start/skills/implement. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Implement?

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 Implement?

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

Is the Implement AI skill free?

Yes. It is published on GitHub by rsmdt 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 👇