Money Skillify logo

Money Skillify

CommunityPopular
iamzifei
money-skillify

Codify a successful workflow from the current conversation into a permanent project-local skill. After you discover (e.g.) a cold-email sequence that converts, an ad-creative format that beats baseline, or a content-pipeline cadence that compounds — /money-skillify writes it as a SKILL.md under the project's local skills directory so future sessions can re-invoke it without re-discovery. Use when the user says: 'this worked, save it', 'codify this', 'turn this into a skill', '把这个固化下来', '存成 skill'.

Overview

Publisheriamzifei
Repositoryshow-me-the-money
Skill namemoney-skillify
Stars
1K
Forks
159
Bundled files
Instructions only
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 iamzifei on GitHub. Read the source before you install it.

Installation

Install the Money Skillify 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/iamzifei/show-me-the-money/tree/master/skills/money-skillify
  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/iamzifei/show-me-the-money.git /tmp/show-me-the-money
mkdir -p .claude/skills
cp -r /tmp/show-me-the-money/skills/money-skillify .claude/skills/money-skillify
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Money Skillify 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 Money Skillify 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 Money Skillify 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.

/money-skillify — Codify a Working Pattern Into a Reusable Skill

Most successful workflows are discovered once, executed by hand, and forgotten. The next time the user faces the same problem, they re-discover it (or rebuild a worse version). /money-skillify solves this: it walks back through the most recent successful workflow, distills the steps, and writes a project-local SKILL.md.

The output is a custom skill stored at ~/.smtm/projects/{slug}/skills/{name}/SKILL.md. Future Claude Code sessions in this project can reference it.


Triggers

CommandBehavior
/money-skillifyCodify the most recent successful workflow in this conversation
/money-skillify <name>Same, with an explicit name for the new skill
/money-skillify listList all project-local skills in ~/.smtm/projects/{slug}/skills/
/money-skillify show <name>Print a project-local skill

Natural-language equivalents:

  • "This worked, save it", "Codify this", "Turn this into a skill", "Make this reusable"
  • "把这个固化下来", "存成 skill", "保存这个流程"

What counts as "a successful workflow"

A workflow is /money-skillify-eligible if all three are true:

  1. The user explicitly confirmed it worked (clear signal: "this worked", "this converted", "ship it", "much better than before", "我们就这么干")
  2. There's a clear sequence of steps (not just a single insight — that's a /money-learn not a skill)
  3. The pattern is reusable — it would help to do exactly the same thing again next time, in this project

Anti-patterns that should NOT be skillified:

  • A one-off bug fix
  • A pattern that's user-specific but not reusable across the user's products
  • A pattern more naturally captured as a learning (single observation)
  • A pattern already covered by an existing money-* skill

Workflow

Step 1 — Identify the workflow

Walk back through the conversation. Find the most recent sequence where:

  1. The user described or asked for something to be done
  2. A series of steps was executed
  3. The user confirmed satisfaction

Quote the user's confirmation back to them so they can verify which workflow you're about to codify:

I'm about to codify the workflow that produced "{quoted confirmation}". The steps as I understood them:

  1. {step 1}
  2. {step 2} ...

Is this what you want to skillify? [y / edit / different workflow]

If the user wants a different workflow, ask which.

Step 2 — Choose a name

Default: {slug-of-the-workflow} (e.g., cold-email-saas-buyers, ad-creative-3x-baseline, weekly-ship-cadence).

If /money-skillify <name> was given, use that. Else propose 1-3 candidate names and ask the user to pick.

The skill name will become the file path:

~/.smtm/projects/{slug}/skills/{name}/SKILL.md

Step 3 — Distill the steps

Convert the workflow into a fixed format:

markdown
---
name: {project-slug}-{name}
description: "{One-line summary of what this skill does, when to invoke. Auto-derived but user can edit.}"
project: {project slug}
captured_at: {ISO 8601}
captured_from: {conversation-summary | snapshot-id}
trigger: {natural-language phrase or /command pattern that invokes this}
---

# {Title}

## When to use

{1-2 sentences describing the trigger condition. Specific. "Cold email to early-stage SaaS founders with under $10k MRR" not "cold email to people".}

## Inputs needed

- {Input 1, e.g., "Target ICP description"}
- {Input 2, e.g., "Sender's product URL"}
- ...

## Steps

1. {Step 1, including any specific commands, tools, or templates used}
2. {Step 2}
3. ...

## Success signal

How to know it worked. ("Reply rate ≥10%", "Conversion ≥1.5%", etc.)

## Failure mode + fallback

What goes wrong, and what to do instead. ("If reply rate <5%, the subject line is the issue — switch to {alternative}")

## Variables / templates

If the workflow uses a template (e.g., email body, ad creative), include the template literally. Mark variables in `{double-braces}`.

## Evidence this works

The original conversation context: who, what, when, what result. One paragraph.

## Limitations

When this skill should NOT be used. ("This works for B2B SaaS; do not use for B2C.")

Step 4 — Write to disk

Path: ~/.smtm/projects/{slug}/skills/{name}/SKILL.md

mkdir -p the directory tree first. If a file already exists at that path, ask:

  • Append a version number (e.g., cold-email-v2/)?
  • Overwrite?
  • Cancel?

Default to "append a version" — preserves the prior skill in case the new one is worse.

Step 5 — Confirm + register

Print:

✅ Skill codified.

Path: ~/.smtm/projects/{slug}/skills/{name}/SKILL.md
Trigger: {trigger}

To re-run this skill in a future Claude Code session:
1. Open Claude Code in this project's directory
2. Type "{trigger}" or load the file directly: `read ~/.smtm/projects/{slug}/skills/{name}/SKILL.md`
3. The skill will execute the same steps with new inputs

Optionally suggest creating a learning to record that this workflow was successfully captured:

Want to also log a learning? E.g., "{name} converts at X% for {ICP}" — /money-learn add.


Auto-loading project-local skills

Other money-* skills should check ~/.smtm/projects/{slug}/skills/ at startup. If any project-local skills exist, surface them once per session:

📦 This project has 3 codified skills: cold-email-saas-buyers, ad-creative-3x-baseline, weekly-ship-cadence. Reference them by name or run /money-skillify list to see all.

This is how the user's accumulated craft becomes part of every future session, automatically.


List mode

/money-skillify list:

Project-local skills for `{project}`:

| Name | Captured | Trigger |
|---|---|---|
| cold-email-saas-buyers | 2026-04-22 | "cold email outreach for SaaS" |
| ad-creative-3x-baseline | 2026-04-15 | "generate ad creative" |
| ... | | |

/money-skillify show <name>: Cat the file. Print path at top.


Edge cases

  • No clear successful workflow in conversation — Ask the user to describe the workflow and walk through Step 3 manually.
  • Workflow uses external tools the user doesn't have configured — Note them in the SKILL.md as prerequisites; don't fail.
  • Workflow contains sensitive data (customer names, internal URLs) — Strip them out, replace with {variable} placeholders, ask user to confirm sanitization.
  • Project-local skill duplicates a global money- skill* — Warn: "This overlaps significantly with /money-content. Are you sure you want a project-local version, or should we update your /money-content workflow instead?"

Principles

  • Codify only proven patterns — Failed or unconfirmed workflows get a /money-learn entry, not a skill.
  • Specific over general — A skill named cold-email-saas-founders-under-10k-mrr is more useful than cold-email-template. Specificity drives retrieval and quality.
  • Sanitize before saving — Project-local skills may end up in version control or shared. Strip secrets and PII as part of Step 3.
  • Versions, not overwrites — cold-email/ then cold-email-v2/ then cold-email-v3/. The progression is itself useful institutional memory.
  • Skill, not journal — A skill encodes a procedure. A journal records what happened. If there's no procedure to encode, log a learning instead.

Value Quantification (Required at End of Output)

After successful codification:

  • 📦 Captured — One reusable skill at {path}
  • ⏱ Time saved per future use — ~30-90 minutes — re-discovering the same sequence vs. running it from a SKILL.md
  • ⚠️ Risk avoided — Re-doing the workflow worse next time — most founders re-build a degraded version of their own prior success because the original wasn't captured
  • 🔁 Auto-surfaced — Every future Claude Code session in this project gets a one-line nudge listing project-local skills available

After /money-skillify list:

  • 📋 Surfaced — {N} project-local skills, each with its trigger
  • ✅ What you got — A complete list of your codified workflows for this project, with file paths and triggers

Frequently asked questions

What does the Money Skillify AI skill do?

Codify a successful workflow from the current conversation into a permanent project-local skill. After you discover (e.g.) a cold-email sequence that converts, an ad-creative format that beats baseline, or a content-pipeline cadence that compounds — /money-skillify writes it as a SKILL.md under the project's local skills directory so future sessions can re-invoke it without re-discovery. Use when the user says: 'this worked, save it', 'codify this', 'turn this into a skill', '把这个固化下来', '存成 skill'.

Why use Money Skillify on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/iamzifei/show-me-the-money/tree/master/skills/money-skillify. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Money Skillify?

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 Money Skillify?

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

Is the Money Skillify AI skill free?

It is published on GitHub by iamzifei. 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 👇