Lock Decision logo

Lock Decision

Community
drobins25
lock-decision

This skill should be used when the user says "lock it", "go with that", "approved", "that's the standard", or explicitly establishes a project-wide pattern like "from now on all forms should use this approach". Formalizes approved decisions into locked standards that the system enforces going forward. Not needed for story-scoped decisions — only for project-wide patterns.

Overview

Publisherdrobins25
Repositorycraft
Skill namelock-decision
Stars
69
Forks
6
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by drobins25 on GitHub. Read the source before you install it.

Installation

Install the Lock Decision 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/drobins25/craft/tree/main/skills/lock-decision
  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/drobins25/craft.git /tmp/craft
mkdir -p .claude/skills
cp -r /tmp/craft/skills/lock-decision .claude/skills/lock-decision
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lock Decision 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 Lock Decision 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 Lock Decision 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.

Lock Decision Skill

You are the commitment mechanism of the Craft harness. When something is approved, you make it official — turning decisions into standards that the entire system respects.

When This Activates

  • User explicitly approves an option ("let's go with A", "yes, that one")
  • User says "lock it", "that's the one", "approved"
  • A design pattern needs to become a standard
  • A technical approach should be enforced

Orchestrator Context

The orchestrator may pass enriched args. Parse labeled fields if present:

  • DECISION_TYPE: design/pattern/token/approach — routes to correct lock template
  • DECISION_SCOPE: project-wide or story-scoped — determines where to write

Fallback: Most lock context comes from conversation. Args are supplementary.

The Lock Process

1. Confirm Understanding

Before locking, verify:

markdown
## Locking Decision

**Decision:** [Clear statement of what's being locked]

**Context:** [Why this decision was made]

**Applies to:** [Where this standard will be enforced]

Is this correct? Once locked, this becomes a project standard.

2. Execute the Lock

Depending on what's being locked:

Design Pattern → locked.md
markdown
## [Pattern Name]

**Locked:** [Date]
**Context:** [Why this was approved]

### Specification

[Detailed description of the pattern]

### Implementation

```tsx
// Example code showing correct implementation

Variations

  • [Allowed variation 1]
  • [Allowed variation 2]

Not Allowed

  • [Anti-pattern 1]
  • [Anti-pattern 2]

#### Design Token → `tokens.yaml`

**When locking colors, typography, or spacing values, update `.craft/design/tokens.yaml`:**

When the file already exists, update it with targeted Edits on the specific keys - never a whole-file Write (the write-permission hook denies Write on an existing tokens.yaml; unnamed keys and their provenance comments must survive).

```yaml
colors:
  primary: "#6366F1"  # Locked: [Date] - [Context]
  surface: "#FAFAFA"

typography:
  font-sans: "Inter, -apple-system, sans-serif"

spacing:
  base: 8  # Locked: [Date]

This file is the source of truth. The implementer agent reads this when writing styles. Quality gates validate against it.

Technical Approach → Story file or project.md
markdown
## Technical Decision: [Title]

**Locked:** [Date]
**Decision:** [What was decided]
**Rationale:** [Why this approach]
**Alternatives Considered:** [What we didn't choose and why]

3. Confirm the Lock

After writing the lock, output a brief confirmation and return silently to the caller:

Locked: [Summary] → [File updated]

Do NOT output a large markdown block or ask "Ready to continue?" — the caller (story-new, creative-spark, etc.) owns the next step. Terminal text kills command chains.

Lock Categories

Four lock types: Design Decisions (typed UI decisions with valid keys per type), Pattern Locks (UI patterns with spec, states, variants, usage rules), Token Locks (design values in tokens.yaml), and Approach Locks (technical decisions with rationale and implementation standard).

Lock templates: Read ${CLAUDE_PLUGIN_ROOT}/skills/lock-decision/references/lock-templates.md for detailed templates and examples for each lock type (design decisions with valid key tables, pattern locks, token locks, approach locks).

Enforcement

Locked decisions are enforced via:

  1. Style hooks — Grep for token violations on Write/Edit
  2. Adhoc Fit Check - on the adhoc tweak path, the Fit Check's read of locked.md (plus its mid-pass pivot re-check) is the lock gate - no blocking hook checks locked.md compliance; the write-gate hook checks only write permission
  3. Code review — Analyzer agents reference locked patterns
  4. Validation — Validation enforces locked decisions during implementation

Unlocking (Rare)

Locks can only be unlocked by explicit user request:

markdown
## Unlock Request

**Pattern:** [What's being unlocked]
**Reason:** [Why the lock should be removed]
**Proposed Change:** [What will replace it]

⚠️ This will remove enforcement. Are you sure?

Options:
1. Unlock and replace with new standard
2. Unlock temporarily for this story only
3. Keep locked, find another approach

Tweak-path lock edits (inline)

The adhoc tweak flow (skills/adhoc/references/tweak.md) may alter or remove a lock inline when a tweak conflicts with it - on the user's explicit yes, at one of two moments (the pre-edit conflict branch or the acceptance reconcile), WITHOUT this skill's unlock ceremony. Same discipline (explicit yes only, locked.md's existing format), lighter surface: a tweak thread gets one clean yes, never a ceremony AUQ, and a lock gets at most one write moment per thread. See tweak.md's "inline lock-edit path" for the rules.

Remember

  • Locks are sacred — they represent approved decisions
  • Context is crucial — always record why something was locked
  • Enforcement is layered, not hooked - implementers and validation enforce locks at story time, the adhoc Fit Check at tweak time; no hook blocks a write on lock compliance
  • Quality only goes up — new locks can add requirements, never remove

Your goal: Turn "yes" into "always" — making decisions stick.

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 Lock Decision AI skill do?

This skill should be used when the user says "lock it", "go with that", "approved", "that's the standard", or explicitly establishes a project-wide pattern like "from now on all forms should use this approach". Formalizes approved decisions into locked standards that the system enforces going forward. Not needed for story-scoped decisions — only for project-wide patterns.

Why use Lock Decision on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/drobins25/craft/tree/main/skills/lock-decision. 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 Lock Decision?

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 Lock Decision?

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

Is the Lock Decision AI skill free?

Yes. It is published on GitHub by drobins25 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 👇