Cmd Olshanskify

Olshanskify

Rewrite or edit content so it matches Olshansky's voice and conventions. Templates encode the rules; this skill picks the right template and applies it.

• Global Style Rules
• 1. Pick a Template
• 2. Inspect the Target
• 3. Propose the Olshanskified Version
• 4. Apply on Approval
• 5. Evolving the Templates

Global Style Rules

These apply across all templates (docs, code, blog, presentation) and across any conversational prompt / status output this skill produces:

• Signal user action with an emoji or admonition. Whenever the reader must decide, approve, resolve, or confirm something, prefix the prompt with a status glyph — green/yellow/red circle or a GitHub-style admonition:
  • 🟢 safe / ready to proceed
  • 🟡 caution / needs review
  • 🔴 blocked / must be addressed
  • ⚠️ / > [!WARNING] — urgent or destructive action
  • ⏳ / 🤔 — waiting on user input
• Wrap every list/option label in square brackets. If something is a selectable option, a referenced list item, or a status tag, use […] around it. Examples: [1] Approve, [2] Reject, [✅ DONE], [OPTION A], [FEAT], [WALLET]. Consistent brackets make options scannable and unambiguous.

1. Pick a Template

Templates live in templates/ — one per content type. Add a new template when a new content type appears; update an existing template when a new rule emerges.

If the user does not specify a content type, ask:

Which Olshanskify template should I apply — docs, code, blog, or presentation? (Or is this a new type worth adding to templates/?)

2. Inspect the Target

Before proposing edits:

1. Read the target file(s) in full.
2. Read the chosen template end-to-end.
3. Note any pre-existing style choices in the target that conflict with the template — surface conflicts explicitly rather than silently overriding.

3. Propose the Olshanskified Version

Show the user a diff or side-by-side before writing. Format:

## Olshanskify: {target_path}

Template applied: **{template_name}**

### Rules triggered
- {rule from template} → {how it reshapes this content}
- ...

### Proposed changes
- {file}:{lines} — {one-line summary of the edit}
- ...

### Conflicts / judgment calls
- {anything where the template and the existing content disagreed, and how you resolved it}

Do not edit yet. Wait for approval.

4. Apply on Approval

After the user confirms, apply the edits. Respect the global rule: the user commits manually — do not run git commit or git push.

5. Evolving the Templates

Templates are living documents. Update them when:

• The user corrects a style choice ("no, always use X" / "drop the Y pattern").
• A cross-skill signal surfaces a rule worth codifying. For example, cmd-pr-gh-comments proposes updates to templates/code.md whenever PR feedback came from @olshansk (see that skill's step 10).
• A new content type appears — add a new template file and an entry to the table above.

When proposing a template edit, show:

1. The rule to add (or change), in the template's existing tone.
2. The source of the rule (which conversation, PR, or file surfaced it).
3. A quick example of before/after if the rule is non-obvious.

Never silently mutate a template. Every change is approval-gated.