cmd-olshanskify
Apply Olshansky's personal style to docs, code, blog posts, or presentations using template-driven rules. Invoke manually via /cmd-olshanskify — pick a content type, point at the target, and the agent rewrites or proposes edits that match the canonical style guide in templates/.
What this skill does
# Olshanskify <!-- omit in toc -->
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](#global-style-rules)
- [1. Pick a Template](#1-pick-a-template)
- [2. Inspect the Target](#2-inspect-the-target)
- [3. Propose the Olshanskified Version](#3-propose-the-olshanskified-version)
- [4. Apply on Approval](#4-apply-on-approval)
- [5. Evolving the Templates](#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.
| Content type | Template | Use when |
|---|---|---|
| Documentation (READMEs, AGENTS.md, guides) | [`templates/docs.md`](templates/docs.md) | Editing any markdown-heavy reference material |
| Code (any language) | [`templates/code.md`](templates/code.md) | Editing source files, proposing refactors, writing new code |
| Blog post | [`templates/blog.md`](templates/blog.md) | Drafting or polishing posts for olshansky.info / substack / similar |
| Presentation / slides | [`templates/presentation.md`](templates/presentation.md) | Editing slide decks, talk outlines, conference abstracts |
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:
```markdown
## 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.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.