Name: agent-skills
Author: olshansk

Stats

Actions

Available In

Help us improve

Share bugs, ideas, or general feedback.

agent-skills

[!NOTE] My personal and public agent skills. Olshansky.info

What is this?

Olshansky's day-to-day agent skills

Follows the Agent Skills pattern for cross-tool skill distribution

Inspired by vercel-labs/agent-skills

Table of Contents

Quickstart

npx skills add olshansk/agent-skills

Then ask your agent to run any installed skill:

"resolve merge conflicts"

"close the loop on this session"

"idiot proof the documentation"

"generate skills dashboard"

[!TIP] Start with cmd-session-commit — it turns every coding session into durable knowledge by extracting patterns, decisions, and gotchas into your AGENTS.md. Future sessions (and future agents) pick up right where you left off.

Available Skills

Skill

Description

cmd-agent-persona-set

Prime the agent with a behavioral persona for the conversation

cmd-code-what

Catch the user up on session activity in 3-5 ultra-tight **label**: explanation bullets

cmd-codex-review-plan

Get a second-opinion plan review from Codex (codex exec) before exiting plan mode

cmd-codex-review-unstaged

Have Codex review the working-tree diff and synthesize a prioritized iteration plan

cmd-docs-idiot-proof

Simplify documentation for clarity and scannability with approval-gated edits

cmd-done-check

Ask the agent whether it finished everything — a lightweight completeness gate for any task

cmd-email-md

Convert markdown to email-safe HTML with inline styles and cross-client compatibility

cmd-gh-issue

Create structured GitHub issues from conversation context using gh CLI

cmd-golden-tests

Set up or extend golden/snapshot tests: fixture design, Makefile targets, snapshot storage, diff workflow, and update protocol

cmd-latest-msg

Store or retrieve the latest agent message to /tmp/agents/{agent}/

cmd-makefile

Create or improve Makefiles with templates (python-uv, fastapi, nodejs, go, flutter)

cmd-mermaid-render

Render and display Mermaid diagrams inline in iTerm2 or Ghostty

cmd-olshanskify

Apply Olshansky's personal style to docs, code, blog posts, or presentations via templates

cmd-plan-store

Capture conversation plans, decisions, and action items into structured markdown in plans/

cmd-pr-build-context

Build high-signal PR context with diff analysis, risk assessment, and discussion questions

cmd-pr-conflict-resolver

Resolve merge conflicts with context-aware 3-tier classification and escalation

cmd-pr-description

Generate concise PR descriptions by analyzing the diff against a base branch

cmd-pr-edgecase

Review branch changes for test gaps, logic edge cases, and failure modes

cmd-pr-follow-up

Post-implementation reflection — surface missed work, simplifications, and idiomatic fixes

cmd-pr-gh-comments

Holistically triage PR comments with line-range context, adjacent sweeps, approval-gated resolution, and cmd-olshanskify updates for @olshansk feedback

cmd-pr-review-prepare

Prepare branch for code review by building context and identifying issues

cmd-pr-scope-sweep

Final pass to identify missed items, edge cases, and risks before closing scope

agent-skills

[!NOTE] My personal and public agent skills. Olshansky.info

What is this?

Olshansky's day-to-day agent skills
Follows the Agent Skills pattern for cross-tool skill distribution
Inspired by vercel-labs/agent-skills

Quickstart
Available Skills
- 3rd Party Skills
Star History
Demo of cmd-skills-dashboard
How It Works

Quickstart

npx skills add olshansk/agent-skills

Then ask your agent to run any installed skill:

"resolve merge conflicts"
"close the loop on this session"
"idiot proof the documentation"
"generate skills dashboard"

[!TIP] Start with cmd-session-commit — it turns every coding session into durable knowledge by extracting patterns, decisions, and gotchas into your AGENTS.md. Future sessions (and future agents) pick up right where you left off.

Available Skills

Skill	Description
`cmd-agent-persona-set`	Prime the agent with a behavioral persona for the conversation
`cmd-code-what`	Catch the user up on session activity in 3-5 ultra-tight `label: explanation` bullets
`cmd-codex-review-plan`	Get a second-opinion plan review from Codex (`codex exec`) before exiting plan mode
`cmd-codex-review-unstaged`	Have Codex review the working-tree diff and synthesize a prioritized iteration plan
`cmd-docs-idiot-proof`	Simplify documentation for clarity and scannability with approval-gated edits
`cmd-done-check`	Ask the agent whether it finished everything — a lightweight completeness gate for any task
`cmd-email-md`	Convert markdown to email-safe HTML with inline styles and cross-client compatibility
`cmd-gh-issue`	Create structured GitHub issues from conversation context using `gh` CLI
`cmd-golden-tests`	Set up or extend golden/snapshot tests: fixture design, Makefile targets, snapshot storage, diff workflow, and update protocol
`cmd-latest-msg`	Store or retrieve the latest agent message to `/tmp/agents/{agent}/`
`cmd-makefile`	Create or improve Makefiles with templates (python-uv, fastapi, nodejs, go, flutter)
`cmd-mermaid-render`	Render and display Mermaid diagrams inline in iTerm2 or Ghostty
`cmd-olshanskify`	Apply Olshansky's personal style to docs, code, blog posts, or presentations via templates
`cmd-plan-store`	Capture conversation plans, decisions, and action items into structured markdown in `plans/`
`cmd-pr-build-context`	Build high-signal PR context with diff analysis, risk assessment, and discussion questions
`cmd-pr-conflict-resolver`	Resolve merge conflicts with context-aware 3-tier classification and escalation
`cmd-pr-description`	Generate concise PR descriptions by analyzing the diff against a base branch
`cmd-pr-edgecase`	Review branch changes for test gaps, logic edge cases, and failure modes
`cmd-pr-follow-up`	Post-implementation reflection — surface missed work, simplifications, and idiomatic fixes
`cmd-pr-gh-comments`	Holistically triage PR comments with line-range context, adjacent sweeps, approval-gated resolution, and cmd-olshanskify updates for @olshansk feedback
`cmd-pr-review-prepare`	Prepare branch for code review by building context and identifying issues
`cmd-pr-scope-sweep`	Final pass to identify missed items, edge cases, and risks before closing scope

Help us improve

Find plugins for your project

Help us improve

agent-skills

Popularity

What's Inside

Help us improve

Health & Quality

Confidence

README

agent-skills

What is this?

Table of Contents

Quickstart

Available Skills

Similar Plugins

skill-optimizer

crystools-skills

skill-creator

agent-skills

claude-skills

toolkit

agent-skills

What is this?

Table of Contents

Quickstart

Available Skills