olshansk
49 verified skills326 total stars
cmd-skills-review
Audit personal skills for redundancy, verbosity, weak triggers, and overlap. Runs a Claude→Codex review loop, presents per-item approval checkboxes, then applies approved edits and updates README and agent metadata. Use when asked to "review my skills", "audit my skills", "revisit my skills", or "clean up my skills". Accepts an optional skill name to scope the review to a single skill.
development7
cmd-write-proofread
Proofread posts before publishing for spelling, grammar, repetition, logic, weak arguments, broken links, and optionally reformat for skimmability or shape the writing vibe toward a known author's style
development7
cmd-review-chain-halt
Review protocol code for chain halt risks, non-determinism, and onchain behavior bugs
development7
cmd-review-rfc
Review RFCs for problem clarity, compliance, security, and performance using SCQA framework
development7
makefile
Create or improve Makefiles with minimal complexity. Templates available: base, python-uv, python-fastapi, postgres, nodejs, go, chrome-extension, flutter, electron, static-site.
tools7
cmd-pr-build-context
Build high-signal PR context for review with diff analysis, risk assessment, and discussion questions
development7
cmd-pr-description
Generate a PR title and description, then commit, create/update the PR on approval
tools7
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/.
development7
cmd-pr-review-prepare
Prepare branch for code review by building context, identifying issues, and suggesting improvements
development7
cmd-codex-review-plan
Get a second opinion on the current plan from Codex (codex exec headless mode) before leaving plan mode. Pipes the plan to codex, captures critique and gap analysis, then proposes a revised plan with an explicit changelog of what changed and what was rejected. Triggers on "/cmd-codex-review-plan", "review plan with codex", "ask codex about this plan", or before approving auto mode on an exit-plan prompt.
development7
cmd-pr-conflict-resolver
Resolve merge conflicts systematically with context-aware 3-tier classification and escalation protocol
tools7
cmd-pr-edgecase
Review branch changes for test gaps, logic edge cases, failure modes, and integration risks
testing7
cmd-proofread
Proofread posts before publishing for spelling, grammar, repetition, logic, weak arguments, broken links, and optionally reformat for skimmability or shape the writing vibe toward a known author's style
development7
cmd-what
Catch the user up on what the agent has been doing in the current session with 3-5 ultra-tight bullet points. Use when the user invokes /cmd-what, asks "what are you doing", "what did you do", "catch me up", "status", "where are we", or otherwise needs a fast situational summary of in-flight agent work.
data-ai7
session-commit
Capture learnings from the current coding session and update AGENTS.md. Use when the user asks to close the loop, run session-commit, record best practices, or update agent instructions based on recent work.
data-ai7
cmd-pr-sculpt-code
Reshape code for readability, naming, structure, TODOs, and reduced surface area across any language
development7
cmd-golden-tests
Set up or extend golden/snapshot tests for a project. Covers fixture design, Makefile targets, snapshot storage, diff workflow, and update protocol.
development7
cmd-done-check
Ask the agent whether it finished everything or has more to do — a lightweight completeness gate for the end of any task
testing7
cmd-interview-prep
Mock-interview Daniel for Staff/Senior-Staff/Principal loops at Uber, Snowflake, and Anthropic. Coding (Python) and system design only. Persona = skeptical staff engineer. Loads context from /Users/olshansky/workspace/interviews/, runs sessions, and on "let's close the loop" persists weaknesses to gaps.md and per-problem review.md.
development7
cmd-code-what
Catch the user up on what the agent has been doing in the current session with 3-5 ultra-tight bullet points. Use when the user invokes /cmd-what, asks "what are you doing", "what did you do", "catch me up", "status", "where are we", or otherwise needs a fast situational summary of in-flight agent work.
development7
cmd-agent-persona-set
Prime the agent with a behavioral persona for the conversation
data-ai7
cmd-docs-idiot-proof
Simplify documentation for clarity and scannability with approval-gated edits
documentation7
cmd-mermaid-render
Render and display Mermaid diagrams inline in iTerm2 or Ghostty. Use when creating, editing, or iterating on mermaid diagrams. Triggers on mermaid diagram work — flowcharts, sequence, state, class, ER, and XY charts.
data-ai7
cmd-makefile
Create or improve Makefiles with minimal complexity. Templates available: base, python-uv, python-fastapi, postgres, nodejs, go, chrome-extension, flutter, electron, static-site.
tools7
cmd-pr-scope-sweep
Final pass to identify missed items, edge cases, and risks before considering a scope done
tools7
cmd-skills-dashboard
Scrape skills.sh and generate an interactive HTML dashboard showing skill distribution by publisher, installs, and categories. Rerun anytime to get fresh data.
development7
cmd-session-commit
Capture learnings from the current coding session and update AGENTS.md. Use when the user asks to close the loop, run session-commit, record best practices, or update agent instructions based on recent work.
data-ai7
cmd-codex-review-unstaged
Get a second opinion on what Claude just implemented from Codex (codex exec headless mode). Pipes Claude's summary plus the working-tree diff to codex, asks codex to leverage cmd-pr-follow-up and cmd-pr-edgecase methodology to surface bugs, test gaps, edge cases, and simplification opportunities, then synthesizes a prioritized iteration plan from the feedback. Triggers on "/cmd-codex-review-unstaged", "review my changes with codex", "have codex review what I just did", or after a non-trivial implementation pass before commit.
development7
cmd-plan-store
Capture the current conversation's plan, decisions, and action items into a structured markdown file in the project's plans/ directory. Triggers on "store this plan", "save this plan for later", "document this for later", "write up what we discussed", "create a plan file", or "/cmd-plan-store".
testing7
cmd-pr-follow-up
Self-review after implementation — surface missed work, simplification opportunities, and idiomatic improvements
tools7
cmd-pr-test-plan
Generate manual test plans for PR changes — focused on hands-on verification a developer would do, not unit-test edge cases
development7
cmd-skills-local-repo
Scaffold cross-tool repo-local skills and agent instructions with canonical source in .agents/ and symlinks for Claude, Codex, Gemini, and Codex-home
tools7
cmd-rfc-review
Review RFCs for problem clarity, compliance, security, and performance using SCQA framework
development6
cmd-chain-halt-code-reviewer
Review protocol code for chain halt risks, non-determinism, and onchain behavior bugs
development6
cmd-productionize
Transform applications into production-ready deployments with systematic analysis, improvement, and framework-specific optimization
development6
cmd-email-md
Convert markdown to email-safe HTML with inline styles and cross-client compatibility. Use when writing newsletters, transactional emails, or any HTML email from markdown source.
tools6
cmd-gh-issue
Create structured GitHub issues from conversation context using gh CLI
tools6
cmd-idiot-proof-docs
Simplify documentation for clarity and scannability with approval-gated edits
documentation6
cmd-pr-gh-comments
Holistically triage and resolve GitHub PR review comments — gather comments with full line ranges, study surrounding code context (TODOs, docstrings, related logic), hunt for adjacent improvements via rg, execute an approval-gated plan, optionally refine AGENTS.md style rules, and propose cmd-olshanskify template updates when feedback comes from @olshansk
development6
skills-dashboard
Scrape skills.sh and generate an interactive HTML dashboard showing skill distribution by publisher, installs, and categories. Rerun anytime to get fresh data.
development6
cmd-scope-sweep
Final pass to identify missed items, edge cases, and risks before considering a scope done
tools6
cmd-sculpt-code
Reshape code for readability, naming, structure, TODOs, and reduced surface area across any language
development6
mermaid-render
Render and display Mermaid diagrams inline in iTerm2 or Ghostty. Use when creating, editing, or iterating on mermaid diagrams. Triggers on mermaid diagram work — flowcharts, sequence, state, class, ER, and XY charts.
data-ai6
cmd-clean-code
Improve code readability without altering functionality using idiomatic best practices
development6
cmd-store-plan
Capture the current conversation's plan, decisions, and action items into a structured markdown file in the project's plans/ directory. Triggers on "store this plan", "save this plan for later", "document this for later", "write up what we discussed", "create a plan file", or "/cmd-store-plan".
testing6
cmd-follow-up
Self-review after implementation — surface missed work, simplification opportunities, and idiomatic improvements
tools6
cmd-latest-msg
Store or retrieve the latest agent message to /tmp/agents/{agent}/
testing6
cmd-local-repo-skills
Scaffold cross-tool repo-local skills and agent instructions with canonical source in .agents/ and symlinks for Claude, Codex, Gemini, and Codex-home
tools6
cmd-persona
Prime the agent with a behavioral persona for the conversation
data-ai6