github is the fun stuff. day to day is complex critical systems, mostly involving AI.
Michael Ramos builds skills that help AI agents review and challenge code, including multi-model adversarial review, browser-based review and annotation of markdown, configs and URLs, and pre-task sharpening of requirements. His catalog also covers software design discipline, such as type system practices and migrating callers before deleting legacy APIs, along with tooling for reflecting on past work and tracing the rationale behind design decisions.
Plannotator
13 skills · 9,874 stars · Apache-2.0
Plannotator Reference for using Plannotator (its `plannotator` tool when you have one, otherwise the CLI): pl…
Plannotator Annotate Open Plannotator's annotation UI for a markdown file, plain-text config file (.yaml, .json, .toml…
Plannotator Annotate Open Plannotator's annotation UI for a file, folder, or URL, then address the returned annotations.
Plannotator Compound Analyze a user's Plannotator plan archive to extract denial patterns, feedback taxonomy, evolutio…
Plannotator Last Open Plannotator on the latest rendered assistant message and use the returned annotations to rev…
Plannotator Last Open Plannotator on the latest rendered assistant message and use the returned annotations to rev…
Plannotator Review Open Plannotator's browser-based code review UI and address the returned feedback.
Plannotator Review Open Plannotator's browser-based code review UI for the current worktree, another directory, or a…
Plannotator Setup Goal Turn an idea or objective into a goal package for /goal.
Plannotator Visual Explainer Generate self-contained HTML visualizations with Plannotator theming.
Release Plannotator Prepare and execute a Plannotator release — draft release notes with full contributor credit, bum…
Review Renovate Review Renovate bot PRs that update GitHub Actions dependencies.
Update Deps Audit and update npm/Bun dependencies with supply chain integrity checks — verifies maintainers,…
Pstack
21 skills · 3,732 stars · MIT
Architect Sketch types, signatures, and module structure before code, then stay in the loop while implement…
Arena Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the loser…
Automate Me Use for \"automate me\", \"create/update/refresh my -mode skill\", \"turn/capture my preferences…
Create Verification Skill Generate a project-local verification skill that drives your app the way a user does — any langua…
How Use for \"how does X work\", code walkthroughs before changing something, and placement / ownersh…
Interrogate Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"st…
Ketchup Catch the user up on what changed in this chat since their last message, in a few plain sentences…
Maintain Verification Skill Periodic pass that keeps a project's verification skill and feature map honest: parallel source r…
No Comments Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
Poteto Help Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle fo…
Poteto Mode poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simp…
Principle Migrate Callers Then Delete Legacy Apis Apply when introducing a new internal API while old callers still exist.
Principle Type System Discipline Apply when designing types, reviewing a function signature, or writing code in any statically-typ…
Recall Reconstruct your recent working context from your own chat history, live state, and the shared re…
Reflect Spawn three parallel review subagents over the active transcript, surface learnings, and route ea…
Setup Pstack Configure which models pstack uses per role and at what reasoning budget.
Sharpen Sharpen a task before starting: the expert approach, what the user is really after, and the right…
Show Me Your Work Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per…
Swarm Fan out N parallel workers, drain them, and return one report.
Typescript Best Practices TypeScript best practices.
Why Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems…
Bro
8 skills · 173 stars
Big Pics Little Words Explain the current subject in HTML with large visuals and minimal text while preserving key deta…
Clean Room Get an independent decision from a fresh agent that receives a neutral brief and none of the curr…
Facts Give a capable engineer a terse, jargon-free briefing on the critical facts and implications of a…
Ladder Render one lane of work as a vertical progress ladder in the terminal, done on top and todo below…
Readback Clearly restate a human's request so they can confirm alignment before work begins.
Recap Give a two- or three-sentence recap of the latest work in the current session.
Sharpen Sharpen a task before starting: the expert approach, what the user is really after, and the right…
Status Render the state of the work in flight as an ASCII status board in the terminal, instead of a sta…