backnotprop

Prepare and execute a Plannotator release — draft release notes with full contributor credit, bump versions across all package files, build in dependency order, and kick off the tag-driven release pipeline. Use this skill whenever the user mentions preparing…

Open Plannotator's annotation UI for a file, folder, or URL, then address the returned annotations.

Open Plannotator's annotation UI for a markdown file, HTML file, URL, or folder and then respond to the returned annotations.

Open Plannotator's annotation UI for a markdown file, plain-text config file (.yaml, .json, .toml, .ini, .csv, .log, …), HTML file, URL, or folder and then respond to the returned annotations.

Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.

Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.

Generate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explainers, architecture diagrams, data tables, slide decks, and any visual explanation of technical concepts. Plans and PR explainers follow Plannotator's…

Open Plannotator's browser-based code review UI for the current worktree or a pull request URL, then act on the feedback that comes back.

Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding…

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Four LLM reviewers challenge changes from independent angles.

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

Apply when work is repetitive or bulk: many similar edits, a check you'll rerun, a population to transform. Build the tool that amortizes it (codemod, script, generator) once you know the recipe, instead of grinding by hand.

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat,…

Capture or refresh durable product context in PRODUCT.md and document an existing visual system in DESIGN.md. Use when a user wants to initialize project context, explain a product to future agents, document the current design system, extract visual rules…

Make an existing frontend resilient to real data, failures, devices, languages, accessibility needs, and performance constraints. Use when preparing UI for production, testing edge cases, fixing fragile responsive behavior, handling…

Design, review, or improve first-use onboarding, activation, setup, empty states, contextual guidance, and feature discovery so users reach meaningful product value quickly. Use when users are confused at first run, abandon setup, miss an aha moment, need…

Refine an existing interface to shipping quality without quietly redesigning it. Use when a user asks to polish, clean up, tighten, clarify, align, simplify, improve hierarchy, spacing, typography, color, copy, interaction states, or overall finish in an…

Review an existing UI and produce prioritized, actionable findings across design, usability, cognitive load, accessibility, responsiveness, theming, performance, and implementation integrity. Use when asked for a UI critique, frontend audit, pre-release…

Clearly restate a human's request so they can confirm alignment before work begins. Use when the human explicitly invokes /readback or $readback after a long, dictated, unclear, or complex prompt; never invoke automatically.

Give a two- or three-sentence recap of the latest work in the current session. Use when the human explicitly invokes /recap or $recap and wants the current state, especially the last thing that happened; never invoke automatically.

Give a capable engineer a terse, jargon-free briefing on the critical facts and implications of an effort before it is built or after it is completed. Use when the human explicitly invokes $facts, and never otherwise; do not invoke this skill automatically.

Restate the last message in plain human language, with no jargon.

Use Orchestrator as a CLI-backed skill to delegate and coordinate work across Claude Code, Codex, Copilot, Grok, Pi, shell, and custom runtimes. Use when an agent should launch one or many sub-agents, choose runtimes or models, apply the user's orchestration…

Search your conversation history using ripgrep. Use when you need to find previous messages, file edits, tool calls, or decisions from earlier in the session.

Explicit-only router for ADR workflow commands. A dead simple engineering skill framework that works reliably.

Audits the CI/CD pipeline, repository, release process, automations, and dependency hygiene of an open-source software supply chain, then produces an elegant HTML report of findings and recommendations. Use this skill whenever the user asks to assess, audit,…

Write, update, validate, and package agent skills inside an existing or new repository. Use when the user asks to scaffold a skill in a repo, write a SKILL.md, add references/scripts/assets by hand, create project-local .agents/skills entries, optionally add…

Design, scaffold, audit, and upgrade Model Context Protocol servers. Use when the user asks to build or migrate an MCP server, adopt MCP 2026-07-28, add dual-era support, create an MCP integration, expose an API or data source through MCP…