runwield-skills

Plugin runwield-skills in gandazgul/runwield. Commands read from the repo's manifest — 23 days ago.

Skills (20)

• runwield-workspace-journey-mapping

  Use when mapping RunWield Workspace personas, journeys, UX gaps, polish priorities, or beta-user test

• guide

  Use when the user asks a question about this repository rather than asking for a change — how something works, why it was built, what is implemented, what changed, what a term means, or which command to run. Answers from durable artifacts with citations, and preserves an explanation as a Markdown do

• ideator

  Use when the user brings a vague idea, a product problem, or a technology choice and wants it stress-tested before any code is written. Runs a Socratic interview, researches external facts, keeps proposed domain language out of the current glossary, and synthesizes a PRD only when asked. Do not use

• review

  Use when the user asks to review a pull request, a merge request, a branch, the changes since a commit or tag, or uncommitted work. Reviews along three axes — Standards (does it follow this project's documented conventions?), Spec (does it do what was asked?), and Tests (would a plausible wrong impl

• agent-browser-use

  Use this skill when building, fixing, reviewing, or debugging web UI, UX, or frontend behavior and you need to exercise the app in a real browser with agent-browser. Use it to reproduce user-reported browser bugs, inspect accessibility snapshots, interact with forms and controls, capture screenshots

• codebase-design

  Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

• diagnose

  Use this skill when the user reports a bug, says something is broken, throwing errors, or failing — even if they don't say "diagnose" or "debug". Also use for performance regressions, when the user says something is slow, degraded, or slower than before. Follows a feedback-loop → reproduce + minimis

• documentation

  Use this skill when the user asks you to write, update, or fix project documentation — READMEs, API docs, user guides, ADRs, or other Markdown docs. Also use when code changes need user-facing docs updates. Only write Markdown files; do not use for implementation, planning or test work.

• front-end-framework-use

  Convention-first frontend engineering for browser UI work. Use when implementing, fixing, debugging, or reviewing frontend JavaScript/HTML/CSS across frameworks; when UX behavior, visual design, design-system fit, framework conventions, or real-browser evidence matter. Don't use for TUI work.

• improve-codebase-architecture

  Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one the user picks. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make the codebase more testable and AI-navigabl

• prompt-writing

  Use when writing or tightening prompts for AI systems — system prompts, agent instructions, skills, or any LLM prompt. Triggers on user mentioning prompt writing, prompt improvement, or making instructions tighter.

• prototype

  Use this skill when the user wants to prototype an idea, sanity-check a data model or state machine, mock up a UI, explore design options, or try several approaches before committing — even if they just say "let me play with it" or "try a few designs". Creates a runnable throwable that lets the user

• research

  Investigate a question against high-trust primary sources and capture the findings as a cited Markdown note. Use when the user wants durable research, docs/API facts gathered, ecosystem comparisons, or reading legwork saved for Ideator, Planner, Architect, or future sessions.

• resolving-merge-conflicts

  Use when you need to resolve an in-progress git merge/rebase conflict.

• runwield

  Use when the user asks how RunWield or wld works, how to do a task in RunWield, why RunWield routed, planned, validated, reviewed, or recovered work a certain way, or how to configure RunWield/wld.

• show-me

  Explain the current topic visually — diagrams, code-shape sketches, or a focused HTML artifact.

• tdd

  Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

• wizard

  Generate an interactive terminal wizard for manual steps an agent cannot do: external account setup, credentials, CI secrets, dashboard configuration, one-off migrations, or cutovers. Use only when a human must act outside the repo.

• write-a-skill

  Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

• write-tests

  Use this skill to write, update, or repair automated tests for existing code. Use when the task involves adding test coverage, fixing flaky tests, or creating regression tests for bugs. Language/framework-agnostic. For test-driven development, use the tdd skill. For general QA and behavioral verific