agents-extras

Plugin agents-extras from marketplace agents-template in toderian/project_template. Commands read from the repo's manifest — 2 days ago.

Skills (18)

• design-an-interface

  Generate multiple radically different interface designs for a module using parallel sub-agents when available. Use when the user wants to design an API, explore interface options, compare module shapes, or mentions \"design it twice\".

• domain-modeling

  Build and sharpen the project's domain model: challenge terms against the glossary, stress-test with edge-case scenarios, and update docs/resources/CONTEXT.md and ADRs inline. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording an ADR.

• doubt-driven-development

  Adversarial review for a non-trivial implementation decision before it stands. Use when the user asks to \"doubt\" or stress-test a decision, when correctness matters more than speed, or when the choice crosses module boundaries, asserts something hard to verify, or is hard to reverse.

• frontend-design

  Create distinctive, production-grade frontend interfaces with high design quality and rendered verification. Use when the user asks to build web components, pages, apps, dashboards, games, or redesign/restyle UI. Avoids generic AI aesthetics and verifies responsive, accessible output.

• github-triage

  Triage GitHub issues through a label-based state machine with interactive grilling sessions. Use when user wants to triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

• improve-codebase-architecture

  Explore a codebase for architectural improvement, focusing on testability by deepening shallow modules. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.

• migration-safety

  Safety review and generation guidance for reversible database schema migrations: table-rewrite locks, unsafe NOT NULL changes, missing indexes, irreversible drops, backfills, and zero-downtime DDL. Use when writing or reviewing a schema migration for PostgreSQL, MySQL, SQLite, Liquibase, or Flyway.

• prd-to-issues

  Break a PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices. Use when the user wants to convert a PRD to issues, create implementation tickets, or break down a PRD into work items.

• qa

  Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when the user wants to report bugs, do QA, file issues conversationally, or mentions \"QA session\".

• request-refactor-plan

  Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when the user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.

• setup-pre-commit

  Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when the user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

• to-questionnaire

  Turn a decision you cannot answer alone into a questionnaire for the one person who can.

• triage-issue

  Triage a bug or issue through a two-role state machine (category + state), exploring the codebase for root cause, and produce a `ready-for-agent` GitHub issue with a TDD-based fix plan. Use when the user wants to \"triage\" a bug, investigate an issue, file an issue, or plan a fix.

• ui-design-review

  Review rendered frontend UI for design quality, accessibility, responsiveness, interaction states, and implementation polish. Use when the user asks for UI review, design critique, visual QA, polish pass, responsive audit, accessibility check, or post-build frontend review.

• write-a-prd

  Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when the user wants to write a PRD, create a product requirements document, or plan a new feature.

• write-a-skill

  Create or edit a skill in this plugin marketplace: pick the plugin, write SKILL.md and its bundled resources, validate. Use when the user wants to create, write, or build a new skill, or restructure an existing one.

• writing-for-agents

  How to write any document an agent consumes: skills, AGENTS.md/CLAUDE.md, and docs reached by a pointer. Covers context pointers, context vs cognitive load, progressive disclosure, completion criteria, leading words, and pruning. Use when creating or editing a skill, editing AGENTS.md or CLAUDE.md,

• zoom-out

  Step up a layer of abstraction and produce a map of the relevant modules and callers, using the project's domain glossary. Use when starting work in an unfamiliar area of the codebase, when broader context is needed, or when a narrow trace has lost the bigger picture.

Similar plugins