Nivoset Skills

Plugin nivoset-skills in nivoset/skills. Commands read from the repo's manifest — today.

Skills (32)

• bdd

  Use when writing, reviewing, or refining Gherkin, BDD scenarios, acceptance criteria, feature files, behavior specs, examples, user journeys, business rules, edge cases, or Given/When/Then wording.

• blackboard-na

  Compact multilingual Blackboard refinement for ambiguous initiatives, epics, cross-domain product ideas, and disputed plans; dynamically coordinates evidence-backed specialist proposals until the proper authority can approve a stable outcome.

• blackboard

  Use for any problem, topic, initiative, decision, or investigation that benefits from several specialist perspectives working over a shared board — discovery and research ("figure out why X", "explore options for Y"), decisions and tradeoffs ("should we A or B"), product or business planning, and im

• codelens-code-review

  Use when a codebase, branch, or changed area needs a harsh review for defect risk, maintainability failure, hidden coupling, weak tests, or likely under-reviewed AI-assisted code.

• deck-vette

  Use when reviewing a presentation for factuality, grammar, narrative flow, audience fit, pacing, notes, accessibility, visual consistency, or browser reliability through narrow independent review lanes.

• demo

  Use when a code change or ticket needs a deterministic browser demonstration with a readable journey script, video evidence, and traceable artifacts.

• feature-tdd-planning

  Use when a repository needs a `.feature-tdd` planning folder, feature-driven TDD planning artifacts, scenario grouping, execution ordering, or traceability documentation.

• handler

  Use when taking a bug or feature ticket through delegated investigation, behavior testing, implementation, browser evidence, and pull-request validation.

• judge-prompt

  Assess, test, or judge an existing prompt, system instruction, agent or skill definition, tool instruction, or prompt-based workflow against its intended behavior. Use when the user asks whether it is clear, safe, reliable, runtime-compatible, or ready to use, including when adaptive Blackboard-styl

• keep-or-cut

  Use when editing or revising a skill (SKILL.md), prompt, rule, system message, or instruction to trim bloat.

• level-1-thinking

  Use when making or reviewing decisions about local AI decision systems, typed-decision runtimes, hosted/local boundaries, model routing, confidence, or operational risk.

• linear-cli

  Use when Codex needs to inspect, create, update, comment on, or otherwise manage Linear issues, teams, projects, milestones, initiatives, documents, labels, or Linear GraphQL data through schpet/linear-cli from the command line. Trigger for Linear CLI workflows, agent-friendly Linear issue queries,

• naming

  Use when writing, reviewing, editing, or renaming tests, variables, functions, classes, types, components, scenarios, tickets, branches, or other identifiers where names may be vague, implementation-focused, misleading, or hard to understand.

• objective-check

  Use when auditing an Epic, Feature, parent ticket, or ticket subtree for objective coverage, dependency safety, acceptance criteria, test evidence, and readiness before implementation or TDD.

• plan-evidence-review

  Use when a delegated reviewer has a bounded factual, citation or verification claim with material evidence uncertainty.

• plan-intent-review

  Use when a delegated reviewer has a bounded draft commitment whose intent fit or decision state is materially uncertain.

• planning-codebase-researcher

  Investigate the existing codebase for behavior, reuse paths, dependencies, risks, and test coverage that matter to planning and ticket design.

• planning-decomposer

  Split a scoped outcome into independently testable tickets with clear dependencies, useful code references, and plain-English acceptance tests.

• planning-orchestrator

  Use when planning a feature, refactor, migration, integration, large repair, or codebase-researched breakdown into developer-consumable tickets.

• planning

  Use when asked to plan, scope, decompose, or design a ticket or requested change against a local repository.

• pr-bug-bash

  Use when Codex needs to run an intense evidence-first pull request review against dev, develop, or a named target branch; gather requirements from GitHub PR text, Linear issues, branch names, tickets, and code; use vette risk lanes to find defects; create and verify temporary TDD-style failing tests

• pr-review

  Use when reviewing the active or named branch against a target branch, drafting GitHub review comments, verifying findings locally, or coordinating focused reviewer subagents.

• product-intake

  Use when a user needs to capture a new product idea, document an existing product, or turn product evidence and interviews into reviewable capability and feature drafts.

• prompt-review

  Use when reviewing prompts, agent instructions, skills, policies, or workflow guidance for contradictions, missing conditions, hidden assumptions, or absolute language such as always, never, must, only, or cannot. Also use when reviewing a SKILL.md file, agent-skill package, or tool/function definit

• questline

  Use when building, grooming, or refining an Epic, Feature, parent ticket, or ticket tree before implementation so work can be manually reviewed, promoted from triage, and later executed with TDD.

• tdd-basic

  Use for software development feature or bugfix work that should follow a strict red, green, refactor loop with isolated subagents, verified failing tests, minimal implementation, review gates, commits, pull requests, and ticket observations.

• tdd

  Use when implementing software features or bug fixes with behavior tests, acceptance criteria, or changing requirements that need traceable test coverage.

• ticket-building-system

  Use when creating, editing, or triaging tracker-neutral tickets, issues, bugs, spikes, epics, features, or implementation tasks.

• ticket-master

  Use when a parent ticket already has child tickets and an orchestration agent must sequence implementation PRs across ticket systems, branches, blockers, and delegated agents.

• ui-vette

  Use when a rendered UI must be visually compared with supplied references through four focused review roles covering design fidelity, frontend implementation, QA edge cases, and accessibility. Requires a reachable implementation URL and at least one usable visual reference; produces a read-only, evi

• vette

  Use when reviewing an implementation plan, codebase, feature area, or pull request for likely defects, missed requirements, weak tests, security gaps, data risks, UX mismatches, or reliability issues before or after implementation.

• workshop

  Use when an early product idea needs collaborative product discovery, architecture and contract planning, or a linked, reviewable set of feature documents before implementation.

Similar plugins