Results for “spec-generation”

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

Designing and reviewing APIs: OpenAPI spec generation, versioning strategy, breaking change detection, REST/GraphQL best practices. Use for API design or OpenAPI specs.

Analyzes an app from video, screenshots, or description, then generates implementation stories in dependency order.

Reads a project spec and writes one detailed plan file per SRS section, producing a complete blueprint for SRS generation.

封装阶段3的Copy Spec为可批量执行的提示词包，生成JSONL请求并调用APIMart API出图。

Guides a structured requirements workflow from topic intake through brainstorming, spec and plan writing, user review, SRS generation, validation, and improvement reporting.

Guides a structured requirements pipeline from topic intake through brainstorming, spec writing, planning, user review, SRS generation, validation, and improvement reporting.

Augment the standard exec lifecycle with monorepo detection, lane-spec generation, guard validation, and package-scoped dispatch

Guides a structured requirements pipeline from topic intake through brainstorming, spec and plan writing, user review, SRS generation, validation, and improvement reporting.

Runs a structured clarifying interview for new project requests before building, then outputs a fully specified prompt.md for a fresh agent session to execute.

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.

Transforms vague UI ideas into polished, Stitch-optimized prompts by enhancing specificity, adding UI/UX keywords, injecting design system context, and structuring output for better generation results.

Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent generation.

Builds and governs design systems with a three-layer token architecture, component specs, and design-to-code handoff, including slide generation.

Write a rigorous, decision-grade experiment spec — falsifiable hypothesis, primary metric, guardrails, randomisation unit, exposure definition, method (A/B, holdout, switchback, quasi-experiment, MAB), MDE/duration plan, peek policy, validity threats, and pre-committed decision rule. Platform-agnostic. Load when the user has a candidate experiment and needs to spec it before launch, or says "spec this experiment", "write the test plan", "design this A/B test", "what's the hypothesis", "how big a sample do we need", "how long should we run this", "define the metrics for this test", or when the experimentation orchestrator routes here.

Creates structured specifications before writing code to clarify requirements, surface assumptions, and define success criteria, reducing rework and miscommunication.

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.

Create a committed per-feature spec under `docs/specs/YYYY-MM-DD-<slug>/{spec,tasks}.md` with frontmatter (status, created, owner, pr, tags). Promotes an ephemeral `.claude/plans/<name>.md` into a persistent, searchable artifact. Use when starting a feature that's larger than a one-shot PR.

Create a structured specification file for a solution component, optimized for Generative AI consumption.

Generate or edit raster images such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts for use in projects.

Identify underspecified areas in the current feature spec by asking targeted clarification questions and encoding answers back into the spec.

Learn best practices for writing effective AI video generation prompts, covering shot types, camera movements, lighting, style keywords, and model-specific tips for Veo, Seedance, Wan, Grok, and others.

Distill any intent input into the SPEC kernel + companions — the canonical, preservation-validated machine contract for downstream work. Use when the user says "create a spec", "distill this into a spec", "validate this spec", "update the spec", or "break this into stories".

Spec Craft

Generates spoken audio clips from text for narration, voiceovers, IVR prompts, and accessibility reads, with support for single clips and batch processing.

Assembles branded, export-ready proposals from brief, research, and pricing artifacts — type-adaptive for pitch, RFP, or scoping. Use when the user asks to generate a proposal, draft a pitch/RFP response/scoping doc, export final-proposal PDF/DOCX/HTML, revise a proposal draft, or add visuals to a proposal. Triggers: 'generate the proposal', 'draft the pitch', 'write the RFP response', 'export proposal to PDF', 'regenerate proposal', 'proposal from Acme brief'.

Agente final do time Code New Project Agents do Reversa. Decompõe um PRD em componentes lógicos e gera specs SDD (Spec-Driven Development) por componente, com score automático de qualidade. Use quando o usuário digitar "/reversa-spec-sdd", "reversa-spec-sdd" ou quando invocado pelo orquestrador `/reversa-new`. Lê `_reversa_sdd/prd.md` e produz `_reversa_sdd/sdd/<componente>.md`. Ao concluir, faz handoff para `/reversa-forward`. Também pode ser usado avulso para avaliar uma spec existente (modo de avaliação) ou para gerar spec única a partir de qualquer entrada que o usuário forneça. Entrega: arquivos `.md` no formato SDD com score de qualidade (0 a 100) e análise de gaps.

Use when the user asks to write specs before code, define acceptance criteria, plan features before implementation, generate tests from specifications, or follow spec-first development practices.

Escribe especificaciones técnicas en formato Given/When/Then, describiendo qué debe hacer el sistema y no cómo, con escenarios de caso feliz, bordes y errores.

Generate, predict, and embed protein sequences and structures using ESM3, ESMC, and ESMFold2 with local or cloud inference.