ospec-workflow

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

Diagnose and recover a derailed agent run. Trigger: an agent loops, drifts, loses context, repeatedly fails, or burns tokens without progress.

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

Engineering operating model for teams where AI agents generate a large share of implementation output.

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.

REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.

Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is.

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

Create pull requests with branch, validation, and publication checks. Trigger: creating, opening, or preparing PRs for review.

Trigger: caveman mode, talk like caveman, use caveman, less tokens, be brief, /caveman. Compress replies without losing technical accuracy.

Trigger: write a commit, commit message, generate commit, /commit, /caveman-commit. Generate terse Conventional Commits messages.

Trigger: /caveman:compress <filepath>, compress memory file. Compress prose files while preserving technical content and backups.

Trigger: /caveman-help, caveman help, what caveman commands, how do I use caveman. Show one-shot caveman command help.

Trigger: review this PR, code review, review the diff, /review, /caveman-review. Write terse actionable review comments.

Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.

Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.

Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.

This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.

Use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling.

Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.

Trigger: release notes, changelog entries, tag release. Generate homogeneous Spanish release notes based on project format.

Inspect, debug, optimize, or harden the ospec workflow harness. Trigger: auditing the plugin manifest, agent boundaries, hooks, skills, or token efficiency.

Design, implement, and refactor Ports & Adapters systems with clear domain boundaries, dependency inversion, and testable use-case orchestration across TypeScript, Java, Kotlin, and Go services.

Create GitHub issues with issue-first checks. Trigger: creating GitHub issues, bug reports, or feature requests.

Trigger: judgment day, dual review, adversarial review, juzgar. Run blind dual review, fix confirmed issues, then re-judge.

Read-only residual router for the Quality Review Gate when deterministic classification is ambiguous.

Read-only targeted correction validator for a bounded review lineage.

Efficiency review skill for the Quality Review Gate.

Evolution and maintainability review skill for the Quality Review Gate.

Readability review skill. Flag/Block/Require-evidence/Do-not-flag rules for the readability dimension of the 4R review gate.

Reliability review skill. Flag/Block/Require-evidence/Do-not-flag rules for the reliability dimension of the 4R review gate.

Resilience review skill. Flag/Block/Require-evidence/Do-not-flag rules for the resilience dimension of the 4R review gate.

Security and risk review skill. Flag/Block/Require-evidence/Do-not-flag rules for the risk dimension of the 4R review gate.

Runtime reliability review skill for the Quality Review Gate.

Trust and security review skill for the Quality Review Gate.

Implement SDD tasks from specs and design. Trigger: orchestrator launches apply for one or more change tasks.

Archive a completed SDD change by syncing delta specs. Trigger: orchestrator launches archive after implementation and verification.

Trigger: sdd baseline, brownfield baseline, seed specs, baseline.status pending or partial. Seed openspec/specs/ with baseline specs of existing behavior in resumable one-domain batches.

Reduce spec ambiguities before design. Trigger: orchestrator launches clarify after sdd-spec completes.

Create the SDD technical design and architecture approach. Trigger: orchestrator launches design for a change.

Generate repository wiki pages mapping architecture, specs, and status. Trigger: orchestrator launches sdd-document.

Explore SDD ideas before committing to a change. Trigger: orchestrator launches exploration or requirement clarification.

Trigger: sdd foundation, new project, empty workspace, project from scratch. Build project foundation docs and config.

Trigger: sdd init, iniciar sdd, openspec init. Initialize SDD context, testing capabilities, registry, and persistence.

Walk users through the SDD workflow on the real codebase. Trigger: orchestrator launches onboarding for the full SDD cycle.

Create an SDD change proposal with intent, scope, and approach. Trigger: orchestrator launches proposal work for a change.

Trigger: sdd reconcile, spec drift, reconcile domain, fold changes into spec, /sdd-reconcile. Fold already-shipped, undocumented code changes back into a baseline domain's spec as a diff-window-scoped retroactive delta.

Write SDD delta specs with requirements and scenarios. Trigger: orchestrator launches spec work for a change.

Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.