liminal-ai

Write complete, traceable Epics using Liminal Spec methodology. Covers User Profile, Flows, Acceptance Criteria, Test Conditions, Data Contracts, and Story Breakdown.

Publish a detailed epic as two handoff-ready artifacts: a PO-friendly business epic with grouped ACs and a developer story file with full AC/TC detail and Jira section markers.

Explore product direction and produce a PRD before feature scoping. Use when requirements are unclear, scope spans multiple features, or stakeholder alignment is needed.

Orchestrate story-by-story implementation with agent teams. Manages teammates, routes verification, and makes judgment calls across the full implementation cycle.

Orchestrate the full Liminal Spec pipeline with agent teams. Manages drafters and verifiers from orientation through technically enriched stories.

Transform a Feature Spec into implementable Tech Design with architecture, interfaces, and test mapping. Validates the spec as downstream consumer.

Write a single functional story with epic-quality rigor. Story-sized epic for focused changes that don't warrant the full pipeline.

Perform inline technical design and embed results into a functional story. Story-sized tech design + enrichment with codebase analysis, architecture, interfaces, and test mapping.

Produce a research-grounded Technical Architecture document that settles foundational technical decisions across 3-8 epics. Companion to the PRD — establishes the technical world that downstream tech designs inherit.

Write complete, traceable Epics using Liminal Spec methodology. Covers User Profile, Flows, Acceptance Criteria, Test Conditions, Data Contracts, and Story Breakdown.

Produce compressed proto-epics across 3-8 features with scenario-driven acceptance criteria. Each feature section seeds automated epic expansion through the full Liminal Spec pipeline.

Publish a detailed epic as individual story files with full AC/TC detail and Jira section markers, and optionally a PO-friendly business epic with grouped ACs.

Orchestrate story-by-story implementation with Claude Code agent teams. Sonnet implements with TDD methodology, Opus and Sonnet verify in fresh sessions with evidence-bound review. No external CLI required.

Orchestrate story-by-story implementation with agent teams and an external CLI model (Codex or Copilot). Opus teammates manage external model subagents for implementation and verification.

Orchestrate the full Liminal Spec pipeline with agent teams and external CLI verification. Procedural learning architect manages drafters and verifiers from orientation through published stories.

Transform a Feature Spec into implementable Tech Design with architecture, interfaces, and test mapping. Validates the spec as downstream consumer.

Run Claude Code CLI as a subagent for code tasks, review, validation, and implementation. Supports sync, async, parallel, and resume workflows with tiered output management.

Run OpenAI Codex CLI as a subagent for code tasks, review, validation, and implementation. Supports sync, async, parallel, and resume workflows with tiered output management.

Run GitHub Copilot CLI as a subagent for code tasks, validation, review, and implementation. Works with enterprise Copilot subscriptions. Multi-model access including Claude, GPT, and Gemini.

Alpha and unstable. Cursor CLI currently shows anomalies in subagent workflows, so this skill is not recommended for normal use.

Test skill containing EICAR test file for malware detection

Analyzes data files

Formats text according to specified style guidelines. A clean example skill with no security issues.

Skill with script files

Builds reusable Convex components with isolated tables and app-facing APIs. Use for new components, reusable backend modules, integrations, or component boundary work.

Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.

Orchestrate implementation and verification subagents across the subagent CLIs (cursor/codex/claude) and built-in forks. Invoke ONLY when the user explicitly requests subagent orchestration — do not self-trigger.

Build a comprehensive current-state developer onboarding wiki for an existing codebase, using existing PRD/architecture docs, build summaries, retrospectives, and the live code itself. Use this skill whenever the user wants to produce documentation that helps developers and onboarding agents quickly understand a system's architecture, design, conventions, and code geography — not how the system was built but how it currently works. Triggers include "build a wiki", "developer onboarding documentation", "current-state docs", "document this codebase", "wiki for our developers and agents", and similar. Strongly prefer this skill over generic markdown-writing approaches when the audience includes both human developers and downstream agents that will consume condensed extracts of the wiki.

Orchestrate implementation as a live caller harness with progressive-disclosure docs, a durable team-impl log, and the lbuild-impl runtime.

Run OpenAI Codex CLI as a subagent for code tasks, review, validation, and implementation. Supports sync, async, parallel, and resume workflows with tiered output management.

Run GitHub Copilot CLI as a subagent for code tasks, validation, review, and implementation. Works with enterprise Copilot subscriptions. Multi-model access including Claude, GPT, and Gemini.