Loading...
Loading...
Found 13 Skills
Converge vague requirements into a goal contract (scope / non-goals / success criteria / verification / stop conditions) that another AI can execute autonomously and be accepted. This skill only writes goal contracts, **never executes tasks for users**. Hard trigger condition: This goal is to be handed over to others for execution — subagent, Codex, another AI session, or another person. It is used to write goals, optimize goals, revise handoff prompts, or turn requests like "finish today, optimize as much as possible, help me research and execute" into task contracts that the executor won't guess randomly or overstep boundaries. Not applicable to: internal team requirement management and version breakdown (use issue-pool — it produces tasks for humans to start working on, not contracts for AI), interface design exploration (use design-exploration), PRD/acceptance criteria/test case documents (use prd-test-writer), framework planning and version roadmaps (use issue-pool), and situations where the user actually wants you to **do the task directly** — just do it directly instead of using this skill to turn the task into a document.
Render DNA codes to Pencil .pen frames. Does ONE thing well. Input: DNA code + component type (hero, card, form, etc.) Output: .pen frame ID + screenshot Use when: design-exploration or other orchestrators need to render visual proposals using Pencil MCP backend.
Export .pen design to React/Tailwind code. Does ONE thing well. Input: .pen frame ID or file path Output: React component code + Tailwind config Use when: design-exploration or user needs implementation code from a finalized Pencil design.
Integrated Collaboration for PRD + Executable Test Cases (Development Paradigm v2 Definition Section). Input is a finalized split task/requirement; outputs 4 files: PRD-MD and Test Case-MD (fact sources for AI) + two template-based review HTMLs (for human review, strictly 1:1 with MD). Co-write and iterate with users: autonomously read code after understanding requirements before writing; story-driven + phased single-point confirmation; UI stories include ASCII wireframes + Mermaid capabilities. Triggers: organizing/writing/refining PRDs, requirement documents, user stories, acceptance criteria, test cases, test benchmarks, test plans. Not applicable to: ambiguous requirements not split into tasks (use issue-pool first), unexplored interface solutions (use design-exploration first, whose output requirement-summary.md is exactly the input for this skill), small requirements for modifying an already launched feature (use req-change-workflow), long HTML articles/retrospectives/reports for human reading (use readable-output), project-level framework plans and version roadmaps (use issue-pool), writing code or running tests (this skill only produces documents, does not implement or execute cases).
Generate long HTML articles for human reading — organize existing materials, experiences, and data clearly before writing. Each time it is triggered, first use AskUserQuestion to clarify 4 key parameters in one go: [Who is it for / What will readers gain after reading / Depth level / Style + Focus], then output according to the 6-stage framework. **The only output format is HTML** — this skill should not be used if the user requests markdown or direct chat responses. It is triggered when the user says phrases like "do a retrospective", "summarize this", "compile into HTML", "create a tutorial/study guide", "explain X clearly", etc., which require structured reading content of over 500 words. It is not applicable for: project plan reports/framework plans/version roadmaps (use issue-pool, which has built-in md2html), PRDs/requirements documents/test cases (use prd-test-writer), interface design drafts (use design-exploration), naming (use product-naming), writing code/fixing bugs/modifying files, or questions that can be answered in one or two sentences.
Unified brand discovery that outputs brand.yaml. Merges brand-builder (voice/audience) + design-exploration (visual direction) into one flow. Run once per project to establish brand identity.
Systematic Learning Material Generator. Given a new field/technology/concept, AI conducts independent research, builds a knowledge system, and generates HTML learning materials (including framework/cases/engineering/controversies + blind spots). Triggered when the user says "I want to learn X / Help me systematically break down X / I want to master the field of X / Help me organize the full picture of X / Conduct in-depth research on X and explain it systematically / Master X thoroughly". Not applicable for "Is X feasible / Why Y" (use long-research), "What interesting cases are there in X" (use case-radar for scattered cases), "Organize these materials into HTML" (use readable-output to process existing materials), article writing (use writing-assistant), design drafts (use design-exploration).
Autonomous execution workflow for complex long-running tasks. This applies to scenarios where users have a complex or vague task (e.g., "Help me figure out X / Help me evaluate Y / Help me organize this pile of stuff / Help me compare N solutions / Help me run a research"), and expect the AI to decompose, execute, and verify the task on its own, only reaching out to the user at critical moments. It enables unattended autonomous execution for 1-2 hours through the process of "Task Confirmation → Task Queue → Batch Execution → Periodic Queue Verification → Triggered Reporting". It is triggered when users say phrases like "Help me figure out / Evaluate / Organize / Compare / Run a research / Run it on your own don't bother me / Long-running task / Run autonomously". **Not applicable to**: UI design (use design-exploration), to-do priority judgment (use priority-judge), article writing (use writing-assistant), backlog management (use backlog-manager), vision exploration (use vision-exploration), naming (use product-naming), implementation coding tasks with clear specs (code directly).
Build multiple genuinely different versions of a UI piece you describe, rendered behind a visual picker so you can flip through them live and promote the one that feels right. Only runs when explicitly invoked; it does not trigger on its own.
Socratic discovery and design exploration before planning. Activates when starting non-trivial work — asks clarifying questions, explores alternatives and tradeoffs, produces a design document for approval. Pulls context from Linear issue description, linked docs, and existing CLAUDE.md learnings. Simple bugs and fixes skip this automatically.
Design exploration with parallel agents. Use when brainstorming ideas, exploring solutions, or comparing alternatives.
Collaborative design exploration for new features and architecture decisions. Triggers: 'brainstorm', 'ideate', 'explore options', or /ideate. Presents 2-3 approaches with trade-offs, documents chosen approach. Do NOT use for implementation planning or code review. Requires no existing design document — use /plan if one exists.