Explore skills

Generate a copy-paste-ready GPT prompt that produces a polished architecture or workflow diagram image, and optionally render the image directly via Codex CLI image generation. Trigger when the user wants to create, make, generate, draw, or visualize a diagram, architecture image, system workflow picture, or flowchart, or pastes a Mermaid diagram asking for a polished image.

Draft high-leverage technical/project articles that use a curiosity-gap title, SCQA introduction, story-first narrative, non-arrogant positioning, confidentiality-safe abstraction, and a reusable operating-system takeaway. Use when the user wants to turn a project, achievement, incident, or career story into a publishable long-form article or narrative draft.

Translate natural-language requests about modifying an AI coding agent, its skills, MCP tools, MCP servers, prompts, routing, tool descriptions, context loading, memory, portability, or other agentic behavior into the concrete mechanics of the target system. Use when a request is underspecified, phrased in human terms instead of runtime terms, or risks making the wrong change because the agent mus

Break down any concept, code, technology, or idea into a clear, layered explanation for adults who want the "aha moment" without the jargon. Produces a single self-contained HTML page with a concrete analogy, embedded CSS visual diagrams, layered detail, and curated links — then opens it in the browser. Use this skill whenever the user says "ELI5", "explain like I'm 5", "explain this simply", "bre

Use when comparing two versions of agent output to determine which is better, or when evaluating whether a skill produces higher quality results than baseline

Structured feedback session analyzing Claude Code usage over a configurable time window. Gathers evidence from git history, memory files, and project state, then delivers an honest 5/5/5 report (going well, not going well, what to improve) with specific evidence and trend tracking against previous sessions. Use when asked to "run feedback", "how am I doing", "feedback session", "usage review", "se

Customer discovery skill for founders. Use when user wants to design user interviews, build surveys, run Jobs-to-be-Done analysis, or synthesize customer research. Triggers on "customer discovery", "user interviews", "Mom Test", "JTBD", "jobs to be done", "customer research", "user research", "survey design", or /discovery commands.

End-of-context-window session transition that saves memory, writes a handoff doc, posts a GitHub progress comment, and instructs the user to /compact for a clean next session. Use when context usage approaches 80%, when remaining tokens are insufficient for the current phase's remaining work, or when user says "handover", "context is full", "save progress", "end session". Distinct from /handoff (l

Break a plan, spec, or PRD into independently-grabbable issues using tracer-bullet vertical slices with enforced AC templates, creation gates, and dual output to GitHub Issues + PLAN.md. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Batch domain availability checker via whois.com with Playwright browser automation. Handles anti-bot/CAPTCHA challenges by bringing browser to foreground for manual verification. Supports any TLD. Use when (1) checking if domains are available for registration, (2) batch-checking multiple domain candidates, (3) verifying domain availability before purchase, or (4) exporting domain check results to

Parse and execute commands given in Cantonese. Use when user gives instructions or requests actions in Cantonese. Translates Cantonese commands to executable actions.

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.