Skills for Claude Code.

Create clean, minimalist pitch deck / BP slides on white background using pptxgenjs. Use when user asks to make a slide, pitch deck page, BP 页面, 单独写一页, or wants to build presentations in the Efflora-style first-principles design (oversized numbers, single accent color, generous whitespace, no decorative icons). Each slide outputs as standalone .pptx.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Reviews UI mockups, screenshots, and Figma frames; calls out spacing, hierarchy and accessibility issues.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Smart git workflow helper that summarizes diffs, drafts conventional commit messages, and explains merge conflicts.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

A friendly demo skill that introduces Claude Code and prints a greeting.

Generate self-contained, reading-first HTML artifacts from already-produced complex agent output. Use when the user invokes /html, asks to turn a plan, research summary, comparison, code review, decision tree, long explanation, or other complex Human-Agent output into human-friendly HTML, or when the agent suggested an HTML artifact and the user confirmed. Do not use for building full web apps or for doing the upstream research, planning, or analysis itself.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Diagnoses pod crashes, networking issues, and resource pressure across namespaces with redacted kubectl context.

Execute an Efflora Linear issue end to end through the `linear` CLI and the local repo workflow after the user explicitly instructs work on a specific issue such as AS-123. Use when Codex needs to autonomously carry an issue from readiness check through implementation, verification, PR creation, independent review, acceptance evaluation, and handoff to `inreview`. Do not use for backlog planning, issue creation without execution intent, or unattended polling.

Breaks down regular expressions into plain-English, token by token, and flags common pitfalls like greedy quantifiers and unanchored patterns.

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

在 Claude Code 内提供中英互译，保留代码块、技术术语，和 Markdown 结构。

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.