用 21 套内置中文 PPT 模板（或用户自带的 .pptx 模板）生成与编辑 PowerPoint 演示文稿：只替换文字、不破坏原排版/配色/字号，内置按文本框尺寸的出框检测与同级标题字号一致校验；也支持完全原创的简洁版式。当用户要"做 / 生成 / 制作 / 编辑一份 PPT / 演示文稿 / 幻灯片 / .pptx"，或需要工作汇报、年终与季度总结、述职竞聘、项目复盘、开题答辩、商务提案、教学课件、数据可视化等成品 PPTX 时使用。Use when the user wants to create or edit a PowerPoint / PPT / slides / .pptx deck, pick from built-in templates, or apply their own template without breaking the layout.

Generate or edit raster images through CodexManager's OpenAI-compatible Images API when Codex should use the current Codex provider base_url and auth.json API key instead of the official built-in image_gen tool. Use when the user asks for CodexManager image generation, API-key/provider-mode image generation, or image generation through CodexManager account pools, routing, logs, and billing.

Use when changing Ax website language docs, language-specific snippets, examples, API symbol mappings, generated package capabilities, or adding a new website language route. Keeps the markdown-only Hugo site source-audited and generated from repo truth.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

Author and review GitHub Actions workflow YAML safely so syntactically-valid YAML can't ship a workflow that GitHub Actions refuses to run. USE FOR: editing, adding, or reviewing any file under .github/workflows/, writing run-name/name/if/env/run values that contain ${{ }} expressions, diagnosing a run that fails with 'This run likely failed because of a workflow file issue' and no jobs starting, deciding when a workflow scalar must be quoted, validating workflows with actionlint. DO NOT USE FOR: authoring application YAML unrelated to GitHub Actions, Azure Pipelines, GitLab CI, or non-workflow YAML. SCOPE: this skill covers *syntactic/structural* correctness of workflow YAML (quoting, parsing, actionlint); for *semantic and functional* workflow design (what a workflow should do, agentic-workflow behavior), see .github/agents/agentic-workflows.agent.md — the two are complementary. INVOKES: actionlint (downloaded pinned binary) plus git/grep for inspection.

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.

Reproduce a single LinkedIn-MCP issue locally on the current branch against the real authenticated LinkedIn session at ~/.linkedin-mcp/profile/, using the MCP streamable-http server. Captures the exact failure mode (tool output, error, missing data) and maps it back to the scraper code path. Use when the user says "reproduce

Use when creating data visualizations for papers - generates publication-quality plots with top-journal color schemes

Use before merging a kimi-code release PR to preview the user-facing CLI changelog in Chinese. Reads the changelog that changesets pre-generated in the release PR, then reuses sync-changelog's strip / classify / translate logic to render a Chinese preview. Writes no files.

Use when developing in packages/agent-core-v2 (the DI × Scope agent engine) — adding or modifying a domain Service, choosing a LifecycleScope, wiring DI dependencies, splitting a domain across scopes, owning or migrating a config section, gating behavior behind an experimental flag, raising coded errors, working on the permission system, writing DI/Scope tests, porting business logic from agent-core (v1) to v2, triaging a main-branch commit against v2, or exposing a v2 domain over server-v2 while keeping the /api/v1 wire contract compatible with released clients. Self-contained guide organized by development stage (orient → design → implement → test → verify) plus align workflows for v1→v2 migration, main-branch commit triage, and server-v2 wire exposure; each file carries the rules, examples, and red lines for its step.

ACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user themselves saying ulw-plan, ulw plan, /skill:ulw-plan, or asking in their own words for a work plan before coding. NEVER self-activates: a bare ulw/ultrawork run, an agent-side routing decision, or reading this file is not a request, and the plan-gated reviewers (metis/momus) stay locked without a user request plus a written .omo/plans plan file. Explore-first planning consultant (Prometheus) that grounds in the codebase, asks only the forks exploration cannot resolve - or researches them to best practice when the intent is fuzzy - waits for explicit approval, then writes ONE decision-complete work plan a worker executes with zero further interview. Triggers: ulw-plan, ulw plan, plan this, make a plan, plan before coding, interview me, break this down, start planning, plan mode.

Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.

Scan the Obsidian wiki and automatically discover missing cross-references between pages. Use this skill when the user says "link my pages", "find missing links", "cross-reference", "connect my wiki", "add wikilinks", "what pages should be linked", or after any large ingestion to ensure new pages are woven into the existing knowledge graph. Also trigger when the user mentions "orphan pages" in the context of wanting to connect them, or says things like "my wiki feels disconnected" or "pages aren't linked well". This is a write-heavy skill — it actually modifies pages to add links, unlike wiki-lint which just reports issues.

Squad Creator (Craft). Use to create, validate, publish and manage squads Triggers: create squad, design squad, validate squad, squad-creator, @squad-creator, expansion pack, task-first. Use when the user runs /aiox-squad-creator or @squad-creator.

Database Architect & Operations Engineer (Dara). Use for database design, schema architecture, Supabase configuration, RLS policies, migrations, query optimization, data modeling, operations, and monitoring Triggers: database, migration, RLS, schema, Supabase, data-engineer, @data-engineer, query optimization. Use w...

This skill should be used when the user asks to co-author documentation, draft a proposal, write a technical spec, create a decision doc or RFC, or structure a substantial document through iterative collaboration and reader testing.

Business Analyst (Atlas). Use for market research, competitive analysis, user research, brainstorming session facilitation, structured ideation workshops, feasibility studies, i...

EXECUTE a lean wave — plan story DAG + file-ownership batches via CLI, dispatch full-sdc per story, fan-in check, hand off merge to @devops. Use when: wave-execute, run wave, epic wave, parallel stories SDC.

Calculate ETF premium/discount vs NAV via Yahoo Finance, and decompose single-day surges into NAV-driven vs structural components (gamma squeeze, dealer hedging, blocked AP arbitrage). Use whenever the user asks about an ETF's premium or discount, NAV comparison, why an ETF diverged from its holdings, or how much of a move is dealer-hedging-driven. Triggers: "ETF premium", "ETF discount", "NAV premium", "is SPY at a premium", "BITO premium", "IBIT premium", "bond ETF discount", "trading above/below NAV", "ETF premium screener", "biggest discount", "compare ETF NAV", "ETF arbitrage", "ETF gamma squeeze", "ETF premium surge", "decompose ETF move", "dealer gamma exposure", "GEX for ETF", "why did this ETF jump", "premium convergence", "AP arbitrage blocked", or any request about the gap between an ETF's price and underlying value. Especially relevant for leveraged, inverse, international, bond, commodity, and crypto ETFs.