Mle Workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
Agent skills for software development, debugging, code review, and implementation. Browse reusable SKILL.md agent workflows and prompt templates in this category. Each card links to when-to-use notes and setup steps.
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
Apply Remotion Studio's pointerless interaction styling to clickable controls. Use when adding or revising Studio buttons or links that should use the default cursor, brighten on hover, and show focus decoration only for keyboard navigation.
One-click contribution flow for OpenDesign (nexu-io/open-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD; translate docs; fix a typo / write a blog; report a bug), the agent validates and opens a PR (or issue) for you. Trigger words contribute to open design, ship my OD skill, ship my OD design system, translate OD docs, report an OD bug, od-contribute.
Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to dashboard', 'data visualization'. Output is a single .xlsx. Scene-layer on officecli-xlsx: inherits every xlsx hard rule. DO NOT invoke for: a single budget tracker / one-sheet CSV-with-formatting (use xlsx), a 3-statement / DCF / LBO financial model (use financial-model), a weekly report with at most 1 chart and fewer than 10 rows (use xlsx).
Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value', 'LBO', 'debt schedule', 'cash sweep', 'MOIC', 'IRR / XIRR', 'sensitivity table', 'scenario analysis', 'ARR model', 'unit economics', 'CAC / LTV', 'cap table forecast'. Output is a single formula-driven .xlsx. This skill is a scene layer on top of officecli-xlsx — it inherits every xlsx v2 rule (4-color code, visual floor, number formats, cache-drift, Known Issues, Delivery Gate minimum cycle). DO NOT invoke for a simple budget tracker, CSV dump, or operational KPI sheet — route those to officecli-xlsx base.
Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions 'deck', 'slides', 'presentation', 'pitch', or references a .pptx filename.
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document', 'onboarding form', 'HR intake', 'survey template', 'contract / SOW template', 'mail-merge template', 'compliance checklist', 'medical intake questionnaire'. Output is a single .docx where specific fields are editable and the rest is locked. This skill is INDEPENDENT, not a scene layer on docx — payload is w:sdt + w:ffData + w:fldChar + documentProtection, none of which docx base skill covers. Do NOT trigger for regular reports, letters, memos, academic papers, pitch decks, or any document with no user-fillable fields — route those to officecli-docx or its scene layers.
Use to build a standalone external program with an agent in it, or connect an external program to a Penguin agent. For an app inside PenguinHarness with its own Agent and workbench tab, use agent-initialization and penguin-plugin directly; no SDK/API question applies. A program reaches an agent in one of two ways, and the skill asks the user which before building — embedded with the Penguin Harness SDK (@prismshadow/penguin-core, no server), or over the Penguin server's Agent API (AMSP, with the @prismshadow/amsp client or curl). This is writing application code, not configuring an Agent State inside PenguinHarness. Covers self-contained projects, the createSession/run streaming loop with thinking and image messages, wiring the user's existing tools in as CLI commands, a complete RAG recipe that ingests documents into a knowledge base and answers with citations behind a web UI, and the Agent API client. Workbenches — the tabs and pages beside the chat that an Agent keeps for itself ins
Quick reference for ponytail levels, skills and commands. One-shot display. Use for /ponytail-help, "ponytail help", "how do I use ponytail".
AI agent orchestrator with Neo4j knowledge graph, Meilisearch search, and Tree-sitter parsing. Use for coordinating multiple coding agents on complex projects with shared context and plans.
Capture and annotate PR screenshots and videos with measured arrows, outlines, alignment guides, spacing brackets, captions, zoom, and speed cues.
Cut and publish a versioned release of @loopdive/js2 + the js2wasm proxy — bump both manifests in lockstep, land a reviewed release PR, then push the vX.Y.Z tag that triggers npm/JSR publish. Use this whenever the user wants to release, publish, ship, cut, or tag a version, bump the version number, push a release tag, cut a patch/minor/major, cut release notes, or get a fix onto npm — even if they only say "ship it" or name a version like "0.70.0" without saying the word release. Also use it when a publish failed on verify-version, when a vX.Y.Z tag needs pushing or re-pushing, or when someone is about to run git tag vX.Y.Z by hand (that is the bug this skill exists to prevent).
QwenPaw 命令行使用技巧:涵盖心跳(Heartbeat)配置、定时任务管理、Docker 打包部署、工作区导出迁移等操作。当用户要求添加心跳任务、配置定时自检、打包 QwenPaw 实例、部署到其他服务器、生成 Dockerfile 或 docker-compose 文件时使用本 skill。
Cut a Lotti release — assemble the changelog.d/ fragments into CHANGELOG.md and the Flathub metainfo, bump the version, open the release PR, then tag. Use when asked to cut or prepare a release, assemble the changelog, publish a new version, or work out what is unreleased.
Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.
How to monitor and fix security issues in Massing — CodeQL alerts, dependency audits, secret scanning, and ReDoS/XXE fixes. Invoke after a push (standing directive) or when doing a hardening pass. Emphasises that a green CodeQL run != zero alerts.
Install or initialize HOL Guard local runtime protection for Claude Code. Use when the user explicitly asks to install, enable, set up, or repair HOL Guard.
The Massing release discipline — how to ship a verified, CI-green version-numbered release direct to main. Invoke whenever finishing a shippable change (feature, fix, doc). Covers version bump (both files), CHANGELOG/roadmap notes, the ruff/lint CI gotchas, tag, push, and CI/CodeQL verification.
Test Slack with Convex-leased user OAuth or QA bots; check credentials, exercise owned messages, prove Gateway behavior, and distinguish API evidence from real Slack client interactions.
Check HOL Guard local protection status for Claude Code without changing configuration. Use when the user asks whether Guard is installed, active, healthy, or protecting Claude Code.
Muxes per-shot storyboard video with Chinese and English voice-over by retiming video to match VO duration (setpts), writing Video-Chinese/ and Video-English/ (matched by shot id 01, 02, …). Use when the user wants storyboard A/V mix, storyboard A/V mix, VO dubbing mix, video retime to audio, Video-Chinese, Video-English, bilingual VO on cut video, or batch mux Video/ + Chinese/ + English/.
Converts storyboard markdown (bilingual Chinese + English narration per shot) into speech audio via IndexTTS2 (same stack as ai-text-to-speech). Batch-writes WAVs under Chinese/ and English/ named by shot id (model loaded once), pads 0.4 s edge silence in place, then a speech-timeline.md and one concatenated SRT per language (Chinese.srt / English.srt). Use when the user wants storyboard TTS, storyboard to speech, narration VO, storyboard-to-speech, bilingual VO export, subtitles, or batch TTS from a storyboard.md.
Show current test262 pass rates for both the js-host (gc) and standalone targets side by side, from committed baseline summaries — no network fetch, no compile. Use for a quick conformance status check.
Triage GitHub issues by applying type, effort, priority, and area labels. Runs in an isolated context to avoid polluting the main conversation with issue details. Delegates to a specialized triage agent with label validation hooks.