AI & ML

wcpaka-lgtm Bundle

Set up local LLM providers (LM Studio, Ollama, llama.cpp) as Hermes Agent backends.

wcpaka-lgtm Bundle

Diagnose PyTorch CUDA mismatches and diffusion model issues.

wcpaka-lgtm Bundle

Configure Hermes auxiliary side-LLM backends (vision).

wcpaka-lgtm Bundle

Manage OpenCodex (Codex proxy fork): model catalog, provider routing, config.

wcpaka-lgtm Bundle

Set up Hermes auxiliary LLM backends (vision, fallbacks).

wcpaka-lgtm Bundle

Use when the user wants to sync Hermes Agent state (config, soul, auth, memories, skills, cron) across multiple machines via a private Git repo. Covers bi-directional sync via cron, PAT auth on GitHub, MSYS path issues on Windows, the .gitignore allowlist trick, the python3→python Microsoft Store stub bug, the staging-vs-working-tree pattern that prevents sync from corrupting a running Hermes process, and the **two-machine cross-contamination problem** (Mac editing HERMES_DIR silently breaks Windows) solved by OSTYPE auto-detection in sync.sh.

wcpaka-lgtm Skill

Drive the user's desktop in the background — clicking, typing, scrolling, dragging — without stealing the cursor, keyboard focus, or switching virtual desktops / Spaces. Cross-platform: macOS, Windows, Linux. Works with any tool-capable model. Load this skill whenever the `computer_use` tool is available.

wcpaka-lgtm Skill

Debug CUDA crashes and Python venv contamination on Windows.

wcpaka-lgtm Bundle

Investigate new AI model releases: weights, license, buzz.

wcpaka-lgtm Skill

Use when the user asks to save a video from a URL (X, YouTube, Instagram, etc.) to NAS. Downloads the video, extracts keyframes, has vision model generate a short Korean title, and renames to "platform_한글제목.mp4".

wcpaka-lgtm Bundle

Build Chrome/Edge MV3 extensions with LLM API integration.

jensen-yao Bundle

Operate, inspect, configure, troubleshoot, and continue DramaClaw projects according to the official workflow. Use whenever the user mentions DramaClaw, NovelVideo, 虾导, 虾料, 虾塘, 虾镜, 虾画, 虾格, 虾条, CLI/API/Web project synchronization, model or storage configuration, characters, identities, portraits, scenes, props, voices, episodes, Beats, scripts, sketches, first frames, audio, video, composition, project status, resume/continue, or asks to generate/fix a DramaClaw production. Enforces asset, image, and review gates before downstream generation.

jensen-yao Skill

Operate this machine's locally hosted AI models and model services on demand: CosyVoice3 TTS (配音/旁白/克隆), local embeddings bge-m3, Ollama models (gemma3:4b), musicgen-small (音乐生成), and LM Studio models. Use whenever the user mentions 本地模型, 本地配音, 本地TTS, CosyVoice, 11436, 11435, bge-m3, ollama, gemma, 本地音乐生成, musicgen, LM Studio, or asks to generate speech/music/embeddings with local models. IMPORTANT: use these resources only when a task actually needs them — do not load heavy models or start services speculatively.

jensen-yao Bundle

Auxiliary workflow for $imagegen when Codex needs high-quality image generation but the built-in image_gen tool is unavailable or not exposed. Use this with $imagegen to run the installed image_gen.py CLI through a separate temporary drawing API key, preferably configured in Codex++ cliWrapper settings, defaulting to OPENAI_BASE_URL=https://code.codingplay.top/v1, without changing the Codex desktop/chat model API configuration.

jensen-yao Bundle

Coordinate CNKI research workflows in Codex using Chrome DevTools MCP. Use when the user asks to search CNKI papers, inspect paper details, browse journals or issues, check journal indexing, download CNKI files, export citations, handle institution/off-campus CNKI login, or combine these tasks into a literature research workflow.

thoughtspot Bundle

Move a tenant Org's bespoke content off its own Table/Model copies onto a governed published Model, then retire the old Org. Use when migrating tenants to the single-model publishing pattern, when a tenant's Answers and Liveboards must be repointed at published objects, or when sizing how many tenants a Sets dependency blocks.

thoughtspot Bundle

Restrict which columns a group can see on a ThoughtSpot Table or Model, choosing between the two mechanisms — Column Security Rules (CSR) and column-level sharing (CLS) — per Org, and explaining the trade-off. Use when hiding columns from a tenant or an audience, securing sensitive fields, or deciding which column-security mechanism applies to a published object. Drives the `ts share` and `ts security column-rules` pipelines.

thoughtspot Bundle

Convert or import a Qlik Sense app into ThoughtSpot — parses a Qlik app (offline .qvf, or an exported Qlik Engine artifacts directory) into tables, columns, master measures and sheets, generates Table + Model TML and a tabbed Liveboard, translates Qlik measure expressions to ThoughtSpot formulas, validates and imports. Direction is always Qlik → ThoughtSpot. Not for ThoughtSpot → Qlik or standalone TML exports.

thoughtspot Bundle

Prepare a ThoughtSpot Model to work well with Spotter. Use when you want to improve how a Model responds to natural language queries — reviewing and writing AI context, synonyms, reference questions, business terms, and data model instructions. Mines real language from existing Liveboards, Answers, and optionally Snowflake query history to ground the coaching in how users actually talk about the data.

thoughtspot Bundle

Convert a Looker semantic model (LookML project) into ThoughtSpot — parses model + view .lkml files, generates Table TML and Model TML per explore, validates invariants, and imports. Optionally converts LookML dashboards to ThoughtSpot Liveboards. Direction is always Looker → ThoughtSpot.

thoughtspot Bundle

Convert or import a Power BI report into ThoughtSpot — parses the Power BI Project (.pbip) TMDL semantic model and PBIR report, generates Table + Model TML and Answers/tabbed Liveboards, translates DAX (including CALCULATE(ALL) → group_aggregate, and time-intelligence rebuilt with parameters), validates and imports. Direction is always Power BI → ThoughtSpot. Not for ThoughtSpot → Power BI or standalone TML exports.

thoughtspot Bundle

Convert or import a Sisense dashboard into ThoughtSpot — parses a captured OFFLINE Sisense bundle JSON ({dashboard, widgets, datamodel}), generates Table + Model TML and Answers/tabbed Liveboard, translates JAQL (aggregations + the deterministic formula subset), validates and imports. Direction is always Sisense → ThoughtSpot. Not for ThoughtSpot → Sisense, and not a live Sisense fetch — the input is a bundle already on disk.

thoughtspot Bundle

Promote formulas and parameters from a saved ThoughtSpot Answer into a Model — makes them available to all users who search against it.

thoughtspot Skill

Convert a ThoughtSpot Worksheet or Model into a Snowflake Semantic View by exporting TML, mapping columns and joins, translating formulas, and creating the view via SYSTEM$CREATE_SEMANTIC_VIEW_FROM_YAML.

thoughtspot Bundle

Creates four Snowflake scalar UDFs that format integer durations (seconds or minutes) as human-readable time strings — HH:MM:SS, DD:HH:MM:SS, HH:MM, DD:HH:MM — then shows the ThoughtSpot formula syntax to display them in any Model. Use this skill whenever the user asks about displaying durations, formatting elapsed time, converting seconds or minutes to a readable format, showing call duration, handle time, SLA elapsed time, ticket age as HH:MM:SS, or any scenario where an integer count of seconds or minutes should appear as a formatted time string in ThoughtSpot.

thoughtspot Bundle

Creates three Snowflake scalar UDFs for calculating business-day (weekday-only) date differences and elapsed time, then shows the ThoughtSpot formula syntax to use them in any Model. Use this skill whenever the user asks about weekday date calculations, business day counts, working day differences, SLA tracking, ticket age, order fulfillment time, or wants to exclude weekends from any date difference in ThoughtSpot or Snowflake. ThoughtSpot's built-in diff_days/diff_hours/diff_minutes count calendar days — if a user needs weekday-only equivalents, invoke this skill.

dojogenesis Bundle

Access and apply the 10 Dojo Seed Patches plus 3 field seeds as reusable thinking modules. Use when architecting systems, optimizing costs, debugging complex issues, or grounding ecosystem-level work. Trigger phrases include "which seed applies here", "suggest a seed pattern", "apply a seed to this", "what pattern should we use", "load the seed library".

dojogenesis Bundle

> **OpenClaw Integration:** This skill is invoked by the Dojo Genesis plugin via `/dojo run agent-teaching`.

dojogenesis Bundle

> **OpenClaw Integration:** This skill is invoked by the Dojo Genesis plugin via `/dojo run skill-creation`.

dojogenesis Bundle

> **OpenClaw Integration:** This skill is invoked by the Dojo Genesis plugin via `/dojo run handoff-protocol`.

dojogenesis Bundle

> **OpenClaw Integration:** This skill is invoked by the Dojo Genesis plugin via `/dojo run decision-propagation`.

dojogenesis Bundle

> **OpenClaw Integration:** This skill is invoked by the Dojo Genesis plugin via `/dojo run workspace-navigation`.

dojogenesis Bundle

Transform Spec to Implementation Prompt Skill

dojogenesis Bundle

> **OpenClaw Integration:** This skill is invoked by the Dojo Genesis plugin via `/dojo run multi-surface-strategy`.

dojogenesis Bundle

> **OpenClaw Integration:** This skill is invoked by the Dojo Genesis plugin via `/dojo run pre-implementation-checklist`.

dojogenesis Bundle

> **OpenClaw Integration:** This skill is invoked by the Dojo Genesis plugin via `/dojo run spec-constellation-to-prompt-suite`.