Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
The six-cut kernel (read first, write second, verify third) and its runnable loop. Use before a non-trivial multi-file diff or multi-slice agent run, when auditing a major change, or to run the best-practices loop on a goal (a fixed ten-checkpoint pass you point at one objective and walk to done).
Generate a complete narrated whiteboard explainer video from a UTF-8 transcript. Use when the user asks to turn pasted text or a .txt script into a whiteboard video with TTS, subtitles, generated illustrations, hand-drawing animation, BGM, and a final 1920x1080 MP4.
Use when scraping JavaScript-heavy pages or SPAs, crawling multiple URLs concurrently, extracting structured data with reusable CSS/JSON schemas, or building automated web data pipelines. Wraps the Crawl4AI library (crwl CLI and Python SDK) with schema-generation patterns for LLM-free extraction. Triggers on crawl4ai…
Create, view, manage, approve, and merge GitLab merge requests. Use when working with MRs: creating from branches/issues, reviewing, approving, adding comments, resolving discussion threads, checking out locally, viewing diffs, rebasing, merging, or managing state. Triggers on merge request, MR, pull request, PR…
Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary)…
Dataverse MCP (Model Context Protocol) Integration. Use when: querying Dataverse data conversationally, Copilot Studio tool integration, schema discovery in constrained environments, live data validation during development.
Use for generic podcast and video-podcast post-production. Run the repo's transcript and optional visual scanner tools on episode media, prepare transcript artifacts, propose YouTube/podcast chapters, and give editorial feedback such as cuts, clips, show notes, quotes, highlights, and proper noun cleanup.
Regenerate the AppointMe frontend API client (orval/TanStack Query hooks + TypeScript schemas) after the backend OpenAPI surface changes. Use this whenever backend endpoints, request/response DTOs, or other contract-affecting types are added, removed, or modified — e.g. after editing files under src/AppointMe.Api…
Guide migration from an existing Metabase instance to a Bonnard semantic layer. Use when user says "migrate from metabase", "import metabase", "metabase to semantic layer", or has Metabase data they want to model.
A skill for writing a clear GitHub README, the main introductory page for a code project. It explains what the project does, why it matters, and how to start using it.
Investigate and remediate exactly one user-selected CodeInspectus finding with evidence-gated reproduction, a separately approved minimal patch, focused regression testing, and an exact-prior-scan rescan. Use when a user asks an agent to examine, reproduce, fix, or verify one CodeInspectus finding without batching…
A Chinese-language guide for analyzing romantic and social conversations, including message screenshots, intentions, distance, invitations, and date planning.
Run a document-driven Vibe Coding workflow for complex AI-assisted software projects. Use when the user wants to build or refactor a non-trivial project with Codex, Claude Code, Cursor, or another coding agent; asks for vibe coding; wants requirements, design docs, task decomposition, multi-agent implementation…
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Build and maintain a persistent, interlinked wiki from source documents. Knowledge is compiled once and kept current. Based on Andrej Karpathy's LLM Wiki pattern. Commands: /wiki (dashboard), /wiki-ingest, /wiki-query, /wiki-lint, /wiki-save, /wiki-graph, /wiki-review.
A workflow for reproducing or checking results reported in academic papers, especially papers with public Python code. It is aimed at machine learning, computer vision, and natural language processing research.
Browser automation with WebMCP Hub integration. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information — with automatic per-site tool discovery from the community hub.
Use when a task spans interface understanding, design-system memory, UI audits, design CI, Figma, shadcn or Tailwind code generation, research, or agent design workflows and needs the correct Memi capability selected.
A workflow for cutting highlights from an already edited long video and its SRT subtitle file. SRT is a subtitle format that includes text and timing; each result is no longer than two minutes.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: