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.
Shape output for a reader with dyslexia. Use this skill whenever responding to ANY user message including coding tasks, debugging, explanations, planning, and casual conversation. Output should open with a one-line headline, use short sentences with bolded key terms, number every process, keep full technical depth…
Query Elasticsearch and Kibana via the Kibana console proxy API. Use this skill whenever the user asks to search logs, query Elasticsearch indices, list indices, view dashboards, check Kibana status, or investigate production issues in the Elastic stack. Also use when the user mentions Kibana, Elasticsearch, ES, logs…
Use this skill whenever a PDF is the input or the output. Creating one — a one-pager, report, invoice, brochure, résumé, certificate, handout, or anything the user asks for "as a PDF". Reading one — extracting text or tables, answering questions about a document's contents, summarising it. Changing one — merging…
USE FOR: Determine the exact Microsoft Graph endpoints and least-privileged permissions needed for a use case and auth context. Identify operation, find docs, copy endpoint, validate permission, and return table with endpoints and permissions. DO NOT USE FOR: Non-Microsoft Graph scenarios. INVOKES: None.
Dia-GramV (DGV) — plan a system's architecture as a typed, linted, live diagram BEFORE writing code. Use when the user wants to design or map an app's architecture, see how modules / APIs / programs / databases / bridges connect, check a plan for incompatibilities, review an existing codebase's structure as a diagram…
End-to-end content pipeline — idea in, published evidence-backed page out. Orchestrates search recon, real lab experiments (cloud VMs / local Docker), screenshot and asset production, drafting in a defined voice, verification loops, ship, and a write-back to your knowledge base. Triggers on "/factory ...", "new piece…
Use when users want a premium, demo-worthy cinematic web experience, immersive landing page, portfolio, product showcase, or Claude-made wow-factor UI with motion, 3D, particles, WebGL, or scroll-driven storytelling.
Audit a documentation folder for quality problems across multiple dimensions (broken links, stale code examples, missing sections, readability) and produce a prioritized report with suggested fixes. Use when asked to "audit the docs", "check documentation quality", or before a docs release.
Goal-first guardrail for planning, changing, testing, reviewing, or removing code and engineering artifacts. Includes engineering Plan entries even when no code is changed. Preserve observable outcome, a single authoritative owner, risk, validation, and honest evidence without scope drift. Not for conceptual questions…
Generates and hardens production nginx configurations for reverse proxying with TLS termination, HTTP/2, response caching, rate limiting, gzip/brotli compression, and security headers. Use this skill when the user asks to "set up nginx as a reverse proxy", "add TLS/SSL to nginx", "configure nginx caching or rate…
Apply the installed language, framework, or database conventions to changed code. Use when a stack-specific decision comes up during implementation or review. Skip audits of unchanged code.
A guided workflow for creating and editing AI videos, including talking-head recordings, where a person speaks to the camera. It coordinates script, review, captions, sound, and final video work.
A writing workflow for turning surveys, interviews, observations, policy documents, historical sources, and other research material into Chinese reports in the humanities and social sciences.
Extract text from scanned PDFs and images with Qubicl's local Poppler and Tesseract pipeline, and choose the appropriate Qubicl document or web tool for mixed document sources. Use for OCR, image-only PDFs, scans, and document extraction diagnostics.
Long-term memory for coding agents. Auto-applies at the start of any coding task — recall past context before answering, capture decisions/learnings/fixes after work, use CodeGraph instead of grep for symbol lookup. Invoke when you see [remem-mcp] in your context or when starting any non-trivial coding work.
A travel-planning guide for building practical itineraries for one city or several destinations. It arranges places by location and travel time, then accounts for opening hours, bookings, weather, transport, and budget.
An email and calendar connection for an OpenClaw agent. It can read, search and draft messages, while sending, deleting and changing the calendar require approval from a person outside the agent.
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: