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.
Trace and investigate GitHub Copilot CLI sessions with agent-strace. Use when the user wants to capture a Copilot session, replay agent activity, explain a decision, diagnose repeated tool calls or failures, inspect cost, or audit a recorded session.
Curador del conocimiento local de un proyecto bajo bucle ralph. Mantiene un conjunto de skills locales (metodologías, pitfalls y decisiones del proyecto) para que futuras iteraciones planifiquen y ejecuten sin dar palos de ciego. Su acción review lee el plan y los logs tras una tarea y crea, extiende o borra esas…
Use the nb CLI for all Jupyter notebook (.ipynb) operations, including reading, inspecting, creating, editing cells, deleting cells, clearing outputs, searching, executing, and working with connected JupyterLab sessions or remote kernel gateways. Required when an agent needs deterministic notebook manipulation without…
A Qimen Dunjia divination skill that uses a time and question to create a chart and interpret it through a nine-step process. Qimen Dunjia is a traditional Chinese method of divination.
Running autonomous loops for nexus-autoloop. Generates script sets from goals, designs operation contracts, audits live loops, and recovers state — runners that complete reliably.
Memory hygiene audit -- finds stale facts, contradictions, low-confidence entries, and consolidation candidates in Pensyve memory. Use periodically to maintain memory quality.
Convert born-digital, scanned, or mixed PDFs into auditable Markdown while preserving reading order, equations, source-page anchors, and information-bearing images as adjacent non-original text descriptions. Use this skill whenever a user asks to transcribe, OCR, understand, or convert a PDF into Markdown, especially…
A workflow for creating a pack of animated Chinese meme stickers for WeChat from a reference image or text idea. It targets 16 or 24 entries, each as a 240-by-240 GIF.
A tool for copying videos saved in an authorised Douyin account into a local Markdown or Obsidian knowledge base. Douyin is a Chinese short-video platform, and Obsidian is an app for organising linked notes.
Check SQL for silent semantic errors (fan-out double-counting, unsafe sums, wrong join keys, sensitive columns) BEFORE executing it against a database. Use whenever you are about to run a SELECT you or another model wrote — especially aggregates over joins. Deterministic, offline, 0.1 ms per check.
Use when the user asks to invoke, delegate to, or collaborate with Claude (Claude Code) on any task. Also use PROACTIVELY when handing part of the work to Claude, or an independent non-Codex perspective, would add value — implementation, review, second opinions on code, plans, architecture, or design decisions.
Receive and verify PagerDuty V3 webhooks (outbound webhook subscriptions created via the /webhooksubscriptions REST API). Use when setting up a PagerDuty webhook handler, debugging X-PagerDuty-Signature verification, or handling events like incident.triggered, incident.acknowledged, incident.resolved…
Access and configure a user's local or cloud Zotero library without MCP by executing the bundled JSON CLI. Use for Skill setup or troubleshooting, Zotero connection configuration, collection/folder browsing, exact collection item retrieval, library search, paper metadata, PDF full text, annotations, notes, tags…
Use when a complex task needs dependency-aware interactive branches, subagents, or AI coding threads while keeping the master session context clean through explicit branch briefs, completion reports, wave planning, and user-approved merges. Especially useful with grill-me, Trellis, research, implementation, writing…
Real-time web research and live synthesis with sources. Use when the question depends on freshness, community chatter, X/Twitter dynamics, breaking updates, or broad multi-source summaries. Prefer this over source-first search when you need fast situational awareness. Prefer exa-search instead for official docs, API…
Search engine for MCP tools and agent skills. Search 790+ MCP server tools and 760+ agent skills in one place, call remote MCP tools, and get full skill instructions via simple HTTP API.
Official parent skill for analyzing HitKeep data through HitKeep MCP and official docs. Use for broad traffic, event, ecommerce, Web Vitals, AI visibility, Search Console, opportunity, tracking-health, MCP setup, or analytics-surface questions; use a narrower HitKeep analytics skill when the task clearly matches one.
Use this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts, validating compliance, converting DICOM to BIDS, writing metadata sidecars…
Install AI agent skills as roles & behaviors from any source — local folder, GitHub, GitLab, SSH git URL. Zero-dependency CLI with 90 agent targets (65 verified).
A project-level CSS file for changing the look of Spherse, such as page backgrounds, text, cards, buttons, and pop-up menus. It uses separate values for light and dark mode.
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: