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.
Coordinate Syft-only personalized news workflows in Codex or Claude Code using only syft following, syft top, and syft search. Use when Codex needs to decide or run the right path for building profile artifacts, capturing durable guidance, drafting daily briefings, generating trunk-branch storyline trees, or…
Use when designing, implementing, configuring, testing, or extending applications built with @purista/harness and its provider adapters, including agents, workflows, tools, skills, models, state, sandbox, telemetry, and custom adapter packages.
Cross-Platform Creator Discovery for cross-platform social media cross-platform creator discovery collection, research, monitoring, analysis, and export. Use when the user asks to scrape, extract, collect, export, monitor, research, analyze, or find browser-visible cross-platform social media data for this workflow…
Perform a general code review. Use it to inspect PRs, commits, diffs, or local changes for functional bugs, regressions, security issues, performance degradation, missing tests, and maintainability risks. Apply it when the user asks for a code review, PR review, risk check, or merge-readiness assessment.
A Chinese-language assistant for researching value investing in A-share companies, the companies listed on mainland China's stock exchanges. It examines business quality, financial health, valuation, dividends, ownership and risks.
A tool for analysing several post-project learning logs and deciding which lessons should change an AI agent's skills, checklists, workflows, templates, tool rules, questions, or local notes. It classifies lessons by scope and proposes scored skill patches.
Process large volumes of requests using Gemini Batch API via scripts/. Use for batch processing, bulk text generation, processing JSONL files, async job execution, and cost-efficient high-volume AI tasks. Triggers on "batch processing", "bulk requests", "JSONL", "async job", "batch job".
Control Godot Editor via OpenClaw Godot Plugin. Use for Godot game development tasks including scene management, node manipulation, input simulation, debugging, and editor control. Can modify, save, and delete scenes/nodes and capture project metadata and screenshots — destructive operations should be confirmed with…
Forensic deep dive on a single deal from the Deal Intelligence pipeline. On-demand only. Triggered by 'deep dive on [deal]', 'prep me for the [company] call', 'analyse [deal]', 'what's happening with [company]', or any request for a single-deal analytical deep dive backed by evidence from di tables.
Rust CLI reference for the headless-ghidra pipeline. Covers command syntax, flags, output contract, artifact paths, and workspace layout for all ghidra-agent-cli subcommands. Load when: constructing a ghidra-agent-cli command, interpreting its output, resolving a flag or artifact path question, or debugging CLI…
Generate complete, multi-file Markdown documentation sets (doc sites) that are fully compatible with mdsvr (Markdown Server). Use this skill whenever the user wants to create documentation, write a doc site, build technical docs, generate a knowledge base, or produce any set of .md files that will be served or…
A workflow for cleaning, checking, and importing domain knowledge into Open Knowledge Protocol, a system for storing structured knowledge by subject area.
Use when an agent needs to bootstrap ui-evidence in a repo, then discover, configure, or run before/after UI screenshot capture, current UI snapshot capture, local HTML review generation, or git-baseline UI evidence workflows for a web app.
A Chinese-language editing and writing workflow for turning ideas, source material, or rough topics into publishable content. It adapts the structure and wording to formats such as WeChat articles, Zhihu answers, Xiaohongshu posts, websites, and blogs.
Use the baud CLI to diagnose and automate serial, UART, COM-port, USB-to-TTL, and firmware-console workflows. Trigger when Codex needs to enumerate serial ports, capture boot logs, diagnose silent or one-way communication, send device commands, run guarded YAML hardware tests, or interpret baud JSON, JSONL, logs, and…
Publish task-scoped changes to GitHub through a branch/commit/push/PR flow, including fork-based external contributions. Use when the user wants changes pushed or a PR opened; draft PR is the default.
Use when designing, reviewing, generating, or refactoring React applications built with Effector, effector-react, Farfetched, Atomic Router, @effector/next, patronum, effector-storage, forms, i18n, testing, and related Effector ecosystem tooling. For Feature-Sliced Design project structure and placement decisions, use…
This Skill includes basic information about nmBot that you should know and describes the features of nmBot, including its capabilities, functionalities, and how it can assist users in various tasks. Use this Skill to provide an overview of what nmBot can do and how it can benefit users in their daily activities.
Use when a user needs to find the right skill for a research task, especially when the task can be mapped to Concepts and Theory, Research Capabilities, Methods and Techniques, Software and Tools, Instruments and Equipment, Data and Resources, Workflows, or Standards and Guidelines, or when the research stage belongs…
Implements Syncfusion WPF DataGrid (SfDataGrid) component for displaying and manipulating tabular data in Windows Presentation Foundation applications. Use this when working with data grids, table views, or data binding scenarios. Supports sorting, filtering, grouping, editing, Excel/PDF export, drag and drop…
Run or resume an autonomous build/fix loop that iterates plan → implement → evaluate against a user-approved, testable contract until it passes. Use when the user wants an agent loop, wants a task to keep iterating unattended or in the background (e.g. overnight), or wants to resume, check the status of, or cancel a…
Use when verifying that an implementation matches a change's SDD artifacts. Triggers: "verify", "check implementation", "did I implement everything", "verify the change", "is implementation complete", "check conformance".
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: