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.
Build, flash/download, and debug STM32CubeIDE firmware safely using project-local memory, generated makefiles, STM32 Programmer CLI, ST-LINK/SWD, serial tools, and runtime verification. Use when working with STM32CubeIDE projects, .ioc/.cproject files, STM32 firmware compile/build/download/flash tasks, Debug/Release…
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
A Feishu product-requirements-to-code workflow, where Feishu is a collaboration platform. It coordinates steps from reading a product brief and API details through documentation, tests, optional coding, and verification.
A Ukrainian-language editing guide for removing wording that sounds machine-generated. It checks for unnatural expressions, loan translations, bureaucratic wording, repetition, promotional language, and hidden Unicode characters.
Query SAP S/4HANA OData services directly from Claude — discover service catalogs, fetch entity metadata, run OData queries (GET/POST/PATCH/DELETE), and retrieve field value lists. Use this when working with SAP S/4HANA data, building integrations, or exploring what OData services a system exposes. Requires a running…
Persistent knowledge base for Claude Code projects using the LLM Wiki methodology by Andrej Karpathy. Bootstraps a structured wiki (markdown files with cross-references) and configures Claude Code to maintain it automatically across sessions. Integrates with Obsidian via MCP for graph view and visual navigation. Use…
Review Convex code for security, auth, validators, performance, and best practices. TRIGGER when the user asks to review/audit Convex code, or after writing convex/ functions you want checked. Applies the Convex-specific review checklist (auth checks, args/returns validators, internal vs public, indexes-not-filter…
Local mirror of the CrossRef database with FTS5 full-text search across 167M+ scholarly works — offline, millisecond queries, no rate limits. Also exposes citation networks, per-topic caches, and an HTTP/MCP relay.
Prepare, upload, save, inspect, and formally publish WeChat Official Account articles through the authenticated wechatpublisher remote MCP server. Use when the user asks to post Markdown, HTML, plain text, covers, or inline images to a subscription or service account; manage WeChat drafts; test account API access; or…
Debug failed Terra/Cromwell workflow submissions. Use when analyzing failed submissions, identifying error patterns, or troubleshooting infrastructure issues like docker pull failures, preemption, or OOM.
Use this skill when working with SQL Server databases, creating tables, writing queries, or modifying database schema. Triggers on database work, SQL queries, table creation, or schema modifications.
Use when Codex needs to read, analyze, fix, verify, or write back ZenTao bugs through zentao MCP tools. Trigger for requests that mention a ZenTao Bug ID, ZenTao defect fixing, Bug attachments, my work lists, product/project/execution Bug lists, REST v1 ZenTao routes, or safe assign/resolve/close/writeback actions…
Automated affiliate marketing engine — discovers new AI tool affiliate programs, generates conversion-optimized promotion content for all platforms, tracks commission status, and identifies new revenue opportunities. Target: ¥5,000+/month from affiliate commissions.
Offline reconstruction and security audit of agent execution traces from JSON, JSONL, or pasted logs. Use when Codex needs to review user input, model planning, tool calls, tool results, approvals, and final answers for prompt injection, unauthorized tools, secret exposure, missing approval, repeated-call loops, or…
One source of truth for local AI agent skills: audit Codex, Claude, Hermes, OpenClaw, OpenCode, workspace skills, and shared roots; score hygiene, diff conflicting installs, classify drift as pristine/dirty/local-only against recorded baselines, deduplicate into one canonical source with symlinks, and migrate the same…
Write GORM data access code using the DAO (Data Access Object) pattern. Use when creating database models, writing queries, setting up GORM, adding CRUD methods, or working with gorm.io in Go services. Also use when the user mentions "DAO", "data access", "ORM", "database models", "GORM", or is building a Go service…
You are a behavioral finance advisor operating as a background quality layer for investment professionals. Your role is to screen investment-related text — whether it's a prompt about to be sent to an LLM, a research memo, an investment thesis, a portfolio review or LLM-generated output — and surface any behavioral…
Opinionated version of grill-me. Walks the user down every branch of a plan or design, one tight question at a time, with options ordered by recommendation. Use when user invokes /cook-me or asks to be "cooked" on a plan or design.
A Chinese-language workflow for analysing mutual funds using data from Eastmoney, a Chinese financial information website. It produces an HTML report with charts, tables, historical return measures, and written analysis.
★not rated 5 5mo agoA39 tokens
originalMIT
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: