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.
Search past Claude Code and Codex sessions. Triggers: /memex, "search old conversations", "find a past session", "recall a previous conversation", "search session history", "what did we discuss", "remember when we".
Port TON smart contracts from FunC (.fc/.func) to modern Tolk (.tolk) with Acton: use acton func2tolk when helpful, then refactor storage/messages/opcodes into typed structs and serialization, implement Acton-style entrypoints, generate wrappers, migrate JS/TS tests to native Tolk tests, and use acton…
Use when a plan, spec, design doc, brainstorm, or walkthrough needs review before anyone implements it — especially when it may be over-engineered, over-abstracted, or scoped past a lean MVP. Triggers include "review this plan", "is this over-engineered", "is this too much for an MVP", "sanity check this design"…
Integrate Green Invoice (Morning) API for Israeli invoicing, receipts, client management, and payment processing. Use when user asks to create invoices via Green Invoice, generate hashbonit mas through Morning API, manage clients in Green Invoice, set up webhook automation for document creation, query documents or…
Comprehensive writing guide for Hong Kong RGC GRF and CRF proposals. Covers all sections including objectives, literature review, methodology, significance, budget justification, and PI track record.
A skill for adding Mermaid diagrams to Markdown documents. Mermaid is a text format that turns descriptions into diagrams, and this skill supports dark and light themes, meaningful shapes, compact layouts, and reusable templates.
Use when coordinating multiple live Codex threads, maintaining a coordination heartbeat, routing work across implementation threads, inspecting cross-thread ownership or gates, or keeping a coordinated effort moving through PR, review, evidence, and human-action boundaries.
use this skill when coordinating complex multi-step or multi-agent work through an autonomous durable kanban dispatch protocol. use it when a user gives only an idea and expects the model to infer product requirements, ux flows, architecture, task decomposition, implementation, review, trace logs, and final results…
Answers incoming RFPs end-to-end using a kapa-powered MCP as the sole knowledge source. Guides the user through a structured workflow: upload the RFP, extract and index every requirement, map each one against product capabilities (Grounded / Assertable / Gap), draft and refine answers rooted in actual documentation…
Join several machines into a myainet personal AI network — each playing its part. Once any AI tool loads the network config, it can dispatch the whole network uniformly.
A step-by-step skill for writing Chinese short stories and saving the finished manuscript as a local Markdown file. It supports planning, drafting, self-checking, and saving.
Security scanning guidance for Israeli web applications covering OWASP Top 10, Israeli Privacy Protection Authority (PPA) compliance, dependency vulnerability scanning, secrets detection, and secure coding patterns for Hebrew/RTL apps. Use when user asks to "scan for vulnerabilities", "check security compliance"…
A framework for evaluating pharmaceutical drug-development projects across biology, drug design, clinical and regulatory plans, and commercial conditions. It also classifies projects by how differentiated their innovation is.
Create ASI-compliant skills with deterministic governance. This is not a general project planning tool; it is a skill creation workflow with explicit gates.
Use this skill when the user wants to search for phone numbers, check number availability, view regions/cities/DID types, check regulatory requirements, reserve numbers, cancel reservations, purchase phone numbers, or delete/cancel an owned virtual number via the 2Chat API. Trigger phrases include "search numbers"…
Initialize a DevCrew workspace and activate the full AI team orchestration protocol — PDEVI workflow, persistent memory, checkpoint-based quality control.
Exhaustive Android performance skill for writing ANR-free, frozen-frame-free, and janky-free code. Use this skill whenever writing, reviewing, or auditing Android code that involves: coroutines or threading (Dispatchers, withContext, runBlocking, GlobalScope, Mutex, synchronized), Android component lifecycles…
AKOÚŌ meta-router for multimodal listening. Use this skill whenever an agent is asked to listen to, analyze, interpret, describe, or evaluate any sound, audio file, music fragment, rhythm, song, voice, speech, transcript, field note, spectrogram, archive fragment, video, caption, dataset, model output, platform…
Record and retrieve structured project learnings using mulch CLI. Use when working on code and wanting to capture patterns, failures, decisions, conventions, references, or guides for future sessions.
Control macOS GUI applications via screen capture, mouse/keyboard automation, and accessibility element inspection. Use when you need to interact with macOS app UIs, take screenshots, click buttons, type text, or inspect accessibility trees.
Build Python data pipelines that liberate structured data from unstructured and semi-structured sources — government PDFs, FOIA releases, scanned reports, scraped HTML, panel-format spreadsheets — into tidy, documented, reproducible civic datasets. Works at six escalating levels, from a one-shot "just give me the CSV"…
Audit a single English passage or compare parallel drafts using the seven component skills in Oiticica's faults-of-clarity section.
★not rated 10 1mo agoA36 tokens
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: