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.
A local-first tracker for Chinese graduate-admissions notices, especially recommendation-based admissions (保研/推免) such as summer camps and direct PhD offers. It watches university notice pages and matches announcements to a student's profile.
A workflow for translating, checking, or polishing text of any length. It first converts local PDFs and EPUBs into Markdown, a plain-text document format, before translating them.
Send progress, completion, and option-prompt messages to the paired user via this agent's Telegram bot. Use whenever work takes more than a few seconds, when blocking on a user decision, or when presenting choices. Never go silent for more than 30s on a long-running task.
Review a change in the EvalBench repo for (a) does it actually work — verified by running the tests and style checks, (b) does it follow EvalBench architecture — base-class contracts, config-key registration, PYTHONPATH-relative imports, sandbox isolation, concurrency safety, docs, (c) does it still build and deploy …
An AI workflow that builds a simulated model of a romantic interest from chat logs, photos, and social media, including personality and attachment-style analysis.
Methodology reference for Mastermind Bug Bounty runtime. Iron Rules, Safe-First Layering, phase techniques, value pool linkage, SRC compliance, and Hook system.
Apply Pilotfish's bounded task routing, Plan and approval gates, typed role delegation, security separation, blocked-task isolation, and fresh-context verification. Use for coding, debugging, refactoring, architecture, security-sensitive work, multi-step repository changes, or any request where execution mode…
Design and scaffold an autonomous "loop" around a coding agent for a recurring workflow. Use when the user wants to stop hand-prompting an agent and instead build a system that discovers work, delegates it to a maker, verifies the result with a separate checker, remembers progress on disk, and re-runs until a goal is…
Use when mapping a repeatable website workflow into a verified Hermes skill so later runs can follow known steps instead of rediscovering the site. Surveys browser compatibility, semantic targets, failure modes, recovery paths, decision gates, and expiry using dummy data and no irreversible submissions.
Organize files using the PARA method (Building a Second Brain). Intelligent categorization into Projects, Areas, Resources, and Archive with inbox workflow. Triggers on "organize my files", "organize my downloads", "second brain", "PARA method", "clean up files". Creates numbered PARA folders, renames poorly-named…
Generates a personalized 3-email outreach sequence for a prospect. Each email is short, human, and built around a specific signal — not a generic pitch.
Conduct a realistic, adaptive technical mock interview from a resume and job description. Use whenever the user wants interview practice, mock interviews, resume-based questioning, system design practice, LLD grinding, or to prepare for a specific tech role — even if they just paste a resume and a JD, upload a PDF…
Create, revise, normalize, and validate thesis-ready flowchart figures for undergraduate theses, graduation projects, dissertations, and academic papers. Use when users ask to draw or convert thesis/graduation-project process descriptions, algorithm steps, system workflows, business processes, experimental protocols…
Medical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript. Creates and manages a project directory with IMRAD-format section files, literature matrix, reference management, and quality checklists. Supports both English and Japanese papers.…
Find, rank, summarize, and track high-quality research papers with Scholar MCP, accept user-submitted PDFs, DOIs, or links through a persistent local inbox as special-interest signals, then create evidence-rich bilingual Feishu deep-read documents with detailed abstracts, contributions, methods, figures, and verified…
Use when answering a business/analytics question over already-aggregated data and the deliverable is a visual. Produces ONE annotated chart plus a compact exact-numbers table, with the headline finding as the title. Defaults to a single secure PNG image (no live code in the artifact). Trigger on requests like "show me…
Complete video ad creation toolkit — from creative brief to published ad. Includes hook formulas, script frameworks, multi-format strategy, A/B testing methodology, and batch workflow patterns. Integrates with Creatify API for automated URL-to-video, ad cloning, AI script generation, custom templates…
Required reference for Prisma ORM 7 SQL driver adapter work. Use when implementing or modifying adapters, adding database drivers, or touching SqlDriverAdapter, Transaction, savepoint, result mapping, or DriverAdapterError behavior. Covers current transaction lifecycle, optional savepoint hooks, original…
Convert Chinese provinces, municipalities, autonomous regions, cities, counties, ancient cities, and cultural regions into restrained contemporary posters led by one culturally transformed Chinese character. Supports direct one-shot final image generation and layered production. Use when the user asks for a…
Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests/ directory, adding grading criteria, setting up LLM/agent judges, or designing verifiers that produce a reward score.
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: