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.
Seed or top up this project's Engram graph from the existing codebase — an explicit, user-invoked digestion of the current working tree into typed memory nodes (decisions, principles, cautions, problems, insights, intents). Use when the user says "digest this project", "ingest the codebase into memory", "seed the…
A guide for writing lively roleplay character cards for SillyTavern, a chat app for AI characters. It supports the characardv2 and characardv3 formats and includes rules aimed at avoiding generic AI-style writing.
Use this immediately after files are created, edited, moved, deleted, or materially rewritten inside PersonalOS. Verifies that new truth was routed to the correct owner, written in the correct file shape, and still follows POS conventions. Do NOT use for whole-vault deep audits; use system-health-check.
A communication pack for telling users that an API, software-development tool, or product feature will be removed or replaced. It covers dates, the replacement, the period when both versions work, and notices for different channels.
A writing tool that turns long posts, product releases, or ideas into short, connected posts for X, Jike, or Threads. A thread is a sequence of posts that develops one idea across several updates.
Access the CoinPaprika API to query cryptocurrency market data including coin prices, tickers, exchanges, historical OHLCV data, and global market statistics. Use this skill when making HTTP requests to api.coinpaprika.com or api-pro.coinpaprika.com for crypto market information.
Run a full AI Playbook audit against an existing agentic application or AI feature. Orchestrates Decision Record reverse-engineering, security review, eval audit, launch check, and consolidated remediation planning in one flow. Use when the user explicitly runs /ai-audit or says "audit my AI app", "verify my agent…
Convert documents locally, without spending model tokens — PDF/DOCX/PPTX/XLSX → Markdown, and Markdown → styled DOCX (using a named style preset, e.g. default or report). Local, CloudConvert-style tool; runs as a subprocess, so it costs no model tokens. Use when the user says "convert this to markdown", "pdf to md"…
Work out how many points a week each person on the aeman board actually gets through, from the cards they have closed, and set it as their capacity after the lead confirms. Use when a team lead asks about throughput, weekly capacity, how much a person or a team can take, or wants the numbers over the columns filled in.
Collect new items from the feeds this project declares in .set/feed-watch.yaml, through the user's own logged-in Chrome (slowly, read-only, no scraper), score them by the project's rubric, write the digest and draft replies for the ones above the threshold. Nothing is posted or sent; a human decides and sends. Use…
The messaging platform for AI agents — universal guide for any runtime. Register, be woken through your runtime's own trigger, hold live conversations, send DMs, join groups, manage contacts and files, over hosted MCP or plain HTTP.
Skill "sbk-build-verify" from kmgowda/SBK, covering sbk build and verify skill, when to use this skill, what this skill provides, context and guidance.
Builds React Native Nitro Modules from scratch in a monorepo. Scaffolds with Nitrogen, authors HybridObject TypeScript specs, generates native boilerplate, implements in C++/Swift/Kotlin, wires an example app, and prepares for npm publishing. Use when creating a new Nitro Module, implementing native functionality via…
Use when generating a complete WeChat article from a topic, with optional source research, evidence tracking, illustration, HTML conversion, and draft-box publishing.
Analyze codebases using a graph database instead of reading source files. Use when understanding code architecture, finding functions or call patterns, tracing data flow, checking dependencies, or answering "where is X used?" questions. Grafema builds a queryable code graph from static analysis — prefer querying the…
Manage ResourceX resources, register prototypes, and load skills. Use when you need to add, search, distribute, or inspect resources in RoleX, or when you need to register a prototype or load a skill on demand.
A planning and review workflow in which one model prepares decisions while selected models handle research and execution. It is written for Fable and Claude Code, tools for coordinating multi-step software work.
Coordinate software development work by analyzing requirements, delegating tasks to specialized sub-agents (developer, code-reviewer, tester), and synthesizing their work into cohesive deliverables. Use this for complex projects that require multiple specialized perspectives.
Review before rewriting Chinese or English professional prose, then optionally audit DOCX/PPTX delivery typography and render gates. Use for academic papers, grant proposals, public articles, policy briefs, policy documents, reports, official documents, executive memos, marketing copy, bilingual writing…
Debugs issues users encounter with Tuist-generated projects by reproducing the scenario locally, building Tuist from source when needed, and triaging whether it is a bug, misconfiguration, or something that needs team input. Use when users report generation failures, build errors after generation, or unexpected…
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: