Propagates approved corrections, decisions, terminology changes, and scope changes across related documents. In Resolution mode it consumes a review-findings Resolution file without re-deciding semantic choices; in Ad-hoc mode it first confirms the user-provided change set. Both modes perform impact analysis, present…
End-of-data-collection workflow. Exports raw MongoDB data as JSONL, writes a companion README documenting schema + provenance, commits both to the repo, and archives the raw dataset to Zenodo with a permanent DOI. Use when the user says "data collection is done", "freeze the data", "archive the raw data", "post the…
Plan a week of meals around the staples someone already keeps on hand. Produces an editable N-day plan (default 5 cooking nights + 2 flex days for leftovers or eating out), a grocery list grouped by store section, prep/cook notes with thaw/make-ahead timing, and short recipes. Optionally estimates per-plate calories…
This skill should be used when the user asks to "create a PR", "open a pull request", "submit my changes", "push and create PR", "finalize my work", "/pr", or wants to commit, validate, and push their current branch as a pull request. Handles the full workflow: commit all changes, run quality gates with best-effort…
Help a family discover colleges that are financially realistic for them — especially "hidden fit" schools that award substantial merit scholarships to families who won't qualify for need-based aid. Uses an embedded dataset of merit-aid generosity extracted from official Common Data Set filings for 300+ U.S. colleges.…
Converts episodic memory (corrections, lessons) into procedural memory (behavioral rules) by synthesizing them via LLM and injecting into SOUL.md or CLAUDE.md. This is the "learning loop" — past mistakes become standing rules.
Comprehensive code review for GitHub/GitLab pull/merge requests with Linear/Jira integration. Works globally from any directory - auto-clones repo if needed and compares against main branch.
Reviews written content (blog posts, articles, documentation, marketing copy) against a quality checklist and provides structured feedback. Use when the user asks to review, critique, edit, or improve any written content.
Alex Hormozi framework for creating lead magnets, free offers, CTAs, and trust funnels. Triggers on: create a lead magnet, free offer, mini offer, headline/name, CTA, engaged leads, funnel strategy, how do I get more leads, what should I give away.
Source discovery - find high-quality candidate URLs with Google operators rendered in a real Chrome session, multi-query strategies, and source-quality triage, emitting deduplicated lead JSON. Use when a task needs to locate official docs, papers, code repositories, community evidence, recent posts, or competitive…
Given a seed paper, model, method, or architecture, trace and analyze what later research did with it — which papers cite it, which actually extend or improve on it versus merely mention it, and how the notable follow-ups compare. Use this whenever the user points at a specific paper/architecture/model (by name or…
Survey and explore a DB2 for i (IBM i / AS/400) instance without stalling it — enumerate libraries, build table inventories and column dictionaries, find implicit join keys, identify live-vs-dead library copies. Use when connecting to an unknown or legacy IBM i / DB2 instance, when catalog queries…
A project-governance method for taking a new or existing product toward a production-ready minimum viable product (MVP). It provides planning levels, decision records, risk tracking, audits, and reusable templates for solo developers or small teams.
Use Context Router when a task requires project context, feature-specific retrieval, memory recall, strict run workflow slices, or session continuation.
Analyze deal stage based on LaunchDarkly's Customer Engagement Process (CEP). Compares completed and missing activities against stage criteria to recommend the correct opportunity stage.
Explain complex topics with the clearest useful visual artifact. Use when the user asks for visual explanations, Mermaid diagrams, images, screenshots, GPT-generated images, Ian/Xiaohei-style conceptual illustrations, teaching aids, architecture diagrams, workflows, state diagrams, data/ranking flows, UI behavior…
Install or maintain market-brief, a scheduled Codex/Claude task that scans Discord and WeChat investing chats, writes an hourly report, pushes it to WeChat, and optionally runs an inbound WeChat listener with MCP tools. Requires chatlog, wxstore, and discord-selfbot MCP servers.
Guided ITR-2 / ITR-3 filing assistant for a resident Indian individual for AY 2026-27 (FY 2025-26). Selects the correct form (ITR-2 vs ITR-3) based on the presence of business/professional income, walks through every applicable schedule one at a time, flags missing inputs as NEEDS INPUT, computes tax under both Old…
Build an offline evaluation set so you can compare LLM prompts and models quantitatively. Invoke when building or iterating on any LLM-powered feature.
Generate valid JSON-LD structured data for any page type. Trigger: 'generate schema for [page type]' or 'schema [URL]'.
★not rated 2 7mo agoA31 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: