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.
Use when working on an agent task where AdaMAST failure-mode checkpoints, final submission gates, trace capture, taxonomy generation/refinement, or AdaMAST CLI setup should guide Codex. This skill helps Codex apply AdaMAST during software or research tasks, diagnose its own trajectory against the active taxonomy, and…
Audit-before-fix protocol — first find all gaps across 7 planes, prioritize, pin the gap table, and only then fix. Principle: never touch code until the full picture of problems is understood. Gap table → approval → flow-first per gap → library-first → plan → code. Use when: task begins with looking for problems…
Depth for Vitest tests of front- React 19 SPAs when DOM, RTL, TanStack Query hooks, or TanStack Router route-tree tests are needed. USE WHEN: adding jsdom or testing-library, writing tsx render or renderHook tests, testing createMemoryHistory plus RouterProvider, Suspense UI, or React 19 act fixtures. DO NOT USE WHEN…
A workflow skill that requires development work to move through specification, analysis, design, implementation, verification, and completion stages. It uses hooks and a state machine, which tracks and controls the current stage.
A Chinese-language investing guide based on MR Dang’s value-investing method. Value investing means judging businesses, cash flow, risks, and price instead of trying to predict short-term market moves.
Compose a long-form pin-point lesson from one paper and register it as a Zotero child note. Use when the user provides a PDF or paper title and wants a math-grounded, idea-genealogy, fundamental-why analysis rather than a quick summary. Contrast with the summary skill, which produces a shorter overview note.
Git diff for AI agent repository instructions. Shows the blast radius of AGENTS.md and CLAUDE.md changes. Use when Git cannot show which agent inherited the edit, a Codex vs Claude Code split, or why one path inherited a stack.
Surgical phrase splicing from real movies and TV shows via yarn.co. Takes any English phrase and slices it into the longest possible runs of words actually spoken on screen, then assembles a final reel where every word is delivered by a real actor. Triggers — "splice a line from movies", "make a fragmovie", "build a…
A coaching tool that finds habits in past coding-agent conversations that waste tokens, the text units used to process requests and responses, and suggests ways to reduce that waste.
Use when generating, reviewing, refactoring, or planning code in polyglot repositories and you need senior-engineer guidance for language choice, architecture, testing, security, performance, dependencies, concurrency, CPU/GPU use, release safety, and LLM coding guardrails.
Author or improve an ADD-method persona file (a .add/personas/ slug.md) — the project-fit requirements LENS the ADD engine validates and the design/build/verify/advisor surfaces load. Use when adding a domain expert to the ADD roster, when the add-worker persona mode must DRAFT a persona because none fits the task…
End-to-end clinical diagnostic reasoning skill. Takes a patient case (SCENARIO.md), runs multi-persona Bayesian reasoning rounds with textbook evidence and literature search, outputs structured DDx with likelihood ratios. Use when solving clinical cases, generating differential diagnoses, discussing clinical…
Forge design system for React. Use when writing any React UI in this project, when picking which component to use, when theming, when creating block templates, or when reviewing UI code for accessibility and anti-patterns. Covers components, tokens, theming, motion, patterns, a11y, and anti-patterns.
Discovery for an autonomous loop — find this turn's work instead of being handed it. Reads what changed since the last run (failed CI, new issues, merged commits), judges what's actually worth acting on, writes findings to a durable state file, and hands each off to the SDLC loop with a stop-condition. Use as the…
Use when working with Jira or Confluence from command line, including authentication, searching issues with JQL, bulk operations, sprint reports, or creating/updating work items using acli.
Turn chat-pasted text/links into a verified, translated, searchable wiki knowledge base. When a user pastes a link or text (in ANY channel — Discord, Slack, CLI, etc.), fetch+verify it, classify it (useful vs ad), translate+summarize it into the target language, save it to the wiki, and optionally alert on…
SEO Drift Monitor - detects when page changes break critical SEO elements. Baselines a page's SEO state, then checks for regressions in schema, headings, meta tags, canonical, and Core Web Vitals. Generates visual before/after reports. Use when user says "seo drift", "drift monitor", "baseline", "seo check", "did…
Use when you need to find, list, or read-and-summarize Obsidian vault notes mechanically — e.g., "find all NPC notes tied to faction X", "list all session N scene files", "read frontmatter of these 12 notes and return a table", "grep all Locations/ notes for wikilinks to [[NPC Name]]". Dispatches a Haiku subagent to…
Read and operate an authenticated personal RoamCode Node through its stable API.
★not rated 19 10d agoA21 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: