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.
Expert assistant for ZMK and QMK keyboard firmware configs. Use when auditing or improving a zmk-config or QMK keymap, tuning home row mods or hold-taps, adding smart layers (numword, caps word), configuring trackballs, trackpads, trackpoints, encoders and per-layer input processors, generating keymap-drawer diagrams…
Build Account-Based Everything (ABX) GTM strategies for complex B2B sales. Use when working on ABM strategy, ICP scoring, messaging architecture, product launches, or pipeline acceleration for companies with <500 accounts, $100K+ deals, and 6+ month sales cycles.
Turn a startup idea, product, URL, pitch, or existing visual identity into a distinctive startup brand system and a polished standalone HTML report. Use when Codex needs to create or refine startup positioning, a salient brand idea, brand promise, tagline, messaging, voice, creative territories, logo or symbol…
A set of ideas attributed to Dan Koe about running a one-person business, writing, focus, personal growth, digital work, and how people think. It is based on 3,378 original posts, according to the description.
Provides expertise on Chroma Cloud integration for semantic search and hybrid search applications. Use when the user is working with Chroma Cloud, CloudClient, managed collections, Schema(), Search(), hybrid search, or Chroma Cloud CLI workflows.
Harness feedback-loop curator. Activate on demand to read friction tags from the harness-friction wing, cluster them, and open one issue per cluster on the canonical/feedback repos in provenance blocks. --deep sweeps wing=transcripts; auto mode (#42) runs scheduled.
Universal de-AI writing skill. Catches and rewrites the tells that expose AI-generated text — forbidden words ("delve", "crucial", "landscape", "tapestry", "Additionally"), forbidden patterns (rule of three, negative parallelism, em-dash overuse, Title Case headings, inline-header bullets, emoji headers…
You are documenting how this repository actually behaves, for a tool called HQFlow. HQFlow has no LLM of its own and never uploads code anywhere — it only renders the structured JSON files you write here, in .codehq/, as an interactive workflow canvas that a human can explore in their browser. Your job is to read the…
XTrace sessions must be explicitly named. For AI JSON, create sessions with args.name and use the same string in target.sessionid; do not rely on numeric or implicit latest sessions. CLI startup uses --name or -n , and later commands use -s . Session names may contain letters, digits, , -, and ., up to 256 characters.…
Create, refine, diagnose, and release adaptive WorkBuddy Dream Skin themes in this project, including image driven light or dark UI selection, lively nonblocking decorations, readable chat and artifact surfaces, external CDP injection, and strict visual auditing. Use for WorkBuddy skin design, theme JSON or CSS…
A guide for examining how a project uses large language models, including how often calls happen, how long they take, and how often they succeed. It uses code-flow documentation and call logs to locate optimization opportunities.
Legacy code archaeology and context bootstrap. Activated when the user mentions "legacy code", "código legado", "sistema antigo", "código sem documentação", "discover module", "entender módulo", "arqueologia de código", "código que ninguém entende", or runs /discover. Populates the empty upper layers of tiered lookup…
Generate AI avatar talking-head videos using HeyGen API. Single videos, multi-scene studio compositions, batch personalization from CSV/JSON, template variable injection, photo-to-avatar pipeline, video translation with lip-sync, Starfish TTS, credit estimation, and asset management. Use when user says "avatar video"…
Zod best practices, patterns, and API guidance for schema validation, parsing, error handling, and type inference in TypeScript applications, for Zod 4 and for projects still on Zod 3. Tells the two apart from the import specifier and the installed version, then applies the rule for that version. Covers safeParse…
Project code-review style for this repo. Review the current branch's changes in two passes (correctness + justify-every-line), tracing any bug claim to ground before reporting.
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
Google Search Console data analysis and site management via google-search-console-cli. Use when the user wants to check search performance, analyze queries, inspect URL index status, manage sitemaps, or view site properties. Triggers: "Search Console", "search performance", "search queries", "GSC", "index status"…
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: