AI
Artificial intelligence, agents, language models, inference, and related research.
42 items
ZeroPointRepo/youtube-skills — YouTube transcripts, search and channel data for any agent
Skill pack (1.1k★, MIT) giving agents YouTube transcripts, video search, channel and playlist data through the TranscriptAPI backend — no yt-dlp, no headless browser, and it ships a Hermes install path.
thedotmack/claude-mem — persistent session memory for any agent
Memory layer (101k★, Apache-2.0, TypeScript) that captures everything an agent does during sessions, compresses it with AI, and injects the relevant context back into future sessions.
Forward-Future/loopy — the Loop Library for repeatable agent workflows
Catalog of practical AI-agent loops (3.2k★, MIT) plus an installable skill for finding, adapting and designing repeatable workflows — a loop is a playbook with built-in feedback, not a one-shot prompt.
addyosmani/agent-skills — production-grade engineering skills for coding agents
25 skills and 9 lifecycle slash commands (107k★, MIT) that encode senior-engineer workflows and quality gates — /spec → /plan → /build → /test → /review → /ship — for any agent.
VoiceStudio — open-source, fully-local ElevenLabs alternative
Self-contained local voice AI: voice cloning, voice design, video dubbing, dictation, transcription and audiobooks across 646 languages, 14 pluggable TTS engines.
Grok Bot Guides
x.ai's official guide series for Grok Bot: nine field reports on running teams of persistent cloud-computer agents, with copy-paste prompts and org patterns.
ZenNotes tui (zn)
Vim-first terminal notes app in one static Go binary: plain-markdown vault, kanban/calendar tasks, CSV databases, command palette — plus an MCP server so coding agents can use the same vault. MIT.
OpenContext
Personal context store for AI agents: capture, search, and reuse project knowledge across repos and agent CLIs (Codex/Claude Code/OpenCode), with a desktop GUI. MIT.
TheBlackCat Site Skill
The agent-side operating manual for this library: bookmark pipeline, blog draft-flag flow, weekly triage, and the Hugo site model — mirrored verbatim from the Hermes skill.
m3e-canvas
Browser sketchpad for Material 3 Expressive screens: drag real components, link screens into a tap-through prototype, export the design as a prompt for your AI coding tool. Static Next.js, no backend, MIT.
jakubkrehel/skills — Agent Skills for Building Great Interfaces
Collection of 11 agent skills (5.5k★) covering UI polish, typography, color systems, accessibility, layout, and product writing — installable in Claude Code, Hermes, and opencode.
TrueForge — the open-source agent harness
Self-hostable runtime that turns any LLM into a working agent — MCP tools, skills, sandboxing, approvals, subagents — exposed as a chat UI, HTTP API, and embeddable SDK.
tokscale — token usage tracker for AI coding agents
Rust CLI/TUI that parses local session files from 50+ AI coding agents (Claude Code, Codex, OpenCode, Cursor…) and reports token usage & cost — dense ratatui terminal dashboard, 2D/3D web contribution graph, optional global leaderboard.
Wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
Wayfinder
Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
Wait What
Stop. That last message did not land — re-pitch it.
Triage
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
To Tickets
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.
To Spec
Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
To Questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
TinyFish MCP — Web Infrastructure for AI Agents
Useful MCP server for agents, and the core endpoints are free.
Syllaby
Viral scripting and video research tool.
Setup Matt Pocock Skills
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
Resolving Merge Conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
Research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
Loop Me
Grill me about specs for the workflows I want to build, within this workspace.
Kimi K3 Founder Reveals the Future of AI Agents, Open Source AI & AI Coworkers
YouTube interview with the Kimi K3 founder on AI agents, open-source AI, and AI coworkers.
Implement
Implement a piece of work based on a spec or set of tickets.
Handoff
Compact the current conversation into a handoff document for another agent to pick up.
Grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Grill With Docs
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
Grill Me
A relentless interview to sharpen a plan or design.
Greek & Hebrew Word Study
Rigorous linguistic and lexical analysis framework for biblical Greek (Koine) and biblical Hebrew/Aramaic words, integrating Strong's concordance, morphological parsing, semantic ranges, Septuagint (LXX) mapping, and fallacy prevention.
Domain Modeling
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
Diagnosing Bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Cross-Testament Typology
Theological framework for analyzing biblical typology, intertestamental Old-to-New Testament connections, Christological fulfillment trajectories, and covenantal continuity while preventing allegorical over-interpretation.
Codebase Design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Code Review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
BlackCat Bookmark Skill
The Hermes Agent skill that automates adding bookmarks to this very library — the agent-side half of the Git-native workflow this repo is built around.
Biblical Exegete
Comprehensive 9-part scholarly framework for exegetical analysis of Scripture passages, chapters, and books across historical, cultural, literary, original-language (Greek/Hebrew), and theological dimensions.
Ask Matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
Analyze Repo
Deeply analyze a public GitHub repository by cloning it and applying a structured reverse-engineering framework. Trigger on phrases such as deeply analyze this GitHub repo, analyze this GitHub repo, deep analysis of repo, or when a GitHub URL is provided with an analysis request.
No matches
Nothing on this shelf fits those filters.