81,561 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Reads every file in sources/ and produces a schema-valid graph/graph.json plus a human-readable graph/graph.md. Every node and edge carries provenance; unsourced claims become explicit Assumption nodes. Rates corpus health and says so loudly when it is thin.
Carry your context across AI coding tools. Adds /carryover and /headroom commands plus a save-to-memory prompt at the end of each session, backed by the headroom proxy.
★not rated 5 3mo agoA
tokens not measured
originalMIT
Houdini toolkit including command-line tools, installation path detection, environment and package configuration, node help authoring, offline documentation lookup, and a bgeo/USD MCP server.
★not rated 5 2mo agoA
tokens not measured
originalMIT
Give Claude deep understanding of any video. Extracts 13 signals (keyframes, OCR, colors, motion, cursor, fonts, loading states, confidence scores) and exposes 17 MCP tools for building frontend code, design specs, tests, PRDs, changelogs, Storybook stories, and more.
★not rated 5 8mo agoA
tokens not measured
originalMIT
A development-triage and governance guide for deciding how a software request should be handled. It helps assess whether a task needs manual work, a script, an AI tool, or an automated agent.
Five commands for GitHub skills in Cowork: load from any repo, save iterated versions, share installed skills, sync updates, and auto-detect pasted URLs.
★not rated 5 7mo agoA
tokens not measured
originalMIT
Author, review, and test durable Botpipe 2.0 Python workflows. Use for workflow design, Provider or Codex calls, prompts, sessions, typed results, activities, artifacts, worklists, human input, concurrency, replay, recovery, and workflow packages.
Analyze Claude Code session cache efficiency — hourly timeline, cliff detection, trigger attribution, subagent cost breakdown. Run with no args for current session, or specify session ID / --since date / --list.
Copy a Markdown table to the macOS clipboard as HTML so pasting into Slack triggers Slack's "format as table?" prompt. Use whenever the user wants to send, paste, share, or post a table to Slack, or when the assistant has produced a Markdown table and Slack is mentioned. macOS only.
Inspect live Anvil Data Tables and invoke server callables from the terminal via the anvil-uplink-cli tool (anvil-bridge). Use when the user references an Anvil app, asks to query/read/inspect a Data Table row, needs to call an @anvil.server.callable function against a deployed app, or mentions files like anvil.yaml /…
Integrate mailbot API for AI agent email automation. Create programmable inboxes, send and receive emails, track delivery events, and handle email-based workflows via API, SDK, or MCP Server. Use when building AI agents that need email identity, when setting up agent-to-human communication, when replacing Gmail or…
Install Lights traffic-light status hooks into Claude Code's settings.json. Lights is a macOS menu-bar app that shows AI activity as a floating traffic light (red=executing, yellow=needs input, green=idle). Use this skill when the user mentions Lights, asks how to connect Lights to Claude Code, says "set up lights…
Interactive Q&A capture of company knowledge into typed nodes in a company-brain vault. Sub-modes - vision (dictation-friendly six-phase flow), for-doc (document-driven interview that walks a target doc's sections), product, persona, competitor, competitor-ifu, competitor-clearance, competitor-snapshot, metric…
Transcribe a video and add translated subtitles in any language, burned into the picture or as a selectable track. Takes an X/Twitter, YouTube, or any yt-dlp URL, or a local file.
★not rated 5 4mo agoA
tokens not measured
originalMIT
Human-in-the-loop context compaction for Claude Code. You choose which turns survive; a SessionStart hook re-injects them deterministically after every compact and resume.
★not rated 5 4mo agoA
tokens not measured
originalMIT
Two skills that bracket the moment an AI product's architecture gets decided: small-council-blueprint forces a written architecture before any code is touched, small-council-audit tears it apart before you build on it.
★not rated 5 3mo agoA
tokens not measured
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: