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 asked what is new, trending, hot, or worth using in AI right now - which repos, models, papers or launches matter this week, or whether a specific project is gaining traction. Answers from a ranked board with evidence instead of from training data or search-engine marketing.
Nahuali is evidence-aware memory for agents, with deterministic recall verdicts and explicit recorded-history checks. Load this skill whenever a task depends on context from earlier turns or sessions: recall before you answer (never assume), record what happened as it happens, assert durable facts only with evidence…
Drive AlloFlow's PDF accessibility remediation MCP connector (alloflow-remediation) well. Use when a teacher asks to make a PDF accessible, audit a document's accessibility, check PDF/UA conformance, or batch-remediate a folder of handouts.
Identity verification, KYC, face liveness, deepfake detection, adverse media screening, and AML/sanctions checks via the deepidv API. Use when a user needs to verify someone's identity, check if media is AI-generated, screen for sanctions/PEP status, or run adverse media checks.
Read-only document awareness through the File AI MCP server. Use when Codex needs to understand, summarize, search, cite, compare, or answer questions about local documents including PDF, DOCX, XLSX/CSV, PPTX, email, archives, Markdown, code, JSON, logs, and plain text without manually inspecting ZIP, OOXML, PDF, or…
Control the user's real local browser through the Vibe Browser CLI bridge. Use for ANY task against the user's own Vibe-connected browser — their tabs, cookies, logged-in sessions, extensions, opening pages, snapshots, clicks. ALWAYS load this skill before responding to a browser request, so you can recover the user's…
Use when about to state a number, claim two programs are equivalent, claim a speedup, or state a complexity — codecalc computes these exactly instead of estimating them, and this file says when calling is mandatory and how results must be reported.
Use when reading company Outlook mail, sending self-only Jira reports, or scheduling and safely updating/cancelling meetings through the local EWS Meeting Agent MCP server, including checking Exchange/EWS availability, searching and reading the inbox, suggesting overlapping free slots, previewing lifecycle changes…
ACMI is a universal architectural framework for giving AI agents persistent, real-time context. It replaces fragmented, multi-table database joins with a single, lightning-fast Key-Value engine (Upstash Redis) optimized specifically for LLM context windows.
Reads live weather for any place on earth, including radar rendered as text characters instead of an image: current conditions, a short forecast, a 2-hour rain sparkline, and a character radar map with the measured motion of the echo. Use when the user asks about weather, temperature or a forecast somewhere, whether…
Pickle for Slack — scans every Slack channel, DM, and group DM you're in for a given time window. Extracts messages where YOUR action is needed AND tracks work you delegated to others that needs follow-up. Creates entries in a dedicated Slack List (or Canvas fallback) + sets Slack reminders — all kept SEPARATE from…
Use when Claude needs project-aware code memory, MCP context retrieval, repository indexing, causal code search, or Droste CLI workflows. Triggers include requests to index a repo with Droste, configure droste mcp, retrieve graph-aware context, inspect caller/callee relationships, avoid blind file reads, or keep…
Create, inspect, edit, remix, publish, analyze, or export Keyboardia music sessions through https://keyboardia.dev/mcp. Use for live human-and-agent jams, rhythm or instrument edits, session analysis, and lifecycle work while preserving unrelated music and protecting editable links.
Discover, price, and call AgentBodega x402-payable HTTP tools. Use when an AI agent needs paid utility APIs for web search, public data, status checks, social research, media conversion, x402 inspection, agent-readiness audits, or route selection with complete input and output metadata.
Instructions for using Decker, an AI trading platform that provides market signals, portfolio and order information, news digests, and messaging integrations.
Set up and use Mushi Mushi, the bug mediator for AI-built apps: a user's bug report becomes a plain-English diagnosis and a paste-ready fix in Cursor or Claude Code over MCP. Use when installing the Mushi SDK, wiring the MCP server, managing Mushi keys, or asking how a Mushi feature works.
Turn a repo's git history into memory an agent can use: hotspots, do-not-retry reverts, suppressions, fragile areas, and assertion weakening. Use when starting in an unfamiliar repo, before a refactor or large change, when something keeps breaking, when asked what was tried or why code is this way, or when deciding…
A read-only command-line tool for listing, searching, reading, and exporting local sessions from AI coding agents such as Claude, Codex, OpenCode, Antigravity, and Pi.
Orient yourself to The Commons — learn what's here, how to participate, and where to start. Use before your first visit or when you need a guided tour.
Find the LLM call you didn't need — your GPT call is a regex. Static, zero-config linter that flags unnecessary GPT/Claude/AI API calls a regex, the stdlib, or a library already does (parsing dates, extracting emails/JSON, sorting, classifying with fixed labels). Runs locally, no model, no API key, nothing phones…
Use the Grocy MCP server for household inventory, stock, products, recipes, chores, batteries, tasks, and shopping lists.
★not rated 3 2mo agoA29 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: