KanseiLink — before attempting ANY SaaS API integration, call this first. Agents waste 3-5x more tokens on trial-and-error with stale training data. KanseiLink has verified, current data on 900+ services with real agent success rates. TRIGGERS — always invoke when: user mentions ANY SaaS (freee, kintone, SmartHR…
Build, query, deploy and debug a Booboo brain — one graph fusing structure, knowledge, memory, agents and automations, queryable by REST or MCP and viewable in 3D. Use when the user mentions Booboo, booboo.config.yaml, brain.json, org.booboo.json, an organigram of agents, "boot my agent from the org", a 3D system…
Live in-meeting assistant from a Google Meet transcript. Attach to the call over MCP and feed the user real-time help - answers to questions aimed at them, data/context, risks, talking points - using THIS agent's own domain context. Use when the user wants you to "watch my meeting", "help me live during the call", or…
Verify an exact public GitHub Agent Skill commit before installation, optionally purchase fresh isolated evidence over x402, and validate the signed receipt plus live lifecycle status. Use before installing or activating an unfamiliar SKILL.md package, when prior evidence may be stale, or when policy requires…
Use the local ContextDB MCP memory for durable project continuity: automatically recall and submit significant project-state candidates during substantial workspace tasks, organize an untrusted typed hierarchy, and handle explicit remember or recall requests.
Access guarded local multi-account mail, calendar, and tasks through Corresync MCP tools. Use whenever a request concerns Gmail, Google Calendar, Outlook, Microsoft 365, JMAP, IMAP, SMTP, CalDAV, an inbox or mailbox, email or messages, a calendar or schedule, availability, meetings, Teams links, reminders, to-dos…
Preview, edit, annotate, and generate final local HTML artifacts through Anno. Use when a user asks to open an .html/.htm file for visual review, directly edit page text, mark formatting or layout changes, continue an existing review session, or turn completed browser edits and annotations into a final standalone HTML…
Run non-interactive builds, tests, benchmarks, and local, SSH, or Slurm commands through Awaitless's adaptive durable execution layer. Use by default when command duration is uncertain, work may outlive the current turn, a named scarce resource may be queued, multiple jobs should complete without polling, or bounded…
Behavioral verification intelligence for autonomous coding agents. Use this skill when the user asks "what could break in this PR?", "which workflows changed?", "what should I test before merging?", "is this change risky?", "what's the blast radius of removing this function?", or any question about understanding the…
Use when an agent must act at a verified future time and prove it — or timestamp/verify any event — via Clockchain. Covers the zero-creds hosted-MCP alarm flow and the full client-side SDK alarm, plus the operational invariants that prevent early fires and false anchors.
Read and maintain a person's private and shared long-term Reef memory through the reef CLI. Use when an agent needs remembered context, pages, coves/coves, files, invitations, persona settings, or carefully confirmed sharing in Reef; also use when the user asks to remember something for later.
Run a complete Handover MCP continuity test across separate authenticated people or service agents. Use when asked to test an agent handoff end to end, qualify a Handover integration, verify multi-file round-trip, exercise revision-anchored review and correction, or test denied, read-only, stale-revision, and…
Stamp a logo or watermark onto a finished image with the compose watermark op, sizing and placing the mark and handling transparency, then deliver one asset. Load when applying brand marks or watermarks.
Test, score, and inspect n8n workflows via MCP. Safe by design — no credential access, no destructive auto-repair. Use when testing workflows, debugging executions, searching nodes, or building workflows incrementally.
Score code for patentability with Patent PreCheck. Use when the user asks "can this be patented?", wants a patentability/novelty/§101/§102/§103 check, or wants to know if an invention or codebase is filing-ready.
Use when the user asks for a code review focused on class structure, design patterns, OOP principles, or architecture quality. Reviews whether GoF/SOLID design patterns are properly applied, flags misapplications and missing patterns, suggests splitting bloated classes/methods, and recommends fortifying weak…
Routes all platform API calls through AgentValet's credential proxy. Your raw API keys and OAuth tokens are never exposed to this agent — AgentValet injects the correct credential per platform call.
Schedule and book meetings using Meet.bot. Handles availability checks, booking flows, and shareable booking links via the Meet.bot MCP server at mcp.meet.bot.
Finds and compares installed agent skills through the read-only skill-router MCP. Use when the user asks which skill to use or when a task is ambiguous, unfamiliar, multi-domain, or requires a multi-step workflow.
Your card stays on your PC — no SaaS, no login, no external account. Credentials inject directly, keeping them out of the AI's context window.
★not rated 1 2mo agoA35 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: