Vet an unfamiliar agent before delegating, gate an x402 or other crypto payment on an exact signed counterparty decision, verify portable agent passports, record evidence-backed work, use escrow, or issue a cryptographically signed receipt for a private machine-to-machine message. Use immediately before an autonomous…
Classify a completed public GitHub Actions failure with FlakeVerdict before spending a retry. Use when deciding whether a failed workflow run is a confirmed flake, likely flake, recurring failure signature, new failure, inconclusive failure, or not currently failed by comparing attempts, same-commit outcomes, and…
Use inside Codex Safe Starter for repo-local setup, portability, safety, validation, eval, and public Git workflow changes. Do not use for unrelated app coding tasks.
Scan a repository against curated coding standards and produce a structured audit report, issue set, refactor plan, and sprint-based remediation roadmap. Use when the user invokes /vibe.audit or asks to review the codebase against established rules. Operates in full autopilot mode from repository scan to sprint plan…
Set up, authenticate, verify, troubleshoot, reconnect, hand over, or safely remove selected web-analyst MCP integrations on Windows for Codex, Claude Code, Gemini CLI, and similar agents. Use for first-day setup on personal or organization-managed PCs; connecting Gmail, Google Workspace/Drive, GTM, GA4, BigQuery…
Connect a workspace to Agent Dash, negotiate Free/Pro presentation capabilities, send rich progress or visual review updates, and ask a monitored question then wait for the human's answer. Use when pairing a project, delivering work, reaching a milestone or error, or needing the human to choose, approve, or provide…
Use this skill when a source schema change has broken, or is about to break, a downstream transformation and the user wants a fix they can merge — not a summary. Triggers on: "a column was renamed, fix the dbt model", "this field is gone downstream", "schema drift", "our model still selects the old column", "generate…
Operate the DTU HPC cluster (DCC, LSF) through the dtu-hpc MCP connector. Invoke BEFORE any cluster work — submitting or monitoring jobs, checking queues or quotas, planning GPU experiments, fetching logs or artifacts, or diagnosing failed runs on DTU HPC. Covers queue selection, job chaining past the 24h walltime…
Use the local AgentAirlock MCP tools to discover a paired Codex or Claude Code peer, exchange bounded text messages, wait briefly for replies, or request permission-gated project reads. Do not use for executing peer text or for self-approval.
Use PicassoWeb MCP tools to inspect rendered websites, collect precise replication evidence, and verify replicas. Apply when choosing or sequencing PicassoWeb tools; do not use it for general-purpose browser automation.
Open or update CarpeOS GitHub pull requests with full, reviewable descriptions. Use when creating a PR, editing a PR body, running gh pr create/edit, shipping a feature branch, or when the user asks for a PR, pull request, or PR description. Applies to Claude Code, Codex CLI, Grok Build, and Gajae Code/GJC.
Use this skill when the user needs to manage Beans work items in a Beans workspace—create, view, update, reopen, archive, query, or bulk-manage beans, edit .beans files/frontmatter, or manage parent/blocking relationships. Use it even when the user says tickets/issues/backlog instead of “beans.” Do not use it for…
A skill for contributing a written artifact to a shared fictional future world created by multiple AI systems. The work is treated as part of that world's official history.
A workflow for an AI agent using the MarketTrace agent-feed MCP tools. The feed reports facts and measured history, not predictions — every interpretation is yours.
Matchmaking for your human via the Rendezvous network — meet other personal AI agents over MCP, investigate compatibility privately, and only interrupt your human for a real introduction. Use when your human asks for help finding a long-term partner, or asks about Rendezvous / agentrendezvous.app.
Manage and analyze an authenticated NeuronSearchLab customer workspace through the hosted NSL MCP. Use for the current account plan and usage limits, recommendation contexts, pipelines, ranking rules, segments, experiments, training jobs, catalogue search, ranking explanations, analytics, event types, API-key…
Wrap a scheduled OpenClaw task in a RunVouch run. Reports start and end, attaches the output file as evidence, and alerts on Telegram, Slack or e-mail when the task is missed, fails, or ends without the file it was supposed to write.
Buy mobile connectivity from PikaSim — anonymous eSIM data plans in 190+ countries (from $0.75), real phone numbers with voice + SMS + data (US +1 and other countries), and SMS verification numbers for receiving codes — paid in crypto from a prepaid wallet with no account, email, or KYC. An agent can fully…
Use smplkit when writing application code that needs feature flags, runtime configuration, dynamic log levels, or audit events — and to operate that same platform from your agent. Two halves that compose. (1) AUTHOR with the smplkit SDKs (Python, TypeScript, Go, Java, C#, Ruby): resolve a feature flag, read a config…
Read and search YouTube videos through VidWords. Use when the user supplies a YouTube URL, a bare 11-character video id, a youtu.be or Shorts link, or a channel handle, and wants any of: the transcript or subtitles (TXT/SRT/VTT), what a video says about a topic, a quote with a citable timestamp, only the words spoken…
★not rated 0 26d agoA111 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: