Turns a user-defined goal into a structured multi-tool workflow. It scans context, discovers available tools (skills, MCP servers, CLI tools, scripts, project commands), builds an execution plan, coordinates execution, handles blockers, verifies results, and returns a concise operational report. Use when a task spans…
Polish any GitHub repository's surface — labels (emoji rating tiers, P0–P3 priority, impact severity), issue forms, PR template, CI workflows, CODEOWNERS, rulesets, docs. Repo meta & config only — no code logic touched. Use when creating a new repo or polishing an existing one.
Escalation-only workflow for materially ambiguous, research-heavy, high-impact, cross-system, or failed-validation tasks. Do not load for clear, bounded, low-risk work; use the AGENTS fast path.
Jobgru pipeline Phase 1 — coordinate parallel job-board researchers to find and verify the user-requested count of unique jobs (LinkedIn has no per-run job cap; LeadGru is capped at 5 people + company people page), deduplicate against the Job Applications Google Sheet, append rows via scripts/sheetswrite.py, then…
Audit, initialize, upgrade, synchronize, discover, and safely curate a shared Agent Skills repository across Claude Code, Codex, Qwen Code, OpenCode, Pi, OpenClaw, and compatible hosts. Use when setting up a machine or server, finding top GitHub skills, checking skill or upstream drift, adding or updating a skill…
Runs a durable inspect/plan, implement, verify, and fresh-review loop toward an explicit repository goal. Preserves manually resumable state and uses oh-my-claudecode for autonomous continuation. Use only when the user explicitly invokes goal-loop.
Use when running the shikanime local dev loop: branching in a fresh jj workspace, push-to-origin, jj bookmark tracking, and landing via plain gh pr merge or direct push.
Use when checking appointment availability, booking services, monitoring for openings, or discovering venues at salons, spas, and restaurants. spot.discover finds and compares venues via Yelp before booking. Supports Acuity Scheduling, Square Appointments, Resy, Tock, SevenRooms, OpenTable, Meevo, Vagaro, Mindbody…
Agile development workflow for AI coding agents, usable from Codex, Claude Code, and any Agent Skills client. Use when the user asks to plan a GitHub issue, write a feature or bug specification, implement an issue, run validation checks, review a pull request, research a topic, or plan an epic. Also triggered by…
Set up and operate DMAF (Don't Miss A Face) — automated WhatsApp photo and video backup with face recognition and Google Photos upload. Use when a user wants to: (1) install and configure DMAF from scratch on GCP, (2) set up the OpenClaw WhatsApp media sync pipeline so group photos and videos flow automatically into…
Create, improve, validate, forward-test, and package Codex skills from a user's brief, examples, files, or instructions. Use when asked to design a new skill, update an existing SKILL.md, add references/scripts/assets, create agents/openai.yaml, validate skill structure, or prepare a skill for…
Test the Wayfinder agent extension UI by starting the dev environment and visually verifying changes via CDP. Covers the new tab page (left sidebar — Home, Scheduled Tasks, Settings, etc.) and the right side panel (chat interface). Use after making UI changes to apps/agent/.
Unified Airtable skill — MCP, public REST API, internal web API, Omni AI, scripting, formulas, webhooks, automations, field types, and gotchas. Auto-triggers on any Airtable task.
Use when creating, deploying, diagnosing, or operating a reusable ChatGPT-as-project-brain bridge for any local Codex project: initialize .ai-bridge state, expose read-only project evidence, expose a narrow stage-plan write connector, avoid stale/freeform connector schemas, and run the ChatGPT plan -> Codex execution…
Run one bounded trajectory reflection when repeated same-cause failures, contradicted assumptions, real-use failure after local green, material scope drift, a materially unresolved phase boundary, an unapproved authority-sensitive next effect, or user doubt suggests the current path may be wrong. Use Context Canvas…
A debugging workflow for WeChat DevTools, the development program used to build and test WeChat mini-programs. It checks build output, DevTools messages, output logs, and network errors, then summarizes problems and suggests fixes.
Locate Apple devices (iPhone, iPad, Mac, AirPods) via iCloud Find My using the findmy-agent CLI. Use this skill when the user asks to find an Apple device, check iPhone/iPad/Mac/AirPods location, locate lost AirPods, "Where's my iPhone", "Dov'è il mio Mac", verify if a device is home vs away, or check if devices are…
CLI for the Make.com automation platform. Manage organizations, teams, folders, scenarios, webhooks, connections, data stores, functions, and sync entire orgs to local disk for analysis. Also covers Make.com MCP server setup, zone configuration, blueprint analysis, and searching for properties across synced scenario…
Critical evaluation of proposed changes BEFORE their implementation. Use when: Need to evaluate proposed changes before implementation Want to reduce merge rejection risk Need to cut scope to minimum valuable change Require pre-implementation quality gate Builds structured JSON with decision (approve/revise/reject)…
Run the Cursor-backed Omnigent Trio loop from the current Claude/Codex UI session when the user explicitly says “Trio Omnigent”, “Omnigent Trio”, or invokes /trio-omnigent. Do not use for an ordinary native Trio request.
Load it when working with Bumfuzzle, or when project has Bumfuzzle import. When you asked to create new rule, or trigger any validation or verification after task is done.
★not rated 2 1mo agoA41 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: