Recursive governance for Executable Operating Units (EOUs). Faceted classification, generating-EOU constraints, ECP-governed change, no-self-approval. Install in any project that needs to turn messy workflows into auditable, retirable operating units.
★not rated 10 19d agoA
tokens not measured
originalISC
Multi-agent task orchestration with visual terminal panes. Decomposes complex dev tasks into parallel Claude Code instances coordinated through dependency-aware waves.
ETYB — engineering co-pilot behind a single /etyb skill: senior-leader routing to specialist roles, TDD/verification/review discipline, and currency-stamped vendor stacks for post-cutoff platform facts.
★not rated 10 2mo agoA
tokens not measured
originalMIT
Several models on the same question at once — Claude sub-agents, OpenAI Codex and a cheap third via OpenCode. Review code (code-review), check whether the work is actually finished rather than finished-looking (check-if-done), brainstorm wide with a different model per cognitive frame (adhd), or just ask all of t.
★not rated 10▲
+1
changed todayA
tokens not measured
originalMIT
Dev skills I use day to day in agentic engineering, focused on multi-agent-driven work modes and long-horizon autonomous tasks. Includes long-horizon, fan-out, handoff, ctx-research, ctx-grill, to-ctx, just-ask, and the lowband and readout modes.
Installs graph engineering into a project that has none: turns an existing process — skills, a runbook, a CI config, or a description — into a guarded graph with typed nodes, total exit guards, bounded retry loops, a run-state file, a skipped-step ledger, its own auditor, and an executable eval suite. Domain-agnostic.
★not rated 10▲
+1 22d agoA
tokens not measured
originalMIT
AI data-flow governance for coding agents: run borderlint before adding any AI SDK, endpoint, or model id — residency, sovereignty, and provenance checked in the conversation, before commit.
★not rated 10▲
+3 2d agoA
tokens not measured
originalMIT
Power Platform from your AI client: build and debug flows, manage connections, run desktop flows (RPA) and work queues, administer Dataverse, Power Pages, and tenant governance.
Persistent memory and receipt-verified workflows for Claude Code — /spec plans, reviews, and executes with quality gates; plus security audits, code reviews, test generation, and release prep from /attune.
★not rated 10
changed 3d agoA
tokens not measured
originalApache-2.0
Portable, plugin-ready bundle of ICN's Claude Code agent tooling: preflight/truth-sync/authority-spine/route-impact/navigator skills, specialist subagents, advisory hooks, and the icn-ops MCP launch. Safe-by-default; complements (does not replace) the repository's project-local .claude/ config.
★not rated 10 yesterdayA
tokens not measured
AGPL-3.0
Connect Gemini CLI to 700+ apps (Gmail, Slack, Stripe, Shopify, HubSpot, Notion, Linear, Salesforce, QuickBooks and more) through One's hosted MCP server. Four tools: list connected integrations, search a platform's actions, read an action's real API documentation, and execute it. OAuth sign-in, nothing to install.
★not rated 10 3d agoA
tokens not measured
originalMIT
Turn a how-to video into a reusable skill for your AI coding agent. Watches the video locally (frames + transcript, no API keys), breaks the procedure down, writes the skill, and proves it works.
★not rated 9 1mo agoA
tokens not measured
originalMIT
A meta-skill that learns a person's writing voice from their own samples and iterative edits, then compiles it into a durable, reusable voice skill for future agents.
★not rated 9 2mo agoA
tokens not measured
originalMIT
SpecRails Agent Workflow System — product-driven AI development pipeline. Installs 14 specialized agents and 20+ workflow skills: /specrails:implement, /specrails:setup, /specrails:get-backlog-specs, and more.
★not rated 9 todayA
tokens not measured
originalMIT
7 specialist agents (PO, Scrum Master, Dev, QA, PR Reviewer, Security, Tech Lead) + 30 slash commands for collaborative agile ceremonies with persistent team memory. Works with any language or framework.
Sixteen installable skills for diagnosing, designing, governing, and scaling enterprise AI transformation. Distilled from 21 flagship sources (Stanford, MIT, McKinsey, BCG, Deloitte, PwC, Accenture, NIST, EU AI Act, IMDA, WEF).
★not rated 9 2mo 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: