Agile planning + execution for AI coding agents: grill the idea, plan with OKRs, adversarial critic panel with kill authority, cheap-model story cards, parallel wave execution, demo-brief review gates.
★not rated 3 2mo agoA
tokens not measured
originalMIT
Keeps shared validation branches (dev/test/uat/staging) out of work and production branches: a skill that teaches the one-way integration workflow, a PreToolUse hook that blocks forbidden git flows, and a release audit script.
★not rated 3 3mo agoA
tokens not measured
originalMIT
Installable agent skills mapped to the Nen system: performance, refactoring, launch, reverse engineering, reliability, orchestration, hatsu (forge new skills), en — auto-routing that reads the problem shape and engages the right abilities — and vow, pre-commitments declared before work and audited before done.
★not rated 3 1mo agoA
tokens not measured
originalMIT
Maps your projects into a living architecture graph: scan a directory of repos, sync the graph to the quasar-graph backend, then use it as a map — graph-aware context, cross-repo research, one-command stack cloning, and in-place graph editing.
★not rated 3 1mo agoA
tokens not measured
originalMIT
Plans before it edits, routes each step to haiku, sonnet or opus by cost, and verifies four ways per wave. Ships tiered subagents, authoring skills, local MCP tools, and gated fail-open hooks.
★not rated 3
changed 8d agoA
tokens not measured
originalMIT
An operating system for data leaders and data product managers: Product decisions, team handoffs and analyst evidence graphs, with domain applications for healthcare, marketing, logistics/ops and ecommerce.
★not rated 3
changed 2d agoA
tokens not measured
originalMIT
Quick AI reviewer for Agent Skills: checks structure, workflow, references, and links. Clear report without jargon, with a summary from an exhausted data scientist.
★not rated 3 3mo agoA
tokens not measured
originalMIT
Skills that keep a codebase healthy as agents work in it: repo orientation, docstring discipline, doc freshness, test coverage for new code, and pre-commit verification gates.
★not rated 3 4mo agoA
tokens not measured
originalMIT
Composable writing instructions on four orthogonal axes (Voice, Tone, Style, Format): pick one entry per axis and the builder assembles a ready-to-paste prompt prefix that steers any LLM toward a precise register, reasoning pattern, and layout. Ships 97 curated entries, 1193 worked examples, 158 diff-pairs, and 14…
Buy-vs-build mode. Forces agents to check standard library, native platform, already-installed dependencies, open source, commercial options, then build in-house only when warranted.
★not rated 3 2mo agoA
tokens not measured
originalMIT
SessionStart and SubagentStart hooks that inject the GraphSmith multi-agent discipline (from the repo's canonical SKILL.md) into context for every session and every Task-spawned subagent from the moment it starts.
★not rated 3 todayA
tokens not measured
originalMIT
A surprise pop quiz for developers: after the agent implements something for you, it springs an oral exam on the concepts, terms, and design tradeoffs of the work — so you actually understand what was built and why, and make better decisions next time.
★not rated 3 2mo agoA
tokens not measured
originalMIT
Integración de envíos con Correo Argentino (apiMiCorreo) para ecommerce: auth + customerId, cotización, sucursales, creación de envíos, tracking, crons y emails de estado. Contratos reales verificados en producción + arquitectura multi-tenant.
★not rated 3 2mo agoA
tokens not measured
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: