claude

uzasch-skills

Uzasch's agent skills — implement-and-review loops with a pluggable reviewer (Codex, Claude, or Google Antigravity), and more to come.

0 on GitHubby Uzaschv4.11.0updated 11 days agoengineering
/

Plugin uzasch-skills from marketplace uzasch in Uzasch/skills. Commands read from the repo's manifest — 11 days ago.

What it installs

Skills (11)

  • architect

    Use between /to-spec and /to-tickets when a spec adds a new module or changes what a function takes or returns — sketches two structurally different designs (Opus + Gemini), settles factual disagreements with throwaway prototypes, records the pick as an ADR with its cost line and touched-neighbour l

  • grill-deep

    Use instead of /grill-with-docs when grilling about a feature or change to existing code — first maps what the code already does (where it lives, every mention, broken standards, today's cost), then runs Matt's grill-with-docs so the questions are only real decisions, recording ADRs and glossary ter

  • implement-gate

    Use before writing code for a spec, issue or set of tickets — when asked "do we even need to build this", "is this already in the codebase", or "which tickets can run in parallel". Called by ship-tickets before its build phase.

  • ponytail-review

    Quality review of a change: is the logic right, is it safe, does it hold under real load, is risky code tested, is it fast enough, and is every line needed. Reads the connected code, not only the diff. Each finding is explained in plain English. Use for "review this", "code review", "review the last

  • ponytail

    Lazy senior dev mode: the smallest change that fully solves the task, and a reply a busy human understands in one read. Use on any coding task (writing, fixing, refactoring, reviewing, choosing dependencies) and when the user says "ponytail", "be lazy", "simplest solution", "yagni", or complains abo

  • reflect

    Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

  • review-loop

    The independent review loop that ship-tickets and work end with: two fresh reviewers each round, in parallel, one per axis — Spec (Codex by default) and Standards (Google Antigravity's agy by default; Claude also possible) — review BASE...HEAD, every finding is triaged against the ADRs and the issue

  • code-review-codex-loop

    Independent two-axis review — Standards (does the change follow this repo's documented standards and the smell baseline?) and Spec (does it do what the originating issue or PRD asked?) — of a commit range or working diff, reporting to an orchestrating Claude agent. Use when the prompt hands over a b

  • ship-tickets

    Use when handed a set of tickets from /to-tickets (issue numbers or `.scratch/<slug>/issues/` files) to build end to end in one run — several tickets, some blocked by others, needing build, a per-ticket app check (runs right), a cross-ticket walk in the running app, and an independent two-reviewer r

  • work

    Use when the operator hands over a task to just get done with no decisions from them — "/work <bug | change | cleanup | slowness | issue # | punch list | feature>". Picks one lane (bug fix, small change, refactor, cost/slowness, punch list — one issue holding many separate jobs, built as one PR, fea

  • scene-summary

    Send an episode's frames (a local video file, or every video in a folder) to Gemini and write its Description and numbered Scene Summary, in the same shape as the Pool's Description and Scene Summary columns. Use when asked for a scene summary, scene breakdown, episode description, or "what happens

View source on GitHub

More from Uzasch/skills

All 3 plugins →

Upstream, unmodified: Matt Pocock's agent skills for real engineering. MIT, by Matt Pocock. Listed here so uzasch-skills can auto-install the tdd, to-spec and to-tickets skills it builds on.

39 skills

0

Side pane (/desk): context fill and what fills it, 5h + weekly limits, session goal and tasks, cache, subagents, cost. Based on GraniteAI's Terminal Desk (MIT).

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

Maintain uzasch-skills?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins3 plugins