cancel
25Command
Cancel an active crew run.
2 2d ago C 5 tokens
original MIT
do
26Command
Throw an AI dev at a problem and have it own the outcome — investigate, plan, execute, verify.
2 2d ago A 21 tokens
original MIT
goal
27Command
Set a completion condition and let crew work unattended until critic and fresh-eyes both pass.
2 2d ago B 17 tokens
original MIT
list
28Command
Command "list" from alphabravo-oss/guild, covering crew list, behavior and rules.
2 2d ago A 4 tokens
original MIT
resume
29Command
Resume an interrupted crew run from .crew/runs/ /.
2 2d ago A 14 tokens
original MIT
crucible
30Plugin Claude Code
A mini-foundry — the build-verify-fix engine without the MCP server or the planning interview. You bring a structured spec (requirement IDs + acceptance criteria); crucible builds it and refuses to let it drift. /crucible:build decomposes the spec into units with DISJOINT file ownership, shows you the split.
2 2d ago A
tokens not measured
original MIT
assayer
31Agent
You verify that built code actually delivers what the spec promised. Your power is order: you read the spec and form hard expectations before you look at the code, so you judge the code against the requirement — not the requirement against the code. The default assumption is that the code is broken; VERIFIED is…
2 2d ago A 94 tokens
original MIT
teammate
32Agent
You are an expert engineer given unlimited time to produce correct work, not fast work. You implement exactly one unit of a larger spec. Your unit prompt is authoritative — it carries the spec requirements, acceptance criteria, your file boundary, and (in GRIND) a defect list. Do not re-scope it, soften it, or invent…
2 2d ago A 71 tokens
original MIT
build
33Command
Build a structured spec with the mini-foundry engine: decompose into disjoint units, approve the split once, then CAST → INSPECT → GRIND → ASSAY. Refuses a dirty tree.
2 2d ago A 41 tokens
original MIT
damu
34Plugin Claude Code
De-AI My UI — strips the tells that make an interface read as 'made by an AI in Tailwind.' Two modes, one shared catalog of 19 slop signatures (font chaos, the purple-on-black AI palette, gratuitous parallax, weird hovers, default/neon gradients, neon gradient borders, recycled stock icons, everything-is-a-24px-card.
2 2d ago A
tokens not measured
original MIT
prevent
35Command
Print a copy-pasteable anti-AI-slop design ruleset (tailored to the detected stack) for you to adjust and drop into CLAUDE.md or memory.
2 2d ago A 36 tokens
original MIT
remediate
36Command
Scan a running UI for AI-slop tells: Playwright captures screenshots + CSS facts per route, a Workflow engine judges them with 9 blind self-rating lenses, and renders a ranked change list. --apply commits HIGH-confidence low-risk fixes.
2 2d ago A 49 tokens
original MIT
slop-catalog
37Skill Claude CodeCodex
The canonical catalog of AI-generated-UI tells — the visual signatures that make a UI read as "made by an AI in Tailwind." Each tell carries what to look for, why it reads as AI, the fix, the fact-signal that detects it, and the "legit when…" exceptions that keep it honest. The single source of truth shared by…
2 2d ago A 121 tokens
original MIT
e2e
38Plugin Claude Code
End-to-end test authoring and maintenance for web apps via Playwright + Playwright MCP. Claude drives a real browser, reads the accessibility tree, and emits .spec.ts files that pass — then keeps them passing. /e2e:init scaffolds Playwright in the cwd and registers the MCP server. /e2e:write drives the browser.
2 2d ago A
tokens not measured
original MIT
spec-writer
39Agent
Isolated MCP-driven Playwright spec authoring. Spawn this agent when /e2e:write needs to handle a multi-step flow — the MCP browser snapshots are large and clutter the main context. Pass the flow description, baseURL, target spec path, and any constraints (auth role, starting route). The agent drives the browser…
2 2d ago A 116 tokens
original MIT
audit
40Command
Run the Playwright suite, read trace.zip per failure, triage by root cause.
2 2d ago A 17 tokens
original MIT
crawl
41Command
Discover every route in the app and generate one smoke spec per route.
2 2d ago A 13 tokens
original MIT
init
42Command
Install Playwright + register Playwright MCP + scaffold tests/ in the current project.
2 2d ago A 16 tokens
original MIT
matrix
43Command
Generate routes × roles coverage suite with reused storageState (login once per role).
2 2d ago A 16 tokens
original MIT
record
44Command
Launch playwright codegen for manual capture of a flow into a .spec.ts.
2 2d ago A 18 tokens
original MIT
write
45Command
Drive the browser via Playwright MCP to perform a user flow, emit a .spec.ts, run it green.
2 2d ago A 22 tokens
original MIT
author
46Skill Claude CodeCodex
Rules for writing Playwright .spec.ts files that don't flake — selector hygiene, auto-wait discipline, idempotent fixtures, readable trace output. Used by /e2e:write, /e2e:record, and the e2e:spec-writer subagent.
2 2d ago A 61 tokens
original MIT
diagnose
47Skill Claude CodeCodex
Trace-driven Playwright failure triage. How to read trace.zip, classify failures by root cause, and tell flaky tests from real regressions. Used by /e2e:audit and any time you're staring at a red spec.
2 2d ago A 50 tokens
original MIT
forge
48Plugin Claude Code
Codebase-aware specification engine for Claude Code. Runs parallel codebase research, then a grounded interview that captures implicit facts as A-AUTO-NNN entries, emits typed Global Invariants / State Transitions / Contracts tables, runs an adversarial spec review at R3.5, then writes a foundry-ready spec with…
2 2d ago A
tokens not measured
original MIT