Skill catalog
Every skill in the pack is a plain-Markdown SKILL.md folder you can read before an agent runs it. Six lanes: orchestration, code review and CI, design and copy, SEO and visibility, iOS and Android shipping, and creator rights. This catalog links each skill to its deep docs and its source folder on GitHub.
$ /plugin marketplace add JasonColapietro/suede-creator-skills $ /plugin install suede-skills@suede
Works in Claude Code today; Codex and other agents install from the GitHub repo. All paths on the install page.
Five entry points cover most sessions. Everything else is one lane down.
Use it for broad, authorized outcomes that deserve maximum useful effort: one controller, non-colliding lanes, consequential reasoning, adversarial review, and an evidence-backed finish.
Install this first. It routes an agent across every lane in the pack: agent teams, code review and A-F grading, CI ship-gates, AI evals, Suedify, design, conversion copy, SEO/AEO/GEO/AI EO, visibility grading, launch packaging, MCP QA, and the creator toolkit.
Claude judges, Codex generates. The orchestrator decomposes a high-volume job, writes self-contained briefs, spawns parallel OpenAI Codex CLI workers billed to your ChatGPT plan, then reviews every output against acceptance criteria before anything ships.
Deep review with TypeScript, React, Next.js, OWASP, and database checklists, an A-F letter verdict across 7 evidence-backed lanes with instant-F triggers, and CI that actually blocks the merge.
One-name writing and design modes that load the whole Suede copy or design stack: supplied-company voice, product surfaces, anti-slop line edits, Suedify, GitHub Pages polish, visibility grading, and visual QA.
Grouped by lane. Rows link to the deep docs page; every folder is inspectable on GitHub before you install it.
Every entry is a real commit: what changed, when it landed, and the hash that proves it. No "various improvements."
Version 0.10.0 released 2026-08-04
suede-ship-copy runs the same graph over a piece of writing: five blind research lenses, an audit that opens every agent-generated claim against its source, three independent angles, one message per section, adversarial review, and a deslop pass. Facts you supply yourself are given and never audited. The pack moves 69 -> 70.
Version 0.10.0 adds suede-instagram-growth: authorized account audits, attention-versus-conversion mapping, Reels, carousels, Stories, experiment cards, and an approval-gated daily loop. The pack moves 68 -> 70 and the marketing lane moves 38 -> 39.
suede-ci-gate now unambiguously owns CI and branch protection, while suede-ship owns the full shipping DAG. Public catalog, install, routing, documentation, and sitemap references match.
suede-ship adds scout, multi-lens research, gap criticism, collision-free lanes, parallel build, dual review, adversarial refutation, integration gates, and release verification. The pack moves 67 -> 68.
Version 0.9.2 accepts the protocol-reserved _meta object sent by current Codex clients while continuing to reject unrelated parameters. Both Suede MCP profiles now complete discovery.
The marketing and growth lane opened inside the gold install band instead of the catalog, rendering gold on gold at a contrast ratio of 1.0. The same thirty-eight were missing from llms.txt and their plugin was advertised nowhere. Counts on this page still read 28. Every fix ships with a validator guard.
All 68 skill pages plus the catalog, install, copy bank and both blog pages now ship a skip link targeting a focusable <main>, per WCAG 2.4.1. Four homepage labels also stopped using the fill-only red as text, clearing 4.5:1 against every composited background.
Version 0.9.1 rewrites thirty-eight marketing and growth skills around Suede contracts, evidence and authority boundaries, interruption-safe state, deterministic routing, and aligned metadata, evals, references, and docs.
suede-deslop strips AI writing patterns from finished prose: a merged kill list, structure fixes, active voice, varied rhythm, and a 50-point score gate. The pack goes 28 -> 29.
suede-codex-fleet now spawns every worker under caffeinate -i: the machine holds awake for exactly as long as workers run, releases the moment the fleet drains, and the slept-mid-run failure signature gets its own troubleshooting entry.
Version 0.7.0 adds the outcome router, one honest Codex marketplace entry, Codex-native plugin metadata, workflow MCP discovery, deterministic triggers, and synchronized full-pack docs.
Reserved internal names can never appear in a public file again: every public text file is scanned against hashed sequences, so a slip fails the build instead of shipping.
The packaged plugin must version like it means it. Tests cover shallow and versioned installs, and e1adeff makes packaged-plugin history validate safely on the same day.
Rights Passport, MCP lifecycle, deterministic routing, and immutable CI, validated against current main and passed through an independent adversarial review.
The build fails if a cited hash doesn't resolve to a real commit, entries fall out of date order, or the versioned release pill disagrees with the release entry. This page can't quietly lie.
One prompt to a Play-Store-ready Kotlin/Compose build, plus a skill that reads repo state and names the single next move. The pack goes 25 -> 27.
suede_creator_mcp now resolves its catalog through CLAUDE_PLUGIN_ROOT instead of assuming a fixed layout, so marketplace-cache installs stop coming up empty.
Ten commits in one sitting: a live sample session that cycles disciplines, a lane index, and copy with an actual hook.
amazon-returns-recovery runs fee discovery and live-chat disputes; subscription-recovery generalizes it to any recurring charge.
Proof is part of the release.
First install takes two commands. After the marketplace is added, install is one. Every skill is plain Markdown.
$ /plugin marketplace add JasonColapietro/suede-creator-skills → /plugin install suede-skills@suede
All install paths