Agent skill · Security

suede-ship

Canonical Suede shipping DAG: scout, multi-lens research, gap critic, lane plan with explicit file ownership, disjoint parallel build, dual-lens review, adversarial refute, integration gate, and release verification. Use for any nontrivial change to a repo that touches more than one file or surface and deserves roughly fifty agents of surgical, research-heavy fan-out. Halts on a blocking hazard (a real secret in a tracked file, a live process holding a target worktree) or a lane collision rather than plowing through. Reads production; never deploys. NOT FOR: high-volume, well-specified work th

JasonColapietrogithub.com/JasonColapietroGitHub ↗
claude-codecodexships scriptsMIT
Install
npx skills add JasonColapietro/suede-creator-skills --skill suede-ship --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 3
SKILL.md size: 6 KB
Bundled scripts: yes
Path: skills/suede-ship/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 165
Language: JavaScript

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Suede Ship The canonical Suede DAG. One prompt in, one shipped change out, with about fifty agents in between arranged as a graph rather than a chain. Invoke the workflow bundled at `skills/suede-ship/workflows/suede-ship.js`. If you keep a personal copy, `~/.claude/workflows/suede-ship.js` works the same way. ## Choose this or the fleet first `suede-ship` is the surgical instrument and it is the expensive one. Roughly fifty agents (about fifty-four when `deploys` is true), research-heavy and front-loaded, billed to the Claude limit. If the job is actually high-volume, well-specified, and splits into independent worker-sized tasks (content batches, test generation, bulk refactors), say so and offer [`suede-codex-fleet`](../suede-codex-fleet/SKILL.md) instead. That runs on the OpenAI subscription and costs nothing against the Claude limit. Brute force beats surgery when the work is genuinely parallel and shallow. ## Parse the invocation The argument is free-form. Extract: - **repo** — required. An absolute path. Resolve a bare name against `~/code/<name>`. If no repo is named and the cwd is inside a git repo, use that repo's root. - **scope** — required. What to change, in the use

What's inside
Steps it walks through
  1. Choose this or the fleet first
  2. Parse the invocation
  3. State the cost before launching
  4. Launch
  5. The graph
  6. While it runs
  7. When it returns
  8. Verdict is advisory
  9. Iterating
Ships with 2 files
  • agents/openai.yaml
  • workflows/suede-ship.js
More from suede-creator-skills
All skills →
About this skill
What does the suede-ship skill do?

Canonical Suede shipping DAG: scout, multi-lens research, gap critic, lane plan with explicit file ownership, disjoint parallel build, dual-lens review, adversarial refute, integration gate, and release verification. Use for any nontrivial change to a repo that touches more than one file or surface and deserves roughly fifty agents of surgical, research-heavy fan-out. Halts on a blocking hazard (a real secret in a tracked file, a live process holding a target worktree) or a lane collision rather than plowing through. Reads production; never deploys. NOT FOR: high-volume, well-specified work th

How do I install it?

Run `npx skills add JasonColapietro/suede-creator-skills --skill suede-ship --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From JasonColapietro/suede-creator-skills, a repository with 165 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going