agentleFS
Sign inStart free
ucsandmanucsandman/claude-skills/ship-it/SKILL.md

ship-it

Skill5 starsChanged 2 months agoMITView on GitHub

Ship a product end to end — render marketing assets with the marketing studio (/marketing), then run the launch/ flow (/launch) with videos attached to X, LinkedIn, Bluesky and YouTube posts. Run from the product's repo.

46 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use modern-go, loop-it and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • jidechaoSkill

    modern-go

    Modernize Go code by applying version-appropriate idioms and APIs (gofix-style transformations). Scans go.mod for the Go version, then transforms Go source files to use modern patterns—from Go 1.0 through 1.26+. Use when the user says "现代化","现代Go语言", "地道的", "idiomatic", "modernize", "modern-go", "update Go code", "gofix", or wants to upgrade Go idioms.

    Also in 3 projects that use this

  • jidechaoSkill

    loop-it

    Automated issue loop with checkpoint/resume: fetch open GitHub issues → dependency-aware topological sort → implement each issue end-to-end → review with /review-it → document with /note-it → ship with /ship-it → repeat. Persists state to .loop-state.json for crash recovery. Triggers on: loop-it, loop issues, auto implement, 批量实现, 循环实现, 实现所有issue, 恢复循环, resume loop.

    Also in 3 projects that use this

  • SentrySkill

    create-pr

    Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.

    Also in 5 projects that use this

  • GitHubSkill

    refactor

    Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

    Also in 4 projects that use this

  • GoogleSkill

    to-issues

    Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

    Also in 3 projects that use this

  • Hugging FaceSkill

    simplify

    Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.

    Also in 3 projects that use this

  • +2 more from jidechao

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run from the product repo you want to ship.

    line 8
  2. Very specific:

    Render if needed: If the manifest is missing, run /marketing first (full pipeline, its own approval gates).

    line 18
  3. Distinctive:

    Never skip the dry-run step.

    line 36
  4. Very specific:

    If the kit manifest promises a video whose file is missing, posting refuses — fix by re-running render-matrix.mjs <brand> --project …

    line 37

“Common” is measured: kept by at least 6 in 10 of the 42 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/ship-it — develop → public, one command

Run from the product repo you want to ship. Studio root = C:/Projects/animations (rendering). Its launch CLI lives at C:/Projects/animations/launch (distribution) — run subcommands via node "C:/Projects/animations/launch/dist/index.js" <cmd> or npx --prefix "C:/Projects/animations/launch" launch <cmd>, from the product repo so its .launch/ state lands there. This skill is the pipeline.

Steps

  1. Find the brand + kit. Brand id = the product's brand in C:/Projects/animations/brands/<id>.json (ask only if ambiguous). Kit = <product>/marketing/assets/<brand>/postkit/manifest.json.
  2. Render if needed. If the manifest is missing, run /marketing first (full pipeline, its own approval gates). If it exists, show its generatedAt and ask: reuse or re-render? Staleness is the user's judgment call, never a heuristic.
  3. Launch flow. In the product repo, run the launch sequence — launch init (if no .launch/launch.config.json), then research, copy scaffold/fill, validate. Wire the kit: either set postkitDir in the config (the dashboard marketing tab does this with a picker) or pass --kit "<product>/marketing/assets/<brand>/postkit" to launch post.
  4. Dry-run, then post. launch post <dir> --all --dry-run and show the user the previews — X and LinkedIn must show the video upload step. Live posting only after the user confirms, through the normal gates (ledger, validation, typed confirmation in the dashboard).
  5. Manual platforms. TikTok / Shorts / Instagram are manual by design. Point the user at the dashboard marketing tab (Open folder per platform) or the kit's POST.md checklists. YouTube is NOT manual any more: launch post --all --live uploads to it whenever the three YOUTUBE_* keys are set. Uploads land private unless YOUTUBE_PRIVACY says otherwise -- say so out loud before any live run, and confirm it the same way as every other api-mode platform.

Rules

  • Never skip the dry-run step. Never post live without explicit user confirmation.
  • If the kit manifest promises a video whose file is missing, posting refuses — fix by re-running render-matrix.mjs <brand> --project <product> --production and build-postkit.mjs <brand> --project <product> --production, not by unwiring the kit.
  • Live publishing remains blocked until the current media, production plan, per-row evidence, and named full-film review are hash-bound and PASS. A dry run may preview an incomplete kit but never weakens the live gate.
  • Drafts own the copy; the kit contributes media. Do not paste kit captions over validated drafts.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free