Skip to content

aaron-he-zhu/aaron-marketing-skills / launch/assemble/launch-asset-packager

launch-asset-packager

Verified

Use when the user asks to "package the launch assets", "build a press kit", or "prep the store listing and go-live checklist"; produces a tier-scoped launch asset manifest with production status — a press kit spec (factsheet, description, history, features, videos, images, logo and icon, awards, contact), demo script and screenshot specs, a launch FAQ, dual-store listing metadata drafts against the official character budgets (per App Store Connect / Play Console documentation), and a technical go-live checklist manifest (robots flip, sitemap, OG tags, analytics verification — execution stays with technical-seo-checker and serp-markup-builder). Not for the message copy itself — use message-house-builder or content-writer; not for landing page UX — use landing-optimizer; not for keyword research beyond the store surfaces — use keyword-research. 发布资产打包/press kit/商店listing规格/上线检查清单

FileKindSize
SKILL.mdskill md12.5 KB
references/action-control.mdmarkdown2.3 KB
references/asset-specs.mdmarkdown6.1 KB

references/action-control.md

View on GitHub
# Launch Action Control

Use this control for a launch manifest and every launch-day action that can change an external surface. It specializes the shared state and receipt rules for launch operations; it does not replace the launch registry or the RAMP gate.

## Frozen manifest

Bind a launch package with `launch_ref`, `manifest_version`, `manifest_hash`, dependency offsets, `frozen_at`, and optional `supersedes`. Any asset, claim, destination, owner, or channel change produces a new manifest version. A SHIP verdict is valid only for the exact manifest hash it audited.

## Three separate records

- **SHIP verdict**: the RAMP gate's eligibility decision for one manifest version. It is neither permission to act nor evidence that an action occurred.
- **Action intent**: one exact irreversible operation with action ID, type, target, payload/manifest hash, owner, scheduled time, observation window, kill criteria, and rollback route.
- **Action receipt**: evidence returned or captured after that exact action is attempted: stable provider-operation or evidence ref, attempted/completed time, `succeeded | partial | failed | unknown`, accepted/rejected scope, and a bound domain evidence record. The domain record may preserve a live URL; the shared locator-free envelope carries only its ref and digest. A rollback is an `operation: rollback` action; `rolled_back` is not a receipt status.

Every irreversible action gets its own intent and its own receipt. A dry run, runbook row, registry proposal, SHIP verdict, or operator assertion without evidence is not a receipt. A rollback is a new action with its own receipt; it does not rewrite the original receipt.

## Lane joins and closeout

The current manifest declares the required action IDs for each lane. A lane is complete only when every required action has a terminal receipt matching the current manifest hash. Missing or `partial | unknown` receipts keep the lane and launch join `OPEN`; do not infer completion from a live URL, dashboard total, later snapshot, or another lane's success.

Monitoring binds snapshots to the manifest, action receipts, and predeclared measurement contract. The retro consumes those bound records. Facts worthy of long-term truth still travel as launch-registry proposals; receipts remain operational evidence and do not become registry truth by themselves.
deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall