What does this skill do, and when should you use it?
Launch Day Conductor is an execution-stage Agent Skill for running a product launch on the launch date. It converts an approved channel plan into an hour-blocked war-room runbook with owners. It will not proceed unless it can verify a SHIP verdict from launch-readiness-auditor and the authoritative date and stage in launch-registry. During the day, it forces a CONTINUE-or-ROLLBACK decision after every irreversible action, manages P0-P3 incidents, and closes with a D0 snapshot and handoff.
Reads the launch-readiness SHIP artifact, authoritative launch date/stage, pre-declared kill criteria and rollback thresholds, plus the user-provided channel plan and owner roster; produces a runbook with time block, action, owner, reversibility, observation window, and data source; schedules a binary CONTINUE or ROLLBACK verdict after each irreversible push; classifies P0-P3 incidents and runs matching rollback or escalation playbooks; submits dated status proposals through registry-events.py; and prepares a D0 snapshot, thank-you queue, next-day queue, incident log, and launch-monitor handoff with Measured, User-provided, and Estimated labels.
- A launch team has a SHIP verdict and needs an owner-assigned war-room schedule for the release date.
- A release includes deployment, embargo lifting, store go-live, or email broadcast and requires a fixed observation window after each irreversible action.
- A launch shows elevated errors or a degraded signup, checkout, or install path and the team needs a CONTINUE-or-ROLLBACK decision.
- The team needs to consolidate launch-day metrics, unresolved replies, incidents, and next-day actions before handing off to sustained monitoring.
How do you install this skill?
- The skill orchestrates launch, rollback, and registry-proposal actions with external effects; before execution, the user should explicitly confirm targets, permissions, thresholds, owners, and rollback procedures.
- Some data sources and platform connectors depend on external services; the supplied material does not establish reachability from mainland-China networks or fallback behavior when connectors fail.
- Referenced upstream skills, runtime scripts, and registry protocols were not executed in this review; repository-level tests should not be treated as end-to-end validation of this skill.
- Shell / CLI
- Network access
- Local filesystem
Python standard-library connector scripts
Install the repository bundle with Claude Code using /plugin marketplace add aaron-he-zhu/aaron-marketing-skills, followed by /plugin install aaron-marketing@aaron; or use npx skills add aaron-he-zhu/aaron-marketing-skills on a generic Agent Skills-compatible host. If the host supports selecting one skill, use npx skills add aaron-he-zhu/aaron-marketing-skills -s launch-day-conductor. The source does not document a manual copy-to-directory installation procedure for this individual SKILL.md.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/launch/mobilize/launch-day-conductor" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Provide the SHIP record, authoritative launch date and stage, channel plan, owners, and pre-declared kill criteria, then use a prompt such as Run my launch day for [product] on [date]. Gate verdict: SHIP (on file). Channels going live: [list]. Owners: [names]. You can also request Build a dated hour-blocked launch-day runbook for a [T1/T2/T3] launch, or paste post-launch metrics and ask CONTINUE or ROLLBACK? After delivery, answer the save-results question if you want the artifacts retained.
What are this skill's strengths and limitations?
- Enforces both the SHIP gate and authoritative launch-date checks before execution begins.
- Makes irreversible actions, observation windows, binary decisions, owners, and data sources explicit.
- Includes P0-P3 incident handling, rollback playbooks, registry proposal events, and launch-monitor handoff.
- Works with user-provided data and free/public sources; keyed MCP dashboards are optional rather than required.
- Does not create channel submission copy, handle platform rules, answer media, or build telemetry instrumentation.
- Observation thresholds must already be declared; the skill must stop if the risk register does not provide them.
- Uses project memory and event-proposal files and may use network-based telemetry sources.
- The supplied material provides no skill-specific test-suite evidence or concrete platform test results.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Launch Day Conductor this page | 59 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
| Google Cloud Operational Excellence Advisor ✓ Google · Official | 53 · Use with care | ★ 21k | 12d ago | Apache-2.0 |
| TAO Workflow Launch Gate ✓ NVIDIA · Official | 60 · Recommended | ★ 3.6k | 12d ago | Apache-2.0 |
| Launch Registry | 59 · Recommended | ★ 3k | 12d ago | Apache-2.0 |
| DOCA Upgrade Control ✓ NVIDIA · Official | 55 · Use with care | ★ 3.6k | 12d ago | Apache-2.0 |
How did FollowSkills review this skill?
The skill requires verification of a SHIP verdict and authoritative date, treats telemetry as untrusted, separates proposal events from canonical registry writes, and specifies observation windows, rollback, and confirmation before saving. However, irreversible launch actions and external telemetry can have real-world effects, while permission boundaries, sensitive-data handling, and rollback isolation are not fully specified; 8 points are deducted.
The contract, NEEDS_INPUT stop condition, time-blocked workflow, P0-P3 incident ladder, and failure feedback are reasonably clear. Static review cannot verify the referenced skills, connectors, registry runtime, or abnormal-input paths, and the workflow has substantial cross-file dependencies; 11 points are deducted.
Trigger semantics, scenarios, inputs, outputs, non-fit boundaries, and handoffs are explicit, with Chinese naming support. Actual Chinese-language output capability, mainland-China network reachability, and availability of some overseas platform connectors are unverified; 4 points are deducted.
The file provides versioning, an Apache-2.0 license, Quick Start examples, a structured contract, data-source notes, save rules, limitations, and handoff guidance. It does not clearly identify a maintainer, changelog, or stable update path for this skill; 5 points are deducted.
The intended outputs cover a launch-day runbook, observation-window decisions, incident handling, end-of-day consolidation, and handoff, which is plausibly directly useful. Static review cannot establish actual completion quality, output usability, or marginal benefit over manual coordination; the static ceiling limits this to 7.
Claims are traceable to repository references covering security, state modeling, contracts, and related skills, and the shared repository includes CI and test evidence. There is no independent execution result or multi-source corroboration for this skill's key paths, so the static ceiling limits this to 5.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →