Plan and execute a launch runbook covering pre-launch verification, go-live procedures, DNS cutover, post-launch monitoring, and rollback procedures. Use this skill whenever the user is preparing to launch a website or product, planning a DNS cutover, building a go-live checklist, or executing a launch day. Triggers on launch runbook, go-live, launch day, DNS cutover, deploy to production, site launch, product launch, cutover plan, launch checklist, deployment procedure. Also triggers when a launch is approaching and the team needs structured coordination, even if 'runbook' is not explicitly stated.
67
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It provides specific concrete actions, comprehensive trigger terms covering natural user language variations, explicit 'what' and 'when' guidance, and a clearly defined niche that minimizes conflict risk with other skills. The description is well-structured and appropriately detailed without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'pre-launch verification, go-live procedures, DNS cutover, post-launch monitoring, and rollback procedures.' These are distinct, actionable phases of a launch process. | 3 / 3 |
Completeness | Clearly answers both 'what' (plan and execute a launch runbook covering specific phases) and 'when' (explicit 'Use this skill whenever...' clause with detailed trigger scenarios and an explicit list of trigger terms). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'launch runbook, go-live, launch day, DNS cutover, deploy to production, site launch, product launch, cutover plan, launch checklist, deployment procedure.' Also includes the edge case of implicit triggers when a launch is approaching. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on launch runbooks and go-live coordination. The specific terms like 'DNS cutover,' 'rollback procedures,' and 'launch day' clearly distinguish this from general deployment or project management skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured launch runbook skill with excellent workflow clarity—clear phases, time markers, verification checkpoints, and rollback criteria. Its main weaknesses are verbosity (generic project management advice that Claude already knows) and limited actionability (no concrete commands, tool-specific examples, or executable snippets). The referenced template file doesn't exist in the bundle, weakening progressive disclosure.
Suggestions
Add a concrete, filled-out example of at least one cutover step showing specific commands (e.g., a DNS cutover with `dig` verification, or a deploy with a specific CLI tool) to improve actionability.
Move the failure patterns and detailed communication plan sections into separate reference files to reduce the main skill's token footprint and improve progressive disclosure.
Trim generic project management guidance (roles table descriptions, 'When to use/NOT to use' lists) that Claude can infer from context—focus tokens on the non-obvious, launch-specific details.
Ensure the referenced `references/runbook-template.md` file actually exists in the bundle, or remove the reference if it's aspirational.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is generally well-organized and avoids explaining basic concepts, but it's verbose in places—the roles table, failure patterns, and communication plan sections contain guidance that is fairly generic project management knowledge Claude already possesses. The 'When to use' / 'When NOT to use' sections and 'Required inputs' add some padding. Could be tightened by ~30%. | 2 / 3 |
Actionability | The skill provides structured checklists, timelines, and role definitions, which is good. However, it's entirely descriptive—no concrete commands, no executable code snippets, no specific tool invocations. Steps like 'Deploy code to production' and 'Run smoke tests' remain abstract. The cutover sequence describes what each step *should have* but doesn't provide a concrete example of a filled-out step with actual commands. | 2 / 3 |
Workflow Clarity | The four-phase framework is clearly sequenced with explicit time markers (T-30, T-7, T-1, T-0, T+1hr, T+24hr, T+7d). Verification checkpoints are built into each phase, rollback criteria are pre-defined with decision authority, and the cutover sequence explicitly requires verification after each step before proceeding. The workflow section at the end provides a clear summary sequence including testing rollback and tabletop exercises. | 3 / 3 |
Progressive Disclosure | The skill references a template file at `references/runbook-template.md` which is appropriate, but the bundle doesn't actually contain this file. The main SKILL.md is quite long (~200+ lines) and some sections (failure patterns, detailed communication plan, full roles table) could be split into reference files. The structure is reasonable but the content-to-reference ratio is skewed toward inline. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
8e70d03
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.