shipping-and-launch

Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/shipping-and-launch/SKILL.md

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An unusually strong operational skill: concrete thresholds, executable commands, and an exemplary staged-rollout workflow with validation at every checkpoint. The weaknesses are a non-runnable ErrorBoundary snippet and a monolithic structure whose external references point outside the skill bundle while duplicating inlined checklist content.

Dimension	Reasoning	Score
Conciseness	The body is dense and checklist/table-driven with almost every line earning its place, and it never explains concepts Claude already knows. Minor trimmable padding ('Ship with confidence...' overview, the Common Rationalizations rebuttal table) keeps it below the lean score-5 anchor.	4 / 5
Actionability	Concrete guidance throughout: a quantified advance/hold/rollback thresholds table, a fill-in rollback plan template, specific commands ('git revert <commit> && git push', 'npx prisma migrate rollback'), and TypeScript snippets. Not fully copy-paste ready — the ErrorBoundary example reads this.state.hasError without ever setting it and lacks getDerivedStateFromError.	4 / 5
Workflow Clarity	The 6-stage rollout sequence has explicit validation checkpoints at every step ('Advance only if all thresholds pass', '24-hour monitoring window'), a quantified decision table, immediate-rollback triggers, post-launch verification steps, and before/after deployment checklists — fully matching the score-5 anchor with feedback loops for a risky batch operation.	5 / 5
Progressive Disclosure	The body is a ~330-line monolith with no bundle files present; the 'See Also' links point to '../../references/*.md' paths outside the skill directory that cannot be verified, and the inlined Security/Performance/Accessibility checklist sections duplicate content those references are meant to hold. Sectioning is clean and references are clearly signaled, which keeps it above score 2.	3 / 5
	Total	16 / 20 Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-constructed description with an explicit, multi-trigger 'Use when' clause covering the main launch scenarios. Its main weakness is the thin 'what' — a single generic action ('Prepares production launches') with no concrete capability enumeration — which slightly limits specificity and completeness.

Suggestions

Expand the 'what' clause with 2-3 concrete capabilities (e.g., 'Runs a pre-launch checklist across code, security, performance, and accessibility; plans staged rollouts with decision thresholds; documents rollback plans') to raise specificity from generic to concrete.

Add common trigger synonyms such as 'release', 'go-live', or 'launch day' so users phrasing the need differently still match the skill.

Narrow the 'setting up monitoring' trigger to launch-specific monitoring (e.g., 'setting up post-launch monitoring and error reporting') to reduce overlap with a dedicated observability skill.

Dimension	Reasoning	Score
Specificity	The 'what' is a single general action — 'Prepares production launches' — with no enumerated concrete capabilities, matching the anchor 'names domain and 1-2 concrete actions, but not comprehensive'. It is above score 2 because the domain is precisely named, and below score 4 because no list of specific actions is provided.	3 / 5
Completeness	Both 'what' ('Prepares production launches') and an explicit, multi-trigger 'Use when...' clause are present, satisfying the score-4 anchor. Not 5 because the 'what' is a single thin statement rather than the concrete capability list seen in the score-5 example.	4 / 5
Trigger Term Quality	Strong natural phrases users would actually say: 'deploy to production', 'pre-launch checklist', 'staged rollout', 'rollback strategy', 'before shipping'. Falls short of 5 because common synonyms such as 'release', 'go-live', or 'launch day' are absent.	4 / 5
Distinctiveness Conflict Risk	The production-launch niche is clear with distinct triggers ('staged rollout', 'rollback strategy'). Minor overlap risk remains with observability/monitoring skills, since 'when setting up monitoring' is a trigger that a monitoring skill would also claim.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: addyosmani/agent-skills
Path: skills/shipping-and-launch/SKILL.md
Commit: 2686b62

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

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.