shipping-and-launch

Prepares production launches. Use when preparing to deploy to production. 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

82%

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

Quality

Content

81%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.

A highly actionable, well-sequenced launch skill with concrete code, threshold tables, and explicit validation gates. Its main weaknesses are motivational padding that inflates length and a progressive-disclosure structure whose external references cannot be verified and partly duplicate inline content.

Suggestions

Trim the Overview philosophy line and collapse the "Common Rationalizations" and "Red Flags" sections into a single concise anti-pattern list to recover tokens while keeping the warnings.

Resolve the inline/referenced duplication: keep the Pre-Launch Checklist as a short summary and move the detailed security/performance/accessibility items fully into the referenced files (or vice versa), so each item lives in one place.

Fix or remove the "See Also" references — the cited ../../references/*.md files are not present in the skill bundle; either ship them under references/ or point to paths that exist so navigation is not broken.

Dimension	Reasoning	Score
Conciseness	The body is ~300 lines and mostly actionable, but it carries motivational padding ("Ship with confidence…", the "Common Rationalizations" table, and the overlapping "Red Flags" list) that could be trimmed without losing instructional value; not below the midpoint because the bulk is lean checklist/code/table content.	3 / 5
Actionability	Provides copy-paste-ready TypeScript (feature-flag check, error boundary, server error handler), concrete rollout percentages (5%→25%→50%→100%), a numeric decision-threshold table, and real commands ("git revert <commit> && git push", "npx prisma migrate rollback").	5 / 5
Workflow Clarity	The staged rollout is a numbered 1–6 sequence with explicit validation gates ("Advance only if all thresholds pass", per-stage monitoring windows) and a rollback feedback loop with trigger conditions; verification checklists bracket the deploy (before/after).	5 / 5
Progressive Disclosure	Well-organized sections with a clearly signaled one-level "See Also" block, but the four referenced ../../references/*.md files do not exist in the bundle, and security/performance/accessibility material is duplicated both inline and as references, leaving minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

83%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 strong, third-person description that answers both what and when with explicit, natural trigger phrases. It is held back from the top band only by a generic opening action, a few missing synonyms, and one broad monitoring trigger that invites minor overlap.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities via its triggers — "pre-launch checklist", "monitoring", "staged rollout", "rollback strategy" — but the opening "what" ("Prepares production launches") is a single generic action, leaving minor coverage gaps rather than comprehensive enumeration.	4 / 5
Completeness	Clearly states what ("Prepares production launches") and gives multiple explicit "Use when…" clauses with concrete trigger phrases, matching the anchor for fully answering both what and when.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ("pre-launch checklist", "staged rollout", "rollback strategy", "deploy to production"), but omits common synonyms such as "canary", "feature flag", "release", or "kill switch".	4 / 5
Distinctiveness Conflict Risk	Occupies a clear production-launch niche with distinct triggers, but the standalone "when setting up monitoring" clause is broad and could overlap with a dedicated observability or general quality skill.	4 / 5
	Total	17 / 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: df1edb2

Reviewed: about 18 hours 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.