exa-prod-checklist

Execute Exa production deployment checklist with pre-flight, deploy, and rollback. Use when deploying Exa integrations to production, preparing for launch, or verifying production readiness. Trigger with phrases like "exa production", "deploy exa to prod", "exa go-live", "exa launch checklist", "exa production ready".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

80%

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

A tight, highly actionable deployment runbook with executable code and specific thresholds. Its main gaps are an implicit validation gate before promoting the canary to full rollout and a single monolithic file with no progressive disclosure into reference materials.

Suggestions

Add an explicit validation checkpoint before resuming the full rollout in Step 3 — e.g. require passing checks on /health/exa, error rate < 5%, and P95 < 5s before uncommenting `kubectl rollout resume`.

Split the Pre-Deployment Checklist and Alert/Error reference tables into a separate reference file (e.g. references/README.md) and link to it from SKILL.md so the main file stays a concise overview.

Make the canary resume step concrete with an actual guarded command rather than a commented-out hint, so the workflow is fully copy-paste executable end to end.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout — checklists, executable code blocks, and compact tables — and never explains concepts Claude already knows; every section earns its tokens.	3 / 3
Actionability	Provides copy-paste-ready executable bash (curl pre-flight, npm test, kubectl rollout), a TypeScript health endpoint, and concrete alert thresholds (e.g. "5xx > 10/min", "P95 > 5000ms") rather than pseudocode.	3 / 3
Workflow Clarity	The deploy sequence is clearly staged (pre-flight, health check, canary, post-deploy, rollback) with explicit pre-flight validation, but the canary-to-full-rollout promotion has only an implicit "monitor for 10 minutes" gate with the resume command commented out — no explicit validation checkpoint before resuming.	2 / 3
Progressive Disclosure	Sections and tables are well organized with no nested-reference problem, but all checklists and code live inline in one ~155-line file with no bundle files to offload detail; the Next Steps cross-references point to other skills rather than reference material for this one.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 description: third-person, concise, with explicit what/when structure and natural trigger phrases. The only mild weakness is that the listed actions are phase-level rather than granular concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the Exa production deployment domain plus three phases (pre-flight, deploy, rollback), but these are high-level phase labels rather than a comprehensive list of concrete actions, so it lands between vague and fully specific.	2 / 3
Completeness	Explicitly answers both what ("Execute Exa production deployment checklist with pre-flight, deploy, and rollback") and when ("Use when deploying Exa integrations to production...") with explicit triggers, meeting the full completeness bar.	3 / 3
Trigger Term Quality	Provides several natural user phrases — "exa production", "deploy exa to prod", "exa go-live", "exa launch checklist", "exa production ready" — giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The Exa-specific niche combined with distinct production-deploy trigger phrases makes it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 6e3a65f

Reviewed: 4 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.