mcpField
R
review

review

github.com/shiplightaiTesting & quality2607 installsUpdated 16w ago
Repository

About review

Review Orchestrator is an entry point for application reviews that triages scope, runs selected domain checks, and combines their findings into a report. It is intended for launch readiness, post-incident planning, or focused reviews across areas including security, privacy, compliance, design, performance, SEO, and GEO.

Key features

  1. 01Triage review scope and create a plan
  2. 02Run full-suite or targeted reviews
  3. 03Cover eight application review domains
  4. 04Load domain-specific review guidance
  5. 05Merge findings into a unified report

Use cases

  1. 01Assess application readiness before launch
  2. 02Plan reviews after an incident
  3. 03Request a focused security or SEO check
  4. 04Combine findings across review domains

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/shiplightai/agent-skills --skill review

After installing, type/reviewin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
compliance.md
design.md
geo.md
performance.md
privacy.md
report-format.md
resilience.md
security.md
seo.md

Details

From the project README

Review Orchestrator

The single entry point for application reviews. It triages what matters, then runs one or more domain reviews and merges them into a unified report. Each domain lives in references/<domain>.md and is loaded only when selected.

When to use

  • User wants a review but isn't sure which kind
  • Pre-launch readiness assessment
  • Post-incident review planning
  • A targeted request for one domain ("check my app's security", "review SEO")

Modes

  • Triage (default, /review) — ask context questions, recommend a plan, run it.
  • Full suite (/review --all) — run every applicable domain.
  • Targeted (/review <domain>) — jump straight into one domain, skipping triage. E.g. /review security, /review seo. Accepts an optional depth flag (--quick / --thorough).

Domains

Each row maps to a reference file. Load the file only when the domain is selected.

DomainReferenceRun it when… (trigger signals)
securityreferences/security.mdauth/login changes, sensitive data, OWASP, headers/CORS/CSP, supply chain
privacyreferences/privacy.mdcollects PII, tracking/analytics, consent banners, GDPR/CCPA
compliancereferences/compliance.mdregulated industry, audit prep, HIPAA/SOC 2/PCI-DSS/GDPR, payments or health data
designreferences/design.mdUI shipping without a designer, responsive, accessibility, typography, i18n
resiliencereferences/resilience.mderror handling, network/API failures, empty/edge states, degradation
performancereferences/performance.mdslow pages, Core Web Vitals, bundle size, runtime/render perf
seoreferences/seo.mdpublic site, meta tags, structured data, crawlability, sitemaps
georeferences/geo.mddiscovered via AI assistants, LLM citation readiness, llms.txt, entity clarity

Shared conventions (phases, scoring, confidence, severity, output paths) live in references/report-format.md — every domain follows them.

Steps

1. Gather context
  • Read the project: tech stack, framework, package.json, routes, components.
  • Check git diff for recent changes.
  • Look for existing reports in shiplight/reports/.
  • Auto-detect compliance markers (HIPAA/PHI, PCI/payment fields, GDPR/cookie consent).

If invoked as /review <domain>, skip to step 4 for that domain.

2. Ask targeted questions (max 4)

One at a time, with auto-detected defaults:

  1. What type of application? (SaaS, healthcare, fintech, e-commerce, internal tool, marketing site, API-only)
  2. What triggered this review? (pre-launch, new feature, dependency update, security incident, audit prep, routine)
  3. Any compliance requirements? (none, HIPAA, SOC2, PCI-DSS, GDPR, multiple) — auto-detect from codebase
  4. Specific concerns? (open-ended, optional)
3. Generate review plan

Categorize each applicable domain as CRITICAL (must run), RECOMMENDED (meaningful value), or OPTIONAL (nice to have), with estimated depth (quick / standard / thorough).

SEO vs GEO prioritization by product type:

Product typeSEOGEO
Developer tools, API products, SaaSRECOMMENDEDCRITICAL
E-commerce, local business, marketplaceCRITICALOPTIONAL
Content/media, documentation, blogCRITICALCRITICAL
Internal tools——

Present a decision matrix:

ReviewPriorityRationaleDepth
securityCRITICALNew auth feature + SaaS appthorough
privacyCRITICALHandles user PII, GDPR appliesstandard
…
4. Execute

Ask: "Run all CRITICAL reviews now? [Y/n] Or pick specific ones."

For each selected domain, read references/<domain>.md and follow its five phases, applying references/report-format.md for scoring, severity, and output paths. Run domains sequentially; show a brief summary after each before moving on.

5. Unified report

After the selected domains complete, merge their per-domain reports into one, saved to shiplight/reports/review-{date}.md:

  • Overall readiness score (0–10) and per-domain scores
  • Top 5 findings across all domains, by severity
  • Regression test summary (total YAML tests generated, in shiplight/tests/)

Tips

  • Run /review before every major launch.
  • /review <domain> is the fast path when you already know what you need.
  • Reports accumulate in shiplight/reports/ — the orchestrator can show trends.
  • YAML regression tests from reviews accumulate in shiplight/tests/.

Comments

Markdown supported