agentleFS
phoenixvnphoenixvn/claude-code-agency/.claude/skills/team-launch/SKILL.md

team-launch

Skill0 starsChanged 7 months agoMITView on GitHub

Multi-department coordination for project go-live. All relevant departments, 6 phases. qa-lead: - Final functional QA pass - Regression testing on all critical paths - Cross-browser and responsive verification - Compile go/no-go status for QA seo-lead: - Sitemap.xml present and correct - robots.txt configured properly - All pages have unique title/meta - Canonical tags set - Structured data validated - Redirect map (old URLs → new URLs if migration) - Compile go/no-go status for SEO security-auditor: - Security headers configured (CSP,…

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All relevant departments, 6 phases.

    line 4
  2. Distinctive:

    All pages have unique title/meta

    line 20
  3. Distinctive:

    All images optimized and alt-tagged

    line 44
  4. Distinctive:

    Verify all tracking is firing correctly

    line 92
  5. Distinctive:

    Create client training session outline

    line 108

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/team-launch — Launch Coordination Pipeline

Multi-department coordination for project go-live. All relevant departments, 6 phases.

Instructions

Phase 1: Pre-launch Audit (PARALLEL: qa-lead + seo-lead + security-auditor)

Spawn in parallel:

qa-lead:

  • Final functional QA pass
  • Regression testing on all critical paths
  • Cross-browser and responsive verification
  • Compile go/no-go status for QA

seo-lead:

  • Sitemap.xml present and correct
  • robots.txt configured properly
  • All pages have unique title/meta
  • Canonical tags set
  • Structured data validated
  • Redirect map (old URLs → new URLs if migration)
  • Compile go/no-go status for SEO

security-auditor:

  • Security headers configured (CSP, HSTS, X-Frame-Options)
  • SSL certificate valid and not expiring soon
  • OWASP quick scan — no critical vulnerabilities
  • Dependencies audited (no known CVEs)
  • Compile go/no-go status for Security

Present consolidated go/no-go status: | Area | Status | Blockers | | QA | GO/NO-GO | [details] | | SEO | GO/NO-GO | [details] | | Security | GO/NO-GO | [details] |

USER APPROVAL GATE — Go/No-go decision.

Phase 2: Content Freeze (content-lead)

Spawn content-lead to:

  • Final content review — all copy proofread
  • All images optimized and alt-tagged
  • Legal/compliance check (privacy policy, terms, cookie consent)
  • Content signoff confirmation

Phase 3: Technical Preparation (devops-engineer)

Spawn devops-engineer to:

  • Production environment verification
  • Database migrations ready and tested
  • CDN and caching configured
  • Backup procedures verified
  • Monitoring and alerting active (Sentry, UptimeRobot)
  • Rollback plan documented:
    1. What triggers rollback
    2. Rollback steps
    3. Communication plan during rollback
    4. Recovery timeline

Phase 4: Launch Execution (project-lead)

Spawn project-lead to create launch runbook:

Pre-launch (T-1 hour):

  • Final backup of existing site (if migration)
  • Team notified and standing by
  • Monitoring dashboards open

Launch (T-0):

  • DNS switch / deployment trigger
  • Wait for propagation (5-15 min)
  • Verify site loads on production URL
  • Run smoke test checklist:
    • Homepage loads
    • Navigation works
    • Key forms submit
    • Authentication works
    • SSL certificate valid
    • No console errors
  • Verify redirects (old URLs → new URLs)
  • Verify analytics tracking fires

Post-launch (T+30 min):

  • Monitor error rates
  • Check Core Web Vitals
  • Verify email delivery (if applicable)

Phase 5: Post-launch (PARALLEL: analytics-specialist + marketing-lead)

Spawn in parallel:

analytics-specialist:

  • Verify all tracking is firing correctly
  • Confirm conversion events recording
  • First data sanity check
  • Set up automated alerts for anomalies

marketing-lead:

  • Launch announcement — social media posts
  • Email announcement to subscriber list
  • PR/outreach if planned
  • Community notifications

Monitor for 30 minutes for issues.

Phase 6: Handover (account-director)

Spawn account-director to:

  • Trigger /handover workflow for documentation
  • Create client training session outline
  • Define support transition plan (warranty period, SLA)
  • Schedule project retrospective
  • Final project sign-off

Update production/session-state/active.md:

## Current Phase: Completed
## Launch Date: [date]

Present project completion summary.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.