platform-setup
Skill12 starsChanged 29 days agoMITView on GitHub
Full autonomous AI agency setup for https://local-llm-server.strikersam.workers.dev. Uses browse CLI (Browserbase remote mode) to log in as admin, onboard the platform itself as a company, configure all specialists, verify agents are running, and fix any issues found. Run this skill to go from "deployed" to "fully autonomous."
- Reads credentials
- Installs packages
1 other project uses a version of this.
Adopted by
Most recently taken up by
- katalon-labs/true-skillstheir own version, first seen Jun 23, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- katalon-labs/true-skills★ 10same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- agent/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- router/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/verification.mdcCursor rule
- agentic-agileSkill
- agentic-portfolioSkill
- client-onboardingSkill
- cooldown-resumeSkill
- drillSkill
- ecc-harness-patternsSkill
- fabric-patternsSkill
- graphiti-temporalSkill
- managed-agents-dreamsSkill
- model-catalogue-updateSkill
- repowise-intelligenceSkill
- risky-module-reviewSkill
- seo-audit-reportSkill
- user-researchSkill
- video-contextSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 174
After setup, the platform maintains itself via:
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
Skill: platform-setup — Autonomous Agency Bootstrap
Prerequisites
npm install -g browse
export BROWSERBASE_API_KEY="bb_live_..."
export PLATFORM_URL="https://local-llm-server.strikersam.workers.dev"
# Admin credentials are in memory/test_credentials.mdPhase 1 — Verify deployment health (no auth needed)
# 1a. Check public health endpoints
python3 -c "
import urllib.request, json, os
base = os.environ['PLATFORM_URL']
for path in ['/api/health', '/api/doctor/public']:
try:
with urllib.request.urlopen(f'{base}{path}', timeout=10) as r:
print(f'{path}: HTTP {r.status}', json.loads(r.read()).get('status','?'))
except Exception as e:
print(f'{path}: ERROR {e}')
"
# 1b. If health endpoints are 403/404 — the Cloudflare Worker routing is broken.
# Fix: check wrangler.jsonc BACKEND_ORIGIN points to correct Render URL.Phase 2 — Login as admin
browse open "$PLATFORM_URL/login" --remote
# Get page snapshot to find form field refs
browse snapshot
# Look for: email input, password input, submit button
# Fill credentials (from memory/test_credentials.md)
browse fill "@eN" "strikersam@gmail.com" # replace @eN with actual ref
browse fill "@eN" "YOUR_ADMIN_PASSWORD"
browse click "@eN" # Submit / Login button
# Verify login succeeded
browse snapshot
# Expected: dashboard visible, no /login redirect
browse screenshotPhase 3 — Onboard the platform itself as a company
# Navigate to Company / Onboarding
browse click "@eN" # "+" or "New Company" button
browse snapshot
# Fill company details
browse fill "@eN" "Agency Core Platform" # Company name
browse fill "@eN" "https://local-llm-server.strikersam.workers.dev" # Website URL
browse click "@eN" # "Scan" or "Start Onboarding" button
# Wait for scan to complete (may take 30-60s)
browse wait 30000
browse snapshot
# Expected: detected systems listed (Cloudflare, Render, FastAPI, React, etc.)
browse screenshotPhase 4 — Verify specialists were provisioned
browse click "@eN" # Navigate to Agents/Specialists screen
browse snapshot
# Expected: specialists created for detected families
# (engineering, security, devops, frontend, backend)
# If no specialists: click "Provision Specialists" or "Setup Agency"
browse click "@eN"
browse snapshot
browse screenshotPhase 5 — Configure GitHub integration
# Navigate to Settings or Integrations
browse click "@eN" # Settings / Integrations
browse snapshot
# Find GitHub token field
browse fill "@eN" "YOUR_GITHUB_PAT" # GH_PAT from GitHub secrets
browse click "@eN" # Save
# Verify: GitHub connection shows green / connected
browse snapshot
browse screenshotPhase 6 — Trigger first agency cycle manually
# Navigate to Agency / Workflow
browse click "@eN" # Agency or Workflow section
browse snapshot
# If there's a "Run Agency Cycle" button:
browse click "@eN"
browse wait 5000
browse snapshot
# Expected: cycle started, assessment running
browse screenshotPhase 7 — Verify autonomous schedule is active
# Navigate to Tasks or Schedules
browse click "@eN"
browse snapshot
# Expected: scheduled tasks visible with next run times
# Check Doctor / Health screen
browse click "@eN" # Doctor
browse snapshot
# Expected: all checks green, no red indicators
browse screenshot
browse stopTroubleshooting checklist
| Symptom | Diagnosis | Fix |
| Login redirects back to /login | Wrong credentials or session issue | Check memory/test_credentials.md |
| Scan finds 0 systems | Scanner or Cloudflare blocking the scan | Run scan on a simpler URL first to verify scanner works |
| No specialists after onboarding | Onboarding didn't complete | Check /api/company/{id}/onboarding/status |
| Agent tasks fail with runtime error | internal_agent blocked by orchestrator | PR #396 fix must be merged |
| Agents not running on schedule | GitHub Actions quarantined | PR #396 restores all schedules |
| Doctor shows red for GitHub | GH_PAT not configured in Settings | Complete Phase 5 above |
Post-setup verification
Once setup is complete, these should all be true:
GET /api/healthreturns{"status": "ok"}- At least 3 specialists visible in Agents screen
- At least 1 task created and visible in Tasks screen
- Doctor screen shows all green
- GitHub integration shows "Connected"
- Scheduled tasks show future run times
- Agency cycle can be triggered manually
Ongoing autonomous operation
After setup, the platform maintains itself via:
- agency-cycle (every 6h): runs pytest, security scan, dispatches Claude agents
- continuous-improvement (daily): tracks quality metrics, creates/closes issues
- ci-failure-autofix (on CI fail): generates and applies patches automatically
- process-quick-note (every 4h): processes owner feature requests end-to-end
- weekly-trend-digest (Monday): surfaces relevant AI/tech trends as issues
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
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.

