supabase
Handles the full Supabase workflow from schema changes to deployment, with built-in security guardrails that catch common traps like RLS...
coordinate-subagents
Advanced subagent troubleshooting. Use when subagent calls fail, return bad output, or need voting for critical decisions.
Full skill instructions
Core coordination patterns are in CLAUDE.md <subagent_coordination>. This skill covers edge cases.
For irreversible actions (deletions, deployments, security assessments), run same query 2-3 times in parallel:
<!-- 3 parallel agents, same question -->
<invoke name="Task">
<parameter name="subagent_type">Explore</parameter>
<parameter name="model">haiku</parameter>
<parameter name="prompt">@type: AssessAction about: "safe to delete auth_old.ts" ...</parameter>
</invoke>
<invoke name="Task">
<parameter name="subagent_type">Explore</parameter>
<parameter name="model">haiku</parameter>
<parameter name="prompt">@type: AssessAction about: "safe to delete auth_old.ts" ...</parameter>
</invoke>
<invoke name="Task">
<parameter name="subagent_type">Explore</parameter>
<parameter name="model">haiku</parameter>
<parameter name="prompt">@type: AssessAction about: "safe to delete auth_old.ts" ...</parameter>
</invoke>
Interpret results:
| Symptom | Action |
|---|---|
| Output exceeds budget by >30% | Discard entirely, retry same prompt |
| Wrong format (expected TOON, got prose) | Discard, retry with stricter instruction |
| 2 consecutive failures | Refine query OR escalate model (haiku→sonnet) |
| Contradictory answers across retries | Query is ambiguous, decompose further |
Never: Try to parse/repair confused output. Discard and retry.
Token-Oriented Object Notation. Use for uniform arrays (file lists, steps, configs).
# Array with header declaring fields
items[N]{field1,field2,field3}:
value1,value2,value3
value1,value2,value3
"value, with comma"\"nested quote\"\nFile list:
files[3]{path,purpose,lines}:
src/auth/login.ts,Main login handler,145
src/auth/session.ts,Session management,89
src/auth/token.ts,JWT utilities,67
Process steps:
steps[4]{position,action,file}:
1,Parse request body,src/middleware/parser.ts
2,Validate auth token,src/middleware/auth.ts
3,Check permissions,src/middleware/rbac.ts
4,Execute handler,src/routes/api.ts
Key-value config:
config[3]{key,value}:
maxTokens,1500
format,toon
itemLimit,10
If coordination isn't working, check for these:
| Anti-Pattern | Fix |
|---|---|
| Single agent doing multiple tasks | Split: one task per agent |
| No token budget specified | Add @constraints: maxTokens: N |
| Using opus for simple search | Downgrade to haiku |
| Full conversation history in prompt | Strip to goal + constraints only |
| Sequential independent calls | Parallelize in one message |
| Parsing broken output | Discard and retry instead |
| Asking to "explain" or "describe" | Request structured format |
| Direct MCP/web tool calls in main context | Delegate: payloads unpredictable, request TOON summary |
| Verifying N external sources inline | Delegate: N scrapes = N×2000 tokens wasted |
Bad: Compound task
Find authentication code and analyze security vulnerabilities and suggest fixes
Good: Three focused agents
Agent 1: Find authentication code (haiku, 1500 tokens)
Agent 2: Analyze security of [files from agent 1] (sonnet, 2000 tokens)
Agent 3: Suggest fixes for [issues from agent 2] (sonnet, 2000 tokens)
Note: Agent 2 depends on Agent 1, so run sequentially. But if you had 3 independent searches, run all in parallel.
Subagent returned garbage
├─ Was format specified? → Add explicit TOON/JSON instruction
├─ Was budget set? → Add @constraints maxTokens
├─ Was task atomic? → Check for "and", split if needed
├─ Right model? → Simple task shouldn't use opus
└─ Second failure? → Escalate model or refine query
MCP tools and web scrapes are context pollution hazards:
| Tool | Typical Payload | Risk |
|---|---|---|
firecrawl_scrape | 500-5000 tokens | High - full page content |
firecrawl_search | 200-1000 tokens | Medium - result snippets |
WebFetch | 500-3000 tokens | High - full page content |
Rule: Any task involving N external fetches should be delegated with:
min(N × 200, 2500) tokens for summary outputonlyMainContent: true, formats: ["markdown"]Example - URL verification:
Task(Explore, sonnet):
"Verify these 10 legislation URLs. For each, scrape with onlyMainContent:true,
confirm HTTP 200, identify managing authority from page content.
@return ItemList in TOON:
results[10]{jurisdiction,url,status,authority}:
Commonwealth,https://legislation.gov.au,valid,Office of Parliamentary Counsel
...
@constraints: maxTokens: 2000"
CLAUDE.md <subagent_coordination>references/toon-format.mdHandles the full Supabase workflow from schema changes to deployment, with built-in security guardrails that catch common traps like RLS...
Comprehensive guides and best practices for Neon Serverless Postgres, covering setup, connection methods, authentication, and platform APIs.
Guide for setting up and using Firebase Authentication. Use this skill when the user's app requires user sign-in, user management, or secure data access using auth rules.
A skill to evaluate how secure Firestore security rules are. Use this when Firestore security rules are updated to ensure that the generated rules are extremely secure and robust.
Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.
Complete Better Auth server and client setup with database adapters, session management, plugins, and security configuration.
Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".
Complete Cloudflare platform integration with decision trees for compute, storage, AI, networking, security, and infrastructure-as-code.
Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault expiration check, expired certificates, expiring secrets, orphaned resources, compliance assessment.
Send, read, and manage Gmail messages, drafts, labels, and account settings.
Comprehensive website auditing across 230+ rules in 21 categories including SEO, performance, security, and accessibility.
Shared authentication, CLI syntax, and output formatting patterns for gws Google Workspace commands.
Discover your celebrity doppelgänger with StarByFace!
GeoSpy: Pricing, Features, FAQs, and Alternatives for AI Teams
Detect AI-generated voices to protect against audio fraud.
Ensure Your Content's Originality with AI Plagiarism Checker
Upscale images by 400% without quality loss
Protect your social media from copyright disputes
Accurately Detect AI-Generated Content with TheChecker.AI
Chrome extension that detects and flags AI-generated content