docs: salvage focused skill curation updates (#1723)

Port the safe, narrow pieces from contributor PR #1694 without taking the broad 11-skill rewrite.

- add drift-prone warnings to external research/media/API skills

- make search-first verify tool availability and use current agent naming

- remove unsafe in-memory rate limiter example from backend patterns

- tighten the CSP example in security-review

Validation: node scripts/ci/validate-skills.js --strict; npx markdownlint targeted skill files; node tests/ci/validators.test.js && node tests/ci/catalog.test.js; npm run lint; node tests/run-all.js

skills/backend-patterns/SKILL.md

@@ -430,51 +430,14 @@ export const DELETE = requirePermission('delete')(
 
 ## Rate Limiting
 
-### Simple In-Memory Rate Limiter
+Rate limiting must use a shared store such as Redis, a gateway, or the
+platform's native limiter. Do not use per-process in-memory counters for
+production APIs: they reset on deploy, split across replicas, and fail open in
+serverless or multi-instance environments.
 
-```typescript
+Keep the backend layer responsible for choosing the integration point and error
-class RateLimiter {
+shape; use `api-design` for the HTTP contract and `security-review` for abuse
-  private requests = new Map<string, number[]>()
+case review.
-
-  async checkLimit(
-    identifier: string,
-    maxRequests: number,
-    windowMs: number
-  ): Promise<boolean> {
-    const now = Date.now()
-    const requests = this.requests.get(identifier) || []
-
-    // Remove old requests outside window
-    const recentRequests = requests.filter(time => now - time < windowMs)
-
-    if (recentRequests.length >= maxRequests) {
-      return false  // Rate limit exceeded
-    }
-
-    // Add current request
-    recentRequests.push(now)
-    this.requests.set(identifier, recentRequests)
-
-    return true
-  }
-}
-
-const limiter = new RateLimiter()
-
-export async function GET(request: Request) {
-  const ip = request.headers.get('x-forwarded-for') || 'unknown'
-
-  const allowed = await limiter.checkLimit(ip, 100, 60000)  // 100 req/min
-
-  if (!allowed) {
-    return NextResponse.json({
-      error: 'Rate limit exceeded'
-    }, { status: 429 })
-  }
-
-  // Continue with request
-}
-```
 
 ## Background Jobs & Queues
 

skills/deep-research/SKILL.md

@@ -6,6 +6,10 @@ origin: ECC
 
 # Deep Research
 
+> **Drift-prone skill.** Firecrawl/Exa MCP tool names, quotas, and result
+> shapes change. Verify the configured MCP tools and current API docs before
+> promising coverage or quoting live source counts.
+
 Produce thorough, cited research reports from multiple web sources using firecrawl and exa MCP tools.
 
 ## When to Activate

skills/exa-search/SKILL.md

@@ -6,6 +6,10 @@ origin: ECC
 
 # Exa Search
 
+> **Drift-prone skill.** Exa MCP tool names, parameters, and account limits can
+> change. Confirm the exposed tool surface and current Exa docs before relying
+> on a specific search mode, category, or livecrawl behavior.
+
 Neural search for web content, code, companies, and people via the Exa MCP server.
 
 ## When to Activate

skills/fal-ai-media/SKILL.md

@@ -6,6 +6,10 @@ origin: ECC
 
 # fal.ai Media Generation
 
+> **Drift-prone skill.** fal.ai model IDs, pricing, inputs, and MCP tool names
+> change quickly. Search or fetch the current model metadata before promising a
+> specific model, parameter, output format, or cost.
+
 Generate images, videos, and audio using fal.ai models via MCP.
 
 ## When to Activate

skills/search-first/SKILL.md

@@ -20,6 +20,10 @@ Use this skill when:
 
 ```
 ┌─────────────────────────────────────────────┐
+│  0. TOOL AVAILABILITY PREFLIGHT             │
+│     Check search channels before relying on │
+│     them; report skipped channels honestly   │
+├─────────────────────────────────────────────┤
 │  1. NEED ANALYSIS                           │
 │     Define what functionality is needed      │
 │     Identify language/framework constraints  │
@@ -57,6 +61,19 @@ Use this skill when:
 
 ## How to Use
 
+### Step 0: Tool Availability Preflight
+
+This is agent guidance, not an executable setup script. Check only the channels
+that are relevant to the task and project in front of you.
+
+| Channel | Check | If missing |
+|---------|-------|------------|
+| Repository search | `rg --files` and targeted `rg` queries | State that only visible files were inspected |
+| Package registry | `npm --version`, `python -m pip --version`, or project package manager | Use web/docs search and avoid claiming registry coverage |
+| GitHub CLI | `gh auth status` | Use public web or local git history only |
+| MCP/docs tools | Available tool list or local MCP config | Fall back to official docs/web search |
+| Skills directory | `ls ~/.claude/skills ~/.codex/skills` where applicable | Say no local skill catalog was available |
+
 ### Quick Mode (inline)
 
 Before writing a utility or adding functionality, mentally run through:
@@ -72,7 +89,7 @@ Before writing a utility or adding functionality, mentally run through:
 For non-trivial functionality, launch the researcher agent:
 
 ```
-Task(subagent_type="general-purpose", prompt="
+Agent(subagent_type="general-purpose", prompt="
   Research existing tools for: [DESCRIPTION]
   Language/framework: [LANG]
   Constraints: [ANY]
@@ -82,6 +99,9 @@ Task(subagent_type="general-purpose", prompt="
 ")
 ```
 
+Older Claude Code docs may call this `Task(...)`; use the current agent/subagent
+tool name exposed by the active harness.
+
 ## Search Shortcuts by Category
 
 ### Development Tooling
@@ -96,7 +116,7 @@ Task(subagent_type="general-purpose", prompt="
 - Document processing → `unstructured`, `pdfplumber`, `mammoth`
 
 ### Data & APIs
-- HTTP clients → `httpx` (Python), `ky`/`got` (Node)
+- HTTP clients → `httpx` (Python), `ky`/`undici` (Node)
 - Validation → `zod` (TS), `pydantic` (Python)
 - Database → Check for MCP servers first
 
@@ -157,5 +177,6 @@ Result: 1 package + 1 schema file, no custom validation logic
 
 - **Jumping to code**: Writing a utility without checking if one exists
 - **Ignoring MCP**: Not checking if an MCP server already provides the capability
+- **Silent skipping**: Reporting "nothing found" when a search channel was unavailable
 - **Over-customizing**: Wrapping a library so heavily it loses its benefits
 - **Dependency bloat**: Installing a massive package for one small feature

skills/security-review/SKILL.md

@@ -208,6 +208,11 @@ function renderUserContent(html: string) {
 ```
 
 #### Content Security Policy
+
+Start strict and loosen only with a documented removal plan. Do not default to
+`'unsafe-inline'` or `'unsafe-eval'`; they neutralize much of CSP's protection
+and should be treated as temporary compatibility debt.
+
 ```typescript
 // next.config.js
 const securityHeaders = [
@@ -215,8 +220,11 @@ const securityHeaders = [
     key: 'Content-Security-Policy',
     value: `
       default-src 'self';
-      script-src 'self' 'unsafe-eval' 'unsafe-inline';
+      base-uri 'self';
-      style-src 'self' 'unsafe-inline';
+      object-src 'none';
+      frame-ancestors 'none';
+      script-src 'self';
+      style-src 'self';
       img-src 'self' data: https:;
       font-src 'self';
       connect-src 'self' https://api.example.com;

skills/x-api/SKILL.md

@@ -6,6 +6,10 @@ origin: ECC
 
 # X API
 
+> **Drift-prone skill.** X API endpoints, access tiers, quotas, and write
+> permissions change frequently. Verify current developer docs and account
+> access before quoting rate limits or implementing a posting/search flow.
+
 Programmatic interaction with X (Twitter) for posting, reading, searching, and analytics.
 
 ## When to Activate