Add LLM key-hunter toolkit, vault, and skill

- tools/scripts/llm-key-hunter: GitHub leak hunting pipeline (hunt_*,
  pivot miner, two-layer verify/content caches, per-provider verification)
- usable_keys: verified key vault across 12 providers (deepseek, minimax,
  volcanoark, longcat, codingplan, zhipu free-tier, mimo, siliconflow, etc.)
- .grok/skills/llm-key-hunter: operator skill for the hunt/verify/vault flow
- NewAPI channel import scripts and CDP capture helpers
- Result verdict buckets (excluding multi-GB blob caches and dedup dumps)

tools/scripts/llm-key-hunter/results/live/china/zhipuai/README.md

@@ -0,0 +1,35 @@
+# ZhipuAI (智谱清言) — 63 usable keys
+
+## OpenAI-compatible endpoint
+```
+POST https://open.bigmodel.cn/api/paas/v4/chat/completions
+Authorization: Bearer <key>
+Content-Type: application/json
+```
+
+## Anthropic-compatible endpoint
+```
+POST https://open.bigmodel.cn/api/anthropic/v1/messages
+x-api-key: <key>
+anthropic-version: 2023-06-01
+Content-Type: application/json
+```
+
+## Models
+- OpenAI: `glm-4-flash` (free, confirmed working)
+- Anthropic: `glm-4.7`, `glm-4.6`, `glm-4.5`
+
+## Key format
+`32hex.16chars` (e.g. `07da445762144f82be2457dc58da35f6.luUK4XLKxBpRHmrK`)
+
+## Example
+```bash
+curl https://open.bigmodel.cn/api/paas/v4/chat/completions \
+  -H "Authorization: Bearer $(head -1 keys.txt)" \
+  -H "Content-Type: application/json" \
+  -d '{"model":"glm-4-flash","messages":[{"role":"user","content":"hi"}],"max_tokens":100}'
+```
+
+## Files
+- `keys.txt` — all 63 usable keys, one per line
+- Sample sources in `results/deep_verify/usable.txt`