fix: stop hermes update from nagging about llm-wiki's wiki.path (#11222)

llm-wiki was the only shipped skill using metadata.hermes.config, which
caused 'hermes update' and 'hermes config migrate' to prompt for a wiki
directory on every run — even for users who have never touched the skill
— because 'enabled' is opt-out (all shipped skills count as enabled unless
explicitly disabled). Declining the prompt didn't persist anything, so
the nag fired again on every update.

Switch llm-wiki to the env var + runtime default pattern that obsidian and
google-workspace already use: WIKI_PATH env var, default $HOME/wiki. No
prompting infrastructure, no config.yaml touch, no nag loop.

Changes:
- skills/research/llm-wiki/SKILL.md: remove metadata.hermes.config,
  document WIKI_PATH env var in the Wiki Location section, update the
  orientation snippet and initialization guidance.
- Docs: replace llm-wiki's wiki.path examples with a generic 'myplugin.path'
  placeholder across configuration.md, features/skills.md, and
  creating-skills.md so users don't try to set skills.config.wiki.path
  expecting llm-wiki to use it.
- skills-catalog.md: mention WIKI_PATH instead of skills.config.wiki.path.

E2E verified: discover_all_skill_config_vars() and get_missing_skill_config_vars()
both return 0 entries after this change, so the prompt branch in migrate_config()
no longer fires.

The metadata.hermes.config feature stays in place for third-party skills
that genuinely need structured config, but built-ins now prefer env vars.

website/docs/reference/skills-catalog.md

@@ -253,7 +253,7 @@ Skills for academic research, paper discovery, literature review, domain reconna
 |-------|-------------|------|
 | `arxiv` | Search and retrieve academic papers from arXiv using their free REST API. No API key needed. Search by keyword, author, category, or ID. Combine with web_extract or the ocr-and-documents skill to read full paper content. | `research/arxiv` |
 | `blogwatcher` | Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI. Add blogs, scan for new articles, and track what you've read. | `research/blogwatcher` |
-| `llm-wiki` | Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency. Unlike RAG, the wiki compiles knowledge once and keeps it current. Works as an Obsidian vault. Configurable via `skills.config.wiki.path`. | `research/llm-wiki` |
+| `llm-wiki` | Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency. Unlike RAG, the wiki compiles knowledge once and keeps it current. Works as an Obsidian vault. Wiki path is controlled by the `WIKI_PATH` env var (defaults to `~/wiki`). | `research/llm-wiki` |
 | `domain-intel` | Passive domain reconnaissance using Python stdlib. Subdomain discovery, SSL certificate inspection, WHOIS lookups, DNS records, domain availability checks, and bulk multi-domain analysis. No API keys required. | `research/domain-intel` |
 | `duckduckgo-search` | Free web search via DuckDuckGo — text, news, images, videos. No API key needed. Prefer the `ddgs` CLI when installed; use the Python DDGS library only after verifying that `ddgs` is available in the current runtime. | `research/duckduckgo-search` |
 | `ml-paper-writing` | Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verificatio… | `research/ml-paper-writing` |