feat(skills): add skill config interface + llm-wiki skill (#5635)

Skills can now declare config.yaml settings via metadata.hermes.config
in their SKILL.md frontmatter. Values are stored under skills.config.*
namespace, prompted during hermes config migrate, shown in hermes config
show, and injected into the skill context at load time.

Also adds the llm-wiki skill (Karpathy's LLM Wiki pattern) as the first
skill to use the new config interface, declaring wiki.path.

Skill config interface (new):
- agent/skill_utils.py: extract_skill_config_vars(), discover_all_skill_config_vars(),
  resolve_skill_config_values(), SKILL_CONFIG_PREFIX
- agent/skill_commands.py: _inject_skill_config() injects resolved values
  into skill messages as [Skill config: ...] block
- hermes_cli/config.py: get_missing_skill_config_vars(), skill config
  prompting in migrate_config(), Skill Settings in show_config()

LLM Wiki skill (skills/research/llm-wiki/SKILL.md):
- Three-layer architecture (raw sources, wiki pages, schema)
- Three operations (ingest, query, lint)
- Session orientation, page thresholds, tag taxonomy, update policy,
  scaling guidance, log rotation, archiving workflow

Docs: creating-skills.md, configuration.md, skills.md, skills-catalog.md

Closes #5100

website/docs/reference/skills-catalog.md

@@ -252,6 +252,7 @@ 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` |
 | `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` |