feat(ai): support project-defined skills (skills/*.md) for AI agents - #9851

Skills are markdown files at skills/<name>.md or skills/<name>/SKILL.md
with YAML front matter (description required; optional name, metrics_views,
agents, always_apply) that teach Rill's AI agents project-specific practices
such as analysis playbooks and business glossaries.

Runtime:
- New session-scoped loader in runtime/ai reads skills from the repo;
  malformed files are reported as issues and logged, never failing the session.
- New list_skills and load_skill tools gated on UseAI only,
  so cloud viewers without repo access can use them;
  they are exposed on the MCP server automatically for external clients.
- The analyst agent's prompt gains an index of relevant skills
  (scope-filtered by the dashboard's metrics views) and inlines always_apply
  skill bodies after ai_instructions, capped at 32kb.
- The MCP server instructions tell clients to discover and load skills.
- instructions.ParseFrontMatter is exported and shared with the embedded instructions.

Frontend:
- load_skill/list_skills render in the chat thinking trace with a skill icon.
- Add > More gains an "AI Skill" entry that creates skills/my_skill.md from
  a starter template; skill files get a dedicated icon in the file explorer.

Claude-Session: https://claude.ai/code/session_017udazBgdXmdTXMTq7sTh2L

… Skills format

Addresses PR review feedback:
- Skills are now parsed in runtime/parser into a new Skill resource kind, inserted into the catalog by the project parser, and read from the catalog by the AI session, so API code no longer reads the repo directly.
- The file format follows the Agent Skills standard (https://agentskills.io): a skill is a directory with a SKILL.md file, the name must match the directory, and the standard optional fields are accepted. Rill's metrics_views/agents/always_apply remain as extension fields that other clients ignore. Skills are also loaded from .agents/skills/ for cross-client compatibility.
- Skill parsing no longer depends on the runtime/ai/instructions package; its ParseFrontMatter export is reverted.
- Invalid skill files now surface as parse errors on the file, and a skill scoped to a nonexistent metrics view gets a reconcile error.

Claude-Session: https://claude.ai/code/session_017udazBgdXmdTXMTq7sTh2L

- Fix `TestAnalystSkills` to use the `skills/<name>/SKILL.md` layout, which the flat
  `skills/<name>.md` paths stopped matching after the Agent Skills refactor.
- Forward `list_skills` and `load_skill` on the Cloud unified MCP server, which
  advertised the skills instructions without exposing the tools they reference.
- Generate unique skill directory names with hyphens instead of post-processing
  `getName`'s `_N` suffix, which could produce an existing name and silently fail
  the create.
- List skills with a dedicated `**/SKILL.md` glob so unrelated markdown files
  don't count against `drivers.RepoListLimit` and fail the whole parse.
- Wire skills into the developer agent, so `agents: [developer]` is no longer
  inert, and share the prompt-building logic with the analyst agent.
- Filter skills by agent in `list_metrics_views`, so developer-only skills don't
  leak into the `ai_instructions` served to external clients.
- Require `UseAI` to access a skill resource, and note in the docs that this
  includes anonymous visitors on public projects.
- Report empty skill front matter as a missing `description` instead of an
  unclosed delimiter.
- Resolve the skills instructions during the MCP initialization handshake instead
  of on every stateless request.

Claude-Session: https://claude.ai/code/session_01WTWACZUSP88ypUfVb8FbJr

…structions

Claude-Session: https://claude.ai/code/session_01P9788r3dVASEXmdLQq57RX

- Resolve explore/canvas metrics views on every analyst invocation so skill scoping works on follow-ups
- Skip skills with reconcile errors when loading them into the session
- Match metrics view scopes case-insensitively
- Reject whitespace-only skill descriptions and require an exact "---" front matter delimiter

Claude-Session: https://claude.ai/code/session_014SrRA996FvGTcB891M5sWS

- Keep `skill` out of the generic YAML kind parser so `type: skill` yields a parse error instead of a panic
- Apply the always-apply size cap to the fully rendered section, including headings and separators

Claude-Session: https://claude.ai/code/session_014SrRA996FvGTcB891M5sWS

- Cap the on-demand skill index and point the agent to list_skills for the rest
- Count the description limit in characters rather than bytes
- Avoid skill name collisions with .agents/skills when creating a skill in the UI
- Document that name is required by the Agent Skills format and that always_apply falls back to on-demand loading past the budget

Claude-Session: https://claude.ai/code/session_014SrRA996FvGTcB891M5sWS

- Expose list_skills to the analyst and developer agents so the capped skill index fallback is actionable
- Gate the list_metrics_views skill enrichment and the MCP skills instructions on UseAI, matching the skill tools
- Give always-apply skills their own 32 KiB budget in list_metrics_views, separate from ai_instructions
- Render scoped always-apply skills with the metrics views they apply to (shared skillSection helper)
- Glob only the two skill roots for SKILL.md files instead of the whole repo
- Add Skill to the file-artifact initialization whitelist so reload attaches skill resources
- Drop the unused Skill.Path field and json tags

…rt files

- develop_file builds its own prompt without the parent conversation, so it now receives the developer skills (always-apply bodies, index, and the list_skills/load_skill tools) like the developer agent
- The parser ignores SQL/YAML files inside a skill directory (other than SKILL.md) on both full and incremental parses, so skill references and examples don't become project resources or parse errors
- Document that supporting files in a skill directory are ignored

…nstructions static

- list_skills and load_skill return false from CheckAccess when the project defines no skills, so they are not advertised; the MCP instructions no longer vary by project
- Drop the redundant UseAI check on the list_metrics_views skill enrichment
- Use ctxsync.RWMutex for the memoized skills so loading respects context cancellation