AgriciDaniel/claude-obsidian / skills/wiki
wiki
VerifiedInitialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt this vault, Obsidian vault, second brain setup, persistent wiki.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.1 KB |
| references/coordination.md | markdown | 1.9 KB |
| references/css-snippets.md | markdown | 4.3 KB |
| references/dataview.md | markdown | 1.6 KB |
| references/frontmatter.md | markdown | 2.7 KB |
| references/git-setup.md | markdown | 2.5 KB |
| references/install-modes.md | markdown | 1.9 KB |
| references/knowledge-recipes.md | markdown | 3.3 KB |
| references/mcp-setup.md | markdown | 1.9 KB |
| references/model-guidance.md | markdown | 1.6 KB |
| references/modes.md | markdown | 3.1 KB |
| references/operation-transactions.md | markdown | 6.0 KB |
| references/plugins.md | markdown | 2.7 KB |
| references/provenance.md | markdown | 3.2 KB |
| references/rest-api.md | markdown | 1.4 KB |
references/model-guidance.md
View on GitHub# Model and host compatibility
The canonical skills describe outcomes, evidence and mutation boundaries. Let
the host select its model; do not bake a model name or host-only frontmatter
into portable workflows. Keep private reasoning private and report the answer,
supporting evidence, actions and unresolved limits.
For Opus 5.5, start a controlled evaluation at its default `medium` effort and
measure quality, latency and usage before changing it. Its thinking is always
adaptive. API adapters must read content blocks by type, handle refusal and
incomplete output, and avoid forced tool choice. Existing clear prompts do not
need a wholesale rewrite merely because the model changed.
When building a prompt from source text, use a fresh application-generated
delimiter, encode source fields safely and state that the enclosed text is
untrusted data. A delimiter is defense in depth, not proof of injection
resistance. Validate generated artifacts independently before using them.
Primary guidance, reviewed 2026-10-17:
- [Opus 5.5 prompting](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5)
- [Opus 5.5 migration](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide)
For an acceptance run, record exact model and host versions, skill hashes,
fixture hashes, effective options, tool permissions and usage. Use synthetic
sources in a disposable vault and compare paired conditions on the same cases.
Keep offline, model, host-loading and native Obsidian evidence separate. Never
infer permission to send a private vault to a provider from a local test.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |