Pre-install eval
llm-wiki Eval report.
A machine-readable install decision for agents: task fit, Trust Score, Audit Score, install safety, permission surface, and a concrete validation plan before this skill touches a workspace.
do not auto install
Permission surface: secrets or environment access, filesystem or document access
Required gates
Checks an agent must pass before install
Task fit
84
Task wording matches this skill metadata.
- Evaluate llm-wiki before installing it in an agent workflow
- research
- RAG and knowledge workflows; Claude Code teams; teams that value GitHub adoption signals
Install path
92
Install handoff is available.
- npx skills add Ar9av/obsidian-wiki --skill llm-wiki
Install command safety
92
standard package or runtime install path
- npx skills add Ar9av/obsidian-wiki --skill llm-wiki
Trust score
71
Potentially useful, but at least one trust signal needs human inspection.
- Manual review
- 3.4K GitHub stars
- MIT
Audit score
79
Needs review
- Permission surface may require sandboxing
Agent safety gate
43
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- Test manually in an isolated workspace and compare against safer alternatives.
- High-risk permission hints: Secrets or environment access
License clarity
86
MIT
- MIT
Permission surface
34
secrets or environment access, filesystem or document access
- Browser automation: medium
- Network access: medium
- Filesystem access: medium
Validation plan
What the agent should do next
- 1Inspect repository, README/SKILL.md, license, and recent commits before production use.
- 2Install in an isolated workspace or sandbox with no production secrets available.
- 3Run the smallest representative task and record files touched, commands run, network access, and outputs.
- 4Compare the selected skill against at least one alternative when the eval status is review or failed.
- 5Promote only after the agent reports a successful verification result and unresolved warnings are accepted.
Do not use when
Conditions that require another skill
- teams that need a vendor-supported SLA
- production agents without a repository review
- The WRITING.md file appears to be an empty template with no actual writing preferences; it may confuse users if they expect guidance on tone or style.
- High-risk permission hints: Secrets or environment access
- Permission surface may require sandboxing
- The skill is explicitly a 'theory' skill and relies on other skills (ingesting, querying, linting) for operational workflows; without those companion skills, this skill alone is not directly executable.
Supporting checks
Trust signals behind the decision
README/SKILL.md completeness
pass86
Metadata includes enough usage and workflow context
Recent maintenance
pass88
2mo since push
Alternatives available
pass82
Alternative skills are available for comparison.