Star200+

Pre-install eval

cognee-cli 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.

FailedHigh riskBLOCK Policy
72
Eval report
74
Trust
83
Audit
39
Agent safety

do not auto install

Permission surface: secrets or environment access, shell or command execution

Required gates

Checks an agent must pass before install

Open JSON

Task fit

70

warn

Task fit is weak; compare alternatives before selecting.

  • Evaluate cognee-cli before installing it in an agent workflow
  • data-analysis
  • Research agents workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add topoteretes/cognee --skill cognee-cli

Install command safety

92

pass

standard package or runtime install path

  • npx skills add topoteretes/cognee --skill cognee-cli

Trust score

74

warn

Good trust signals with a few areas worth checking before rollout.

  • Strong shortlist
  • 30K GitHub stars
  • Apache-2.0

Audit score

83

warn

Needs review

  • Dependency or permission surface needs review

Agent safety gate

39

warn

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

  • Test manually in an isolated workspace and compare against safer alternatives.
  • Metadata combines secrets access with shell or command execution

License clarity

86

pass

Apache-2.0

  • Apache-2.0

Permission surface

18

fail

secrets or environment access, shell or command execution

  • Shell or command execution: high
  • Network access: medium
  • Filesystem access: medium

Validation plan

What the agent should do next

  1. 1Inspect repository, README/SKILL.md, license, and recent commits before production use.
  2. 2Install in an isolated workspace or sandbox with no production secrets available.
  3. 3Run the smallest representative task and record files touched, commands run, network access, and outputs.
  4. 4Compare the selected skill against at least one alternative when the eval status is review or failed.
  5. 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 skill documents `forget --all` as a destructive command without confirmation, but it clearly warns users about this risk, so it's acceptable.
  • No OpenAgentSkill engagement data yet
  • High-risk permission hints: Shell or command execution, Secrets or environment access
  • Dependency or permission surface needs review

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

86

Metadata includes enough usage and workflow context

Recent maintenance

pass

100

Pushed today

Alternatives available

pass

82

Alternative skills are available for comparison.