Skill audit report

Manifest Audit report.

Manifest provides smart routing for LLMs in OpenClaw, significantly reducing costs.

REVIEWED · REVIEWSafe to tryGenerated Aug 22, 2026Heuristic metadata audit

91

Audit

88

Trust

100

Quality

82

Security

88

Maintain

92

Install

OpenAgentSkill Trust Score

88

Production candidate

OpenAgentSkill Trust Score

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

PASS

94

7.1K GitHub stars

Stars/forks activity

PASS

88

7.1K stars, 459 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

88

2mo since push

License clarity

WARN

42

Unknown

README/SKILL.md completeness

PASS

84

Metadata includes enough usage and workflow context

Dependency/runtime risk

PASS

90

no major dependency risk hints in public metadata

Install availability

PASS

92

npx skills add mnfst/manifest

Install command safety

PASS

92

standard package or runtime install path

Permission surface

PASS

100

no high-risk permission surface in public metadata

Repository evidence

PASS

86

https://github.com/mnfst/manifest

Review status

PASS

88

AI review data available

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

10 Passed · 3 Needs review

Install path

92

PASS

npx skills add mnfst/manifest

Repository

88

PASS

https://github.com/mnfst/manifest

License

45

CHECK

Unknown

Maintenance

88

PASS

2mo since push

AI review

88

PASS

Approved with no listed issues

README/SKILL.md completeness

84

PASS

Usable description available

Dependency risk

90

PASS

no major dependency risk hints in public metadata

Install command safety

92

PASS

standard package or runtime install path

Permission surface

100

PASS

no high-risk permission surface in public metadata

Stars/forks activity

88

PASS

7.1K stars, 459 forks; issue activity unavailable in current metadata

Adoption

88

PASS

7.1K GitHub stars

Warnings

License is unclear
License clarity: Unknown

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.

Install path

Review the report before installing into production agents.

$ npx skills add mnfst/manifest

Agent-readable metadata

Machine decision packet

Embedded JSON exposes suited tasks, suited agents, install command, trust score, safety gate, alternatives, and do-not-use conditions for agent review.

Install policy: review
Best agents: Codex + Claude Code
Alternatives: 2

Open agent JSON

Signals

Audit score: 91/100
Quality: 100/100
Trust: 88/100
Install safety: 92/100
Permission surface: 100/100
Maintenance: 2mo since push
Events: 31 events
GitHub stars: 7.1K
Last push: Jun 26, 2026

Agent safety v2

79/100 · Review before install

Reviewedreview

Good audit and safety signals with no high-risk permission hints in public metadata.

Review the audit page, then allow agent install in a sandboxed workflow.

Safe-to-try audit
79/100 agent safety score

Network access

medium

Skill likely fetches remote pages, APIs, repositories, or external services.

License is unclear

Back to skill Alternatives Audit badge SVG

Compare nearby options

Related skills to audit next

Khazix Skills

A collection of practical, installable AI agent skills for disk cleanup, AI news retrieval, and project management, following the Agent Skills standard.

20K Stars · Audit report

Awesome Claude Skills

A curated list of resources and tools for enhancing Claude AI workflows.

66K Stars · Audit report

OpenAgentSkillRegistry

Star200+Submit Skill

200+

Skill audit report

Manifest Audit report.

Manifest provides smart routing for LLMs in OpenClaw, significantly reducing costs.

REVIEWED · REVIEWSafe to tryGenerated Aug 22, 2026Heuristic metadata audit

91

Audit

88

Trust

100

Quality

82

Security

88

Maintain

92

Install

OpenAgentSkill Trust Score

88

Production candidate

OpenAgentSkill Trust Score

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

PASS

94

7.1K GitHub stars

Stars/forks activity

PASS

88

7.1K stars, 459 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

88

2mo since push

License clarity

WARN

42

Unknown

README/SKILL.md completeness

PASS

84

Metadata includes enough usage and workflow context

Dependency/runtime risk

PASS

90

no major dependency risk hints in public metadata

Install availability

PASS

92

npx skills add mnfst/manifest

Install command safety

PASS

92

standard package or runtime install path

Permission surface

PASS

100

no high-risk permission surface in public metadata

Repository evidence

PASS

86

https://github.com/mnfst/manifest

Review status

PASS

88

AI review data available

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

10 Passed · 3 Needs review

Install path

92

PASS

npx skills add mnfst/manifest

Repository

88

PASS

https://github.com/mnfst/manifest

License

45

CHECK

Unknown

Maintenance

88

PASS

2mo since push

AI review

88

PASS

Approved with no listed issues

README/SKILL.md completeness

84

PASS

Usable description available

Dependency risk

90

PASS

no major dependency risk hints in public metadata

Install command safety

92

PASS

standard package or runtime install path

Permission surface

100

PASS

no high-risk permission surface in public metadata

Stars/forks activity

88

PASS

7.1K stars, 459 forks; issue activity unavailable in current metadata

Adoption

88

PASS

7.1K GitHub stars

Warnings

License is unclear
License clarity: Unknown

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.

Install path

Review the report before installing into production agents.

$ npx skills add mnfst/manifest

Agent-readable metadata

Machine decision packet

Embedded JSON exposes suited tasks, suited agents, install command, trust score, safety gate, alternatives, and do-not-use conditions for agent review.

Install policy: review
Best agents: Codex + Claude Code
Alternatives: 2

Open agent JSON

Signals

Audit score: 91/100
Quality: 100/100
Trust: 88/100
Install safety: 92/100
Permission surface: 100/100
Maintenance: 2mo since push
Events: 31 events
GitHub stars: 7.1K
Last push: Jun 26, 2026

Agent safety v2

79/100 · Review before install

Reviewedreview

Good audit and safety signals with no high-risk permission hints in public metadata.

Review the audit page, then allow agent install in a sandboxed workflow.

Safe-to-try audit
79/100 agent safety score

Network access

medium

Skill likely fetches remote pages, APIs, repositories, or external services.

License is unclear

Back to skill Alternatives Audit badge SVG

Compare nearby options

Related skills to audit next

Khazix Skills

A collection of practical, installable AI agent skills for disk cleanup, AI news retrieval, and project management, following the Agent Skills standard.

20K Stars · Audit report

Awesome Claude Skills

A curated list of resources and tools for enhancing Claude AI workflows.

66K Stars · Audit report

OpenAgentSkillRegistry

Star200+Submit Skill

200+

Skill audit report

Manifest Audit report.

Manifest provides smart routing for LLMs in OpenClaw, significantly reducing costs.

REVIEWED · REVIEWSafe to tryGenerated Aug 22, 2026Heuristic metadata audit

91

Audit

88

Trust

100

Quality

82

Security

88

Maintain

92

Install

OpenAgentSkill Trust Score

88

Production candidate

OpenAgentSkill Trust Score

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

PASS

94

7.1K GitHub stars

Stars/forks activity

PASS

88

7.1K stars, 459 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

88

2mo since push

License clarity

WARN

42

Unknown

README/SKILL.md completeness

PASS

84

Metadata includes enough usage and workflow context

Dependency/runtime risk

PASS

90

no major dependency risk hints in public metadata

Install availability

PASS

92

npx skills add mnfst/manifest

Install command safety

PASS

92

standard package or runtime install path

Permission surface

PASS

100

no high-risk permission surface in public metadata

Repository evidence

PASS

86

https://github.com/mnfst/manifest

Review status

PASS

88

AI review data available

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

10 Passed · 3 Needs review

Install path

92

PASS

npx skills add mnfst/manifest

Repository

88

PASS

https://github.com/mnfst/manifest

License

45

CHECK

Unknown

Maintenance

88

PASS

2mo since push

AI review

88

PASS

Approved with no listed issues

README/SKILL.md completeness

84

PASS

Usable description available

Dependency risk

90

PASS

no major dependency risk hints in public metadata

Install command safety

92

PASS

standard package or runtime install path

Permission surface

100

PASS

no high-risk permission surface in public metadata

Stars/forks activity

88

PASS

7.1K stars, 459 forks; issue activity unavailable in current metadata

Adoption

88

PASS

7.1K GitHub stars

Warnings

License is unclear
License clarity: Unknown

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.

Install path

Review the report before installing into production agents.

$ npx skills add mnfst/manifest

Agent-readable metadata

Machine decision packet

Embedded JSON exposes suited tasks, suited agents, install command, trust score, safety gate, alternatives, and do-not-use conditions for agent review.

Install policy: review
Best agents: Codex + Claude Code
Alternatives: 2

Open agent JSON

Signals

Audit score: 91/100
Quality: 100/100
Trust: 88/100
Install safety: 92/100
Permission surface: 100/100
Maintenance: 2mo since push
Events: 31 events
GitHub stars: 7.1K
Last push: Jun 26, 2026

Agent safety v2

79/100 · Review before install

Reviewedreview

Good audit and safety signals with no high-risk permission hints in public metadata.

Review the audit page, then allow agent install in a sandboxed workflow.

Safe-to-try audit
79/100 agent safety score

Network access

medium

Skill likely fetches remote pages, APIs, repositories, or external services.

License is unclear

Back to skill Alternatives Audit badge SVG

Compare nearby options

Related skills to audit next

Khazix Skills

A collection of practical, installable AI agent skills for disk cleanup, AI news retrieval, and project management, following the Agent Skills standard.

20K Stars · Audit report

Awesome Claude Skills

A curated list of resources and tools for enhancing Claude AI workflows.

66K Stars · Audit report