Skill audit report
Writes personalized B2B cold emails at a steady daily volume: researches real prospects against your ideal customer profile (ICP), drafts a genuinely 1:1 email for each, and dedupes against a permanent contact log that updates itself from real Gmail replies, bounces, and unsubscribes. Each email is timed to the prospect's local business hours, checked for deliverability and anti-spam compliance, and A/B-tracked by subject line, with the outreach strategy re-confirmed monthly. Queues everything for approval (or creates Gmail drafts if connected) and never sends on its own. Use for cold email, cold outreach, sales prospecting, lead generation, or sales outreach to new contacts. Not for drip or nurture emails to people who already opted in; that is email-sequence.
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
WARN48
33 GitHub stars
Stars/forks activity
WARN43
33 stars, 3 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
Pushed today
License clarity
PASS86
MIT
README/SKILL.md completeness
INFO76
Public metadata needs stronger README/SKILL.md context
Dependency/runtime risk
INFO64
command execution surface, network or browser surface
Install availability
PASS92
npx skills add marcosmodly/marketing-skill --skill email-outreach
Install command safety
PASS92
standard package or runtime install path
Permission surface
WARN48
shell or command execution, filesystem or document access
Repository evidence
PASS86
https://github.com/marcosmodly/marketing-skill/tree/main/skills/email-outreach
Review status
WARN46
AI review approval is missing
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add marcosmodly/marketing-skill --skill email-outreach
Repository
88
https://github.com/marcosmodly/marketing-skill/tree/main/skills/email-outreach
License
86
MIT
Maintenance
100
Pushed today
AI review
55
Review approval is missing
README/SKILL.md completeness
84
Warnings
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.
Compare nearby options
Eliminates predictable AI writing patterns from prose while preserving specific meaning and reader trust.
16K Stars · Audit report
Applies Cursor's prose-discipline rules to remove filler and AI writing tells from agent-facing and user-facing text.
4.8K Stars · Audit report
Rewrites AI-sounding text so it reads naturally while preserving every factual claim and matching the writer's voice.
37K Stars · Audit report
Usable description available
Dependency risk
64
command execution surface, network or browser surface
Install command safety
92
standard package or runtime install path
Permission surface
48
shell or command execution, filesystem or document access
Stars/forks activity
43
33 stars, 3 forks; issue activity unavailable in current metadata
Adoption
42
33 GitHub stars
Agent safety v2
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
Shell or command execution
highSkill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
Network access
mediumSkill likely fetches remote pages, APIs, repositories, or external services.
Filesystem access
mediumSkill may read or write project files, documents, generated artifacts, or local workspace state.