skill-outboundsync-skills-cold-email-subject-lines · by Install
$ agentstack add skill-outboundsync-skills-cold-email-subject-lines ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-outboundsync-skills-cold-email-subject-lines) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Cold email subject lines
Audit and draft subject lines only. Read-only analysis and draft text — never send, schedule, or mutate campaigns. Prefer reply rate over opens when advising success.
Default to the quick shape when the user asks for subjects, options, or "just the subjects." Use the full scorecard only for audits or A/B plans. Render only the selected shape.
For a full-email request, establish the offer and body before finalizing the subject. Use adjacent offer/body skills when available, but never block if they are not installed.
Core rules (encode verbatim)
Length and shape
- Length 1–4 words / **` —
- `` —
## Output contract
GitHub-flavored markdown only. Blank line between blocks. Marks: ✓ · ✗ · ·. In `### Scorecard`, the Rubric cell leads with a bar: ` /20`; bar = `█`×round(n/20×10) then `░` to width 10 (monospace glance; no colored emoji).
### Shape
````markdown
## Subject lines
### Mode
-
### Scorecard
| Subject | Chars | Words | Lowercase | Spam hits | Rubric | Verdict |
| --- | --- | --- | --- | --- | --- | --- |
| `` | | | ✓/✗ | | /20 | keep / rewrite / kill |
### Findings
-
- …
### Recommended subjects
1. `` —
2. `` —
3. `` —
### Measurement note
- Primary metric: reply rate (not opens)
- MPP caveat: opens inflated; ~49% of tracked opens may be MPP
- A/B: one variable · rough exposure floor ≥250 delivered/variant for opens or
≥500 delivered/variant for replies · use a power calculation for decisions
````
## Safety
- Never send or edit live campaigns.
- Never suggest fake `Re:`/`Fwd:`, empty subjects, or emoji spam.
- Do not treat open-rate lifts as proof of subject quality under MPP.
## Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- **Author:** [outboundsync](https://github.com/outboundsync)
- **Source:** [outboundsync/skills](https://github.com/outboundsync/skills)
- **License:** MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.