Install
$ agentstack add skill-outboundsync-skills-omnichannel-campaigns ✓ 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.
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
Omnichannel campaigns (email + social)
Plan email + B2B social networking (professional social platforms) outbound as one system. Draft plans and scorecards only — never send, schedule, activate campaigns, or mutate CRM/SEP data.
Render only the selected output shape. No invented metrics, scarcity, or case-study numbers the user did not provide.
Note: These instructions reflect OutboundSync best practices shared freely and without warranty of outcomes — see [DISCLAIMER.md](../../DISCLAIMER.md). Treat techniques as widely-taught industry patterns; do not paste copyrighted course modules or private playbooks.
When to use adjacent skills
| Need | Skill | | --- | --- | | Offer / CTA | outbound-offer | | Email body | cold-email-body | | Subject lines | cold-email-subject-lines | | Connection note copy | connection-requests | | Launch wiring / Sources | preflight | | CRM reply performance | crm-analysis |
Never block if an adjacent skill is missing — return this skill’s plan and list remaining inputs.
Modes
Audit— score an existing multi-channel plan; name gaps.Draft— produce a channel map + sequence skeleton from ICP / offer / assets.
Infer from the ask. If both needed, Audit then Draft.
Design principles (patterns, not prescriptions)
Encode these as checks. Treat them as widely-taught industry patterns, not proprietary playbooks — describe the technique itself, and never invent metrics or attribute claims to specific people or companies.
- One job per touch — each step has a single job (open a loop, earn a connect, bump, break up).
- Channel fit — email for async narrative + CTA; social for familiarity, soft bumps, and relationship context — not a second identical pitch dump.
- Familiarity before ask — light social presence / connect intent before heavy asks when the motion is cold.
- Handoffs are explicit — when a reply or accept happens, stop the parallel sequence; define who owns the thread.
- Volume is a constraint — respect mailbox and social limits; prefer fewer high-signal touches over parallel spam.
- Same offer, different surface — offer/CTA stays coherent; copy length and proof density change by channel.
- Breakup is a step — plan an exit; do not infinite-nudge.
Rubric detail: [references/channel-rubric.md](references/channel-rubric.md). Sequence skeletons: [references/sequence-patterns.md](references/sequence-patterns.md).
Required inputs
Collect or mark missing:
- ICP / persona
- Offer + soft CTA (or run
outbound-offerfirst) - Channels in scope (email, B2B social networking sites, other)
- Assets available (case study, resource, personalization signals)
- Constraints (daily send caps, seat count, compliance notes the user states)
Output contract
GitHub-flavored markdown only. Blank line between blocks. Marks: ✓ pass · ✗ fail · · advisory. In ### Scorecard, the Score cell leads with a bar: /5; bar = █×n then ░ to width 5 (monospace glance; no colored emoji).
Quick (default for “build me a sequence”)
## Omnichannel plan
- Goal:
- Channels:
- Spine:
- Handoff:
- Watchouts:
Scorecard (Audit)
## Omnichannel audit
| Lever | Score | Note |
| --- | --- | --- |
| Channel fit | n/5 | |
| One job per touch | n/5 | |
| Familiarity before ask | n/5 | |
| Handoff clarity | n/5 | |
| Volume safety | n/5 | |
| Offer coherence | n/5 | |
| Exit / breakup | n/5 | |
**Weakest lever:**
**Rewrite focus:**
Scores are judgment against the rubric — not industry benchmarks.
Safety
- No sends, CRM writes, or SEP mutations.
- No fabricated proof or reply-rate claims.
- Respect platform terms the user mentions; this skill is not legal advice.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: outboundsync
- Source: 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.