Goose Skills is a library of workflows and data APIs that lets coding agents handle growth and go-to-market work such as advertising, social media, content, SEO, lead generation, and customer research. It is intended for teams using Claude Code, Cursor, Codex, and similar agents. The catalogue entries are its reusable skills.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gooseworks-ai/goose-skills --skill news-signal-outreachgit clone --depth 1 https://github.com/gooseworks-ai/goose-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gooseworks-ai/goose-skills/news-signal-outreach)<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/news-signal-outreach"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/news-signal-outreach/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/news-signal-outreach"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/news-signal-outreach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00201 | $0.07524 |
| Opus 5 | $0.00101 | $0.03762 |
| Sonnet 5 | $0.00040 | $0.01505 |
| Haiku 4.5 | $0.00020 | $0.00752 |
Grade A, and why
news-signal-outreach scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 804 lines — stays where its author put it; the contents beside it link to each section on GitHub.
News Signal Outreach
The catch-all signal composite. Every other composite handles a specific signal type (funding, hiring, leadership change, champion move). This one handles everything else — any piece of news or public event that could create a reason to reach out.
A regulation change. A product recall. A competitor acquisition. A market expansion. A layoff. An earnings miss. A new partnership. An industry report. A conference keynote. A viral LinkedIn post. Any external event that shifts a company's priorities, creates urgency, or opens a window for your product.
Why this composite exists: The world generates an infinite stream of potential outreach triggers. The four structured signal composites handle the most common patterns. This composite handles the long tail — the unpredictable, opportunistic moments that often produce the best outreach because nobody else is sending a templated sequence about them.
When to Auto-Load
Load this composite when ANY of these are true:
- User shares ANY URL (LinkedIn post, article, tweet, blog, news) and asks about a company or person mentioned in it
- User says "came across", "saw this post", "found this article", "check this out", "is this relevant", "is this company a fit", "should we reach out"
- User mentions a company or person they discovered from an external source (social media, news, conference, podcast, newsletter) and asks about relevance or fit
- User asks "can we reach out to anyone based on this?"
- User says "check if this news is relevant to our prospects", "news-based outreach", "trigger-based outreach"
- User has a list of companies and wants to check recent news for outreach angles
- The news doesn't fit neatly into funding, hiring, leadership change, or champion move categories
- An upstream workflow surfaces a news item that needs evaluation
Key principle: If the user shares an external signal (URL, post, article, mention) and asks ANY question about the companies/people in it — load this composite. Don't wait for the word "outreach." The composite handles both evaluation-only (Steps 1-3) and full outreach (Steps 1-6).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 804 lines · 201 tokens per session scan A d79217f85875
news-signal-outreach is a skill published in the GitHub repository gooseworks-ai/goose-skills (1,202 stars, last pushed 11d ago), licensed MIT. It adds 201 tokens to every session and 7,524 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
sequence-architect
Design a 4-6 touch outreach cadence with channels, timing, tonal arc, and branching. Use when starting a new sequence from scratch given an ICP and offer.
icebreaker
Draft 3 distinct opening messages for a specific prospect, anchored on a why-now and a why-this-person. Use when sending a high-leverage first touch where personalization is worth the time.
sequence-doctor
Audit an outreach sequence and produce a ranked fix list. Use when reply rates are low, when you want a second opinion before sending, or when rewriting a sequence from scratch.
jargon-bingo
Score sales calls, emails, or posts on a 5x5 bingo card of cliches. Mostly for fun; quietly useful for spotting jargon-heavy patterns.
prospect-twin
Build a believable persona simulation of a prospect from their LinkedIn profile, then practice outreach against them. Use when preparing for a high-stakes outreach or call, when iterating on openers, or when testing whether a pitch lands.
cringe-translator
Translate sales-jargon-laden LinkedIn messages into what the sender actually means. Mostly for fun; occasionally educational about why a message tanked.