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 write-outreach-outreach-qagit 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/write-outreach-outreach-qa)<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/write-outreach-outreach-qa"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/write-outreach-outreach-qa/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/write-outreach-outreach-qa"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/write-outreach-outreach-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00055 | $0.00602 |
| Opus 5.5 | $0.00022 | $0.00241 |
| Sonnet 5.5 | $0.00011 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
write-outreach-outreach-qa 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 4d 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.
What it actually says
outreach-qa
Run on the whole pack and the send file. Fix every failure, then run again. Nothing about the check goes into the pack itself.
Facts and proof
- Every first line rests on its row's signal or hook URL and date (
signal_1_date/hook_date); the fact still says that (a sample of 5 rows re-checked by link, or every row when under 10). - No invented compliment, mutual connection, number, customer, result, peer story, "brands like X", "most teams we talk to". Every proof line went through claims-gate; cuts are listed with the proof that would restore them.
- Prices and product facts match the brand's site or brain, with the date read.
Compliance
- Each email has the sender's name and company, a postal address placeholder the marketer fills once, and the opt-out line.
- Row rules applied: no email body for
UK-soletrader(letter instead), non-publishedCASL/AU-NZ, Germany/Austria rows; unchecked and catch-all addresses sit inemail_to_check, neveremail; EU and unknown-country first emails carry the source-and-object line; the one-line country summary is in the pack. - Suppressed, cooled-down and duplicate rows are out of the send file, with counts.
Craft
- Touch 1 50–90 words (fail over 120); follow-ups shorter; subjects under 50 characters (fail over 60); connection notes ≤200 characters (≤300 only if the marketer said paid).
- At most 6 touches per person; one ask per message; no calendar link to a stranger in touch 1; no attachment; at most one link.
- No banned words or openers (email-craft.md § Hard rules); nothing about us in the first sentence.
- Follow-ups each add something new; LinkedIn text differs from the email.
- Swap test: swap two rows' first lines — if they still fit, they're generic; rewrite.
The pack
- The brand copy holds no person's name, company or first line.
- write-report §3 passes; its first move is who to send to first and why (with no list, that there is no one yet). Outside tools the marketer runs (an email finder, a checker, a sending tool) may be named as examples, never endorsed.
- The send file imports: header row, one subject and body column per touch, no merged cells, UTF-8.
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.
- 4d ago First seen · 35 lines · 55 tokens per session scan A e862f7fe1e6c
write-outreach-outreach-qa is a skill published in the GitHub repository gooseworks-ai/goose-skills (1,265 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 602 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-21.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.