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 messaging-ab-testergit 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/messaging-ab-tester)<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/messaging-ab-tester"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/messaging-ab-tester/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/messaging-ab-tester"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/messaging-ab-tester.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 | $0.00089 | $0.02301 |
| Opus 5 | $0.00044 | $0.01151 |
| Sonnet 5 | $0.00018 | $0.00460 |
| Haiku 4.5 | $0.00009 | $0.00230 |
Grade A, and why
messaging-ab-tester 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Messaging A/B Tester
Stop debating which message is better — test it. Generate messaging variants, deploy them through real channels, and measure which framing actually resonates with your ICP.
Core principle: At seed/Series A, you don't have enough traffic for website A/B tests. But you do have enough LinkedIn impressions and cold email sends to test messaging angles fast.
When to Use
- "Which of these value props should we lead with?"
- "Test our messaging angles and tell me which works"
- "I can't decide between [message A] and [message B]"
- "What messaging resonates most with [ICP]?"
- "Run a messaging test for [product/feature]"
Phase 0: Intake
What to Test
- Core value prop — The claim or positioning you want to test (e.g., "We help growth teams run outbound 10x faster")
- Test goal — What are you deciding? (Headline for website, cold email angle, LinkedIn content strategy, ad copy direction)
- ICP — Who should this resonate with? (Title, company type, stage)
- Current messaging — What are you using today? (Baseline to beat)
Test Channel
- Where to test:
- LinkedIn organic — Post variants across consecutive days, compare engagement
- Cold email — A/B test subject lines or opening hooks via Smartlead
- Both — Run in parallel for fastest signal
- Sample size available:
- LinkedIn: followers/typical impressions per post
- Email: list size available for testing
Constraints
- Number of variants — 3-5 recommended (more = slower signal)
- Test duration — How long to run? (Default: 1 week for LinkedIn, 3-5 days for email)
Phase 1: Generate Messaging Variants
Create 3-5 variants that test different angles, not just different words. Each variant should represent a distinct strategic bet:
Variant Types
| Type | What It Tests | Example |
|---|---|---|
| Outcome-driven | Leading with the result | "3x your pipeline in 30 days" |
| Pain-driven | Leading with the problem | "Tired of spending 4 hours a day on manual prospecting?" |
| Identity-driven | Leading with who they are | "Built for growth teams who move fast" |
| Proof-driven | Leading with evidence | "How [Customer] went from 10 to 50 demos/month" |
| Contrast-driven | Leading with what you're not | "Not another CRM. An outbound engine." |
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 · 265 lines · 89 tokens per session scan A e7c3fefba6d4
messaging-ab-tester is a skill published in the GitHub repository gooseworks-ai/goose-skills (1,202 stars, last pushed 11d ago), licensed MIT. It adds 89 tokens to every session and 2,301 once invoked, about $0.0004 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
excalidraw-ai
Create professional Excalidraw diagrams by generating JSON directly. This skill provides the Excalidraw JSON schema reference and professional icon libraries for AI agents to autonomously create diagrams without templates.
error-handling
Python error handling patterns for FastAPI, Pydantic, and asyncio. Follows "Let it crash" philosophy - raise exceptions, catch at boundaries. Covers HTTPException, global exception handlers, validation errors, background task failures. Use when: (1) Designing API error responses, (2) Handling RequestValidationError…
linting
Python linting with Ruff - an extremely fast linter written in Rust. Use when: (1) Standardizing code quality, (2) Fixing style warnings, (3) Enforcing rules in CI, (4) Replacing flake8/isort/pyupgrade/autoflake, (5) Configuring lint rules and suppressions.
logfire
Structured observability with Pydantic Logfire and OpenTelemetry. Use when: (1) Adding traces/logs to Python APIs, (2) Instrumenting FastAPI, HTTPX, SQLAlchemy, or LLMs, (3) Setting up service metadata, (4) Configuring sampling or scrubbing sensitive data, (5) Testing observability code.
commit-message
Analyze git changes and generate conventional commit messages. Supports batch commits for multiple unrelated changes. Use when: (1) Creating git commits, (2) Reviewing staged changes, (3) Splitting large changesets into logical commits.
python-backend
Python backend development expertise for FastAPI, security patterns, database operations, Upstash integrations, and code quality. Use when: (1) Building REST APIs with FastAPI, (2) Implementing JWT/OAuth2 authentication, (3) Setting up SQLAlchemy/async databases, (4) Integrating Redis/Upstash caching, (5) Refactoring…