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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gooseworks-ai/goose-skillsnpx agentmods add skills/gooseworks-ai/goose-skills/render-street-interviewWrote 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/render-street-interview)<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/render-street-interview"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/render-street-interview/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/render-street-interview"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/render-street-interview.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 | $0.00065 | $0.03720 |
| Opus 5.5 | $0.00026 | $0.01488 |
| Sonnet 5.5 | $0.00013 | $0.00744 |
| Haiku 4.5 | $0.00006 | $0.00372 |
Grade A, and why
render-street-interview 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 yesterday.
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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human version
render-street-interview
Summary. This is the renderer for the street-interview ad format (goose-studio
recipe one-shot-videos/create-street-interview-video). Product guessing retains its
visible object and reveal. Conversation supports mic-only, prepared-sample and visible-task
script/prompt previews. Choose a coherent situation and earned ad connection before
writing words. People are generated; conversation media delivery remains unverified.
Agent version
Script first: choose the execution
Read street-script-writing before adapting a brand. The recipe fixes camera, audio, native timing and finishing rules. Its story choices govern premise, participant role, participation reason, visible task, actions, edited opening, hook, supported brand explanation and payoff. Do not force a correct-answer winner into a service conversation or reduce every brand to a routine problem followed by a logo card.
| Interaction | Current support | Person image reference | Max participants |
|---|---|---|---|
product-guess |
Existing object renderer; standalone product reference required | forbidden | 4 |
mic-only |
Conversation preview; service explanation without a product or device | forbidden | 1 |
product-sample |
Conversation preview; prepared sample in a plain cup, no exact package reference | forbidden | 1 |
concept-challenge |
Conversation preview; described visible task using non-UI props | forbidden | 1 |
Use [[composes::write-video-ad-script]] with the scoped angle bank, current facts and
selected complete commercial street interactions. scripts/prepare_script_context.py
requires a brief with offering_type=physical|service|digital and
interaction_type=product-guess|mic-only|product-sample|concept-challenge. Inspect the full
visual timeline and spoken exchange: setup, participation reason, hook, product role and
payoff. Record unseen recruitment or setup as unknown; inference is not observation.
Seed snippets are leads. Radio and editorial exchanges cannot fill a street-ad gap.
Keep private observations project-scoped and transfer mechanics, not source-brand claims.
What ships with it
60 files 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.
- brands/demo-tallgrass-oat.json 3.9 KB
- brands/graza-ep1-a2.json 2.5 KB
- brands/graza-ep1-b.json 2.7 KB
- brands/graza-ep1-c.json 2.5 KB
- brands/liquid-death-4816.json 4.6 KB
- brands/liquid-death-4817.json 2.3 KB
- brands/liquid-death-4818.json 2.6 KB
- brands/liquid-death-4819.json 2.1 KB
- brands/liquid-death-4820.json 2.8 KB
- brands/liquid-death-4821.json 2.8 KB
- brands/liquid-death-4822.json 2.5 KB
- brands/liquid-death-4823.json 2.4 KB
- brands/liquid-death-4824.json 4.2 KB
- brands/liquid-death-4827.json 4.7 KB
- brands/liquid-death-4828.json 4.3 KB
- brands/liquid-death-4829.json 3.9 KB
- brands/liquid-death-4830.json 3.9 KB
- brands/liquid-death-4831.json 4.2 KB
- brands/liquid-death-4832.json 3.6 KB
- brands/liquid-death-4833.json 3.8 KB
- brands/liquid-death-4834.json 3.9 KB
- brands/liquid-death-4835.json 3.9 KB
- brands/liquid-death.json 4.7 KB
- brands/olipop-ep3-a.json 2.2 KB
- brands/olipop-ep3-b.json 2.6 KB
- brands/olipop-ep3-c.json 2.3 KB
- episodes/graza-ep1.json 775 B
- episodes/liquid-death-ep1.json 2.2 KB
- episodes/liquid-death-ep2.json 2.2 KB
- episodes/liquid-death-ep2fix-v2.json 4.9 KB
- episodes/liquid-death-ep2fix-v3.json 5.7 KB
- episodes/liquid-death-ep2fix.json 3.7 KB
- episodes/liquid-death-ep3.json 2.5 KB
- episodes/liquid-death-ep3b.json 2.3 KB
- episodes/liquid-death-ep3c.json 2.3 KB
- episodes/liquid-death-ep4.json 3.7 KB
- episodes/olipop-ep3.json 985 B
- READINESS.md 13 KB
- REFERENCE.md 62 KB
- references/cast-writing.md 9.6 KB
- references/h3-generation.md 2.2 KB
- references/model-behaviors.md 5.0 KB
- references/street-reference-library.json 6.8 KB
- references/street-script-writing.md 17 KB
- scripts/bench.py 18 KB runs code
- scripts/brandkit.py 19 KB runs code
- scripts/build_episode.py 77 KB runs code
- scripts/build_looks.py 32 KB runs code
- scripts/build.py 8.0 KB runs code
- scripts/check-cut.py 66 KB runs code
- scripts/conversation.py 13 KB runs code
- scripts/edit_timeline.py 7.6 KB runs code
- scripts/falsify-all.py 20 KB runs code
- scripts/fit_grade.py 7.8 KB runs code
- scripts/format_spec.py 93 KB runs code
- scripts/measure-pace.py 2.8 KB runs code
- scripts/media_proxy.py 56 KB runs code
- scripts/paths.py 3.0 KB runs code
- scripts/phone_look_video.py 7.2 KB runs code
- scripts/prepare_script_context.py 12 KB runs code
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.
- yesterday Changed a0e036308350
- 5d ago Changed · +4 lines 8e2ecb39e32b
- 9d ago Changed 730779be2f1e
- 11d ago Changed · +33 lines c75ec8a14c6c
- 12d ago Changed a15396604440
- 13d ago Changed · +93 lines · -31 tokens per session 7349d408f987
- 14d ago Changed · +36 lines 393ac91816a9
- 15d ago First seen · 76 lines · 96 tokens per session scan A 7158e19a8f0d
render-street-interview is a skill published in the GitHub repository gooseworks-ai/goose-skills (1,254 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 3,720 once invoked, about $0.0003 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 2026-10-03.
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…
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.
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.
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…