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 caption-burngit 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/caption-burn)<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/caption-burn"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/caption-burn/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/caption-burn"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/caption-burn.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 | $0.00159 | $0.01167 |
| Opus 5.5 | $0.00064 | $0.00467 |
| Sonnet 5.5 | $0.00032 | $0.00233 |
| Haiku 4.5 | $0.00016 | $0.00117 |
Grade A, and why
caption-burn 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superseded: the video kit now does this with the captions-layer part, version 1.1.0, in the parts folder of this repository. It burns the same plate captions from the speech timings, holds the last caption to the end, transcribes only when there are no timings, and returns a WebVTT of what it drew. This atom stays, unchanged in behaviour, for skills outside the kit until they move; its scripts still run.
caption-burn
Captions timed to what is actually said in the finished video, not to the script's estimate.
Run
python transcribe.py --media reel.mp4 --out reel.words.json # paid, cents
python captions.py --video reel.mp4 --beats cutlist.aligned.json \
--words reel.words.json --out final.mp4 [--style plate|outline] [--highlight Brand]
--beats supplies the lines (vo), their timing and, for split layouts, seam, size
and each beat's state. Any file with beats: [{start, end, vo}] works.
Placement and style
-
--anchor seam(the default when the beats have a seam): onsplitbeats the plate is pinned to the seam, positioned by the plate, not the text: 25% of the plate above the line, 75% below. Full-frame beats use--full-y. -
--anchor fixed --y 0.62: every caption's plate centred at that fraction of the height. -
plate(default): white bold on a dark grey rounded plate, 1–2 words, cap ~0.019 H. -
outline: white bold with a dark outline, no plate, 1–3 words, cap ~0.034 H. -
--highlight WORDcolours that word yellow (the CTA keyword). Repeatable. -
serif-word: ONE word at a time, heavy serif (Georgia Bold), white with a black outline, on a fixed baseline at 0.77 H (the screen-insert look). The highlight word is quoted. -
--card "LINE ONE|LINE TWO" --card-until 4.7: a white rounded hook card with two lines of heavy red capitals near the top, for the opening seconds. ~14 characters a line.
Captions for a format with no voice (plates.py)
python plates.py --video walk.mp4 --beats cutlist.json --out captioned.mp4 [--logo logo.png]
What ships with it
8 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.
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 Changed · +3 lines d0047d2ac4c3
- 11d ago Changed · +6 lines 6a05fc361d2d
- 19d ago First seen · 63 lines · 159 tokens per session scan A 96dbc02f1585
caption-burn is a skill published in the GitHub repository gooseworks-ai/goose-skills (1,254 stars, last pushed today), licensed MIT. It adds 159 tokens to every session and 1,167 once invoked, about $0.0006 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 2026-09-29.
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…