Writing DocsSAFE
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.
Overview
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.
5ff3ca429e5bOBSERVED · 2026-10-08What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: writing-docs
description: Guides for writing and editing Remotion documentation. Use when adding docs pages, editing MDX files in packages/docs, or writing documentation content.
---
# Writing Remotion Documentation
Documentation lives in `packages/docs/docs` as `.mdx` files.
## Adding a new page
1. Create a new `.mdx` file in `packages/docs/docs`
2. Add the document to `packages/docs/sidebars.ts`
3. Write the content following guidelines below
4. Run `bun render-cards.ts` in `packages/docs` to generate social preview cards
**One API per page**: Each function or API should have its own dedicated documentation page. Do not combine multiple APIs (e.g., `getEncodableVideoCodecs()` and `getEncodableAudioCodecs()`) on a single page. This is the established pattern throughout the codebase.
**Public API only**: Documentation is for public APIs only. Do not mention, reference, or compare against internal/private APIs or implementation details. Users should only see what is exported and intended for public use.
**Use headings for all fields**: When documenting API options or return values, each property should be its own heading. Use `###` for top-level properties and `####` for nested properties within an options object. Do not use bullet points for individual fields.
## Language guidelines
- **Keep it brief**: Developers don't like to read. Extra words cause information loss.
- **Link to terminology**: Use [terminology](/docs/terminology) page for Remotion-specific terms.
- **Avoid emotions**: Remove filler like "Great! Let's move on..." - it adds no information.
- **Separate into paragraphs**: Break up long sections.
- **Address as "you"**: Not "we".
- **Don't blame the user**: Say "The input is invalid" not "You provided wrong input".
- **Don't assume it's easy**: Avoid "simply" and "just" - beginners may struggle.
## Code snippets
Basic syntax highlighting:
````md
```ts
const x = 1;
```
````
### Type-safe snippets (preferred)
Use `twoslash` to check snippets against TypeScript:
````md
```ts twoslash
import {useCurrentFrame} from 'remotion';
const frame = useCurrentFrame();
```
````
### Hiding imports
Use `// ---cut---` to hide setup code - only content below is displayed:
````md
```ts twoslash
import {useCurrentFrame} from 'remotion';
// ---cut---
const frame = useCurrentFrame();
```
````
### Adding titles
````md
```ts twoslash title="MyComponent.tsx"
console.log('Hello');
```
````
## Special components
### Steps
```md
- <Step>1</Step> First step
- <Step>2</Step> Second step
```
### Experimental badge
```md
<ExperimentalBadge>
<p>This feature is experimental.</p>
</ExperimentalBadge>
```
### Interactive demos
```md
<Demo type="rect"/>
```
Demos must be implemented in `packages/docs/components/demos/index.tsx`.
## Generating preview cards
After adding or editing a page, generate social media preview cards:
```bash
cd packages/docs && bun render-cards.ts
```
## Verifying docs compile
To check that documentation builds without errors:
```bash
# from the monorepo root
bun run build-docs
```
This validates MDX syntax, twoslash snippets, and broken links.Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
5ff3ca429e5bfull audit observations/trust-audit/skill/foryourhealth111-pixel__writing-docs.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 5ff3ca429e5b | SAFE | B | 89 | first audit |
Questions
What does the Writing Docs skill do?
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.
Is Writing Docs safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Writing Docs access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (5ff3ca429e5b), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.