Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Privacy Publish · rshankras | DecimalAI

devopsby rshankras

Privacy Publish

rshankras/privacy-publish

Source rshankras/claude-code-apple-skills ↗License MIT

Turn drafted legal docs (privacy policy, terms) into hosted pages and set the App Store Connect Privacy Policy / Support / Marketing URLs via the ASC REST API. Use at Phase 6 / submission, after legal drafts exist. The App Privacy "nutrition label" stays manual (Apple exposes no API) — this prints the exact answers to click.

SkillScore73Maintained

Automatic

Legal & Contracts pack

Last verified 8/18/2026

What it changes

Passed 14 of 19 test cases with the skill, and 8 of 19 without it.

Without skill41%

With skill73%

Checks it passed that the model alone missed

Recommends using the hosting provider's dedicated CLI tool
Identifies --apply as the required flag for writing changes
Prompts the user to specify their hosting infrastructure choice

and 4 more in the full report

7 fixed9 passed either way6 still failing0 broke

Pass-rate lift: +32 pp
Tokens: 0%
Agent turns: 0%
Response time: -47%

Model gemini-3.6-flashMeasured 8/18/2026v116 of 22 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/rshankras-privacy-publish/SKILL.md https://app.decimal.ai/s/rshankras-privacy-publish/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add rshankras-privacy-publish, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/rshankras-privacy-publish/ and pins it in .decimal/skills.lock

decimalai skills add rshankras-privacy-publish

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/rshankras-privacy-publish/SKILL.md https://app.decimal.ai/s/rshankras-privacy-publish/SKILL.md

Raw file: /s/rshankras-privacy-publish/SKILL.md ↗ · machine-readable summary at /s/rshankras-privacy-publish.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

In the asc.py CLI tool workflow, which flag is required to execute the actual write request after validating the payload?

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies --apply as the required flag for writing changes	Missed	Passed

case-22 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md42 linessingle file

Privacy Publish

Close the "hosted legal pages + ASC URLs" gap: render .planning/legal/{privacy,terms}.md → host them → PATCH the Privacy/Support URLs onto the App Store version. The one thing with no API — the App Privacy nutrition label — is handed off as a precise checklist.

Depends on the user's web infra, so ask once, remember. Hosting choice is theirs; the ASC URL-setting is the automatable part.

Prerequisites

Legal drafts exist: .planning/legal/privacy.md, .planning/legal/terms.md (from legal/privacy-policy).
_shared/asc-api/ set up (README).
Set ASC="python3 <path to asc.py>" — resolve asc.py relative to this SKILL.md file's location (../../_shared/asc-api/asc.py), never the project cwd. Known install locations:
- SwiftShip symlink install: ~/.claude/swiftship-skills/_shared/asc-api/asc.py
- Copied install: .claude/skills/_shared/asc-api/asc.py (project) or ~/.claude/skills/_shared/asc-api/asc.py (global)
- Plugin install: resolve from this file's location — the _shared/ tree ships with the plugin.
The app has a current editable App Store version + an en-US appInfoLocalization and appStoreVersionLocalization (get their ids first).

Flow — dry-run → confirm → apply

Render. Markdown → minimal self-contained HTML (or keep .md if the host renders it).
Publish (pick per the user's infra — AskUserQuestion once, then remember in .planning/):
- git static site — commit + push to the pages repo/branch.
- WordPress — POST /wp-json/wp/v2/pages with an application password.
- Netlify / S3 / other — the host's CLI.
- Browser fallback — drive the CMS with claude-in-chrome (detect → preview → confirm → act → fall back, per TOOL-HANDOFF.md).
- Confirm both URLs resolve (HTTP 200) before touching ASC.
Set the ASC URLs (REST — dry-run, confirm, then --apply):
- Privacy Policy URL → appInfoLocalizations (privacyPolicyUrl):
```
$ASC PATCH /v1/appInfoLocalizations/<id> '{"data":{"type":"appInfoLocalizations","id":"<id>","attributes":{"privacyPolicyUrl":"https://…/privacy"}}}' --apply
```
- Support / Marketing URL → appStoreVersionLocalizations (supportUrl, marketingUrl) — PATCH the current version's en-US localization id.
Nutrition label (manual — no API). Emit a checklist matching Sources/PrivacyInfo.xcprivacy (e.g. Data Not Collected, no tracking) for the user to click in ASC ▸ App Privacy. Do not claim this step is automated.

Done

Legal pages live + resolving; Privacy/Support URLs set via API; nutrition-label checklist handed off.

Caveats

Verify each endpoint/field against the current ASC API reference before --apply (captured 2026-07).

Track record

Benchmark

14 / 19

test cases passed, vs 8 / 19 without

Adoption

Users: 1
Times used: 15

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

rshankras / claude-code-apple-skills

skills/legal/privacy-publish/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Privacy Publish

Prerequisites

Flow — dry-run → confirm → apply

Done

Caveats

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills