Skip to content
Back to search

selkay-skill

Official Selkay Content Moderation Agent Skill for AI coding agents (Claude Code, Cursor, Codex, OpenCode, Antigravity)

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/selkay-dev--selkay-skill/badge.svg)](/listings/selkay-dev--selkay-skill)

HTML

<a href="/listings/selkay-dev--selkay-skill"><img src="/api/listings/selkay-dev--selkay-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Install this skill directly into your AI coding agent (Claude Code, Cursor, Codex, OpenCode, Antigravity, etc.) using the official skills CLI:

npx skills add Selkay-dev/selkay-skill

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 51 lines
  1. # Selkay Moderation Skill (`selkay-moderation`)
  2. A complete, production-ready, agentic-friendly skill for integrating **Selkay**'s server-side text and image moderation API (`POST https://api.selkay.com/v1/moderate`).
  3. ---
  4. ## Installation via Vercel Labs / `skills.sh`
  5. Install this skill directly into your AI coding agent (Claude Code, Cursor, Codex, OpenCode, Antigravity, etc.) using the official skills CLI:
  6. ```bash
  7. npx skills add Selkay-dev/selkay-skill
  8. ```
  9. ---
  10. ## Skill Architecture & Structure
  11. This package follows the portable [Agent Skills specification](https://agentskills.io/specification):
  12. ```text
  13. selkay-skill/
  14. ├── README.md # Repository overview & setup instructions
  15. └── skills/
  16. └── selkay-moderation/
  17. ├── SKILL.md # Main agent instructions & workflow
  18. └── references/
  19. ├── api-contract.md # Full HTTP API schema, limits, headers & errors
  20. ├── production-handling.md # Reliability, fail-closed handling, retries & security
  21. └── code-examples.md # Battle-tested TypeScript & Python client implementations
  22. ```
  23. ---
  24. ## What This Skill Delivers
  25. 1. **Precision API Contract**: Exact schema definitions, byte limits (1 MiB text, 3 MiB decoded image, 5 MiB payload), 8,192px/16MP dimension bounds, request unit billing math, and response headers (`X-Request-Id`, `X-Edge-Latency`, `Server-Timing`).
  26. 2. **Fail-Closed Reliability**: Proper enforcement of Selkay's fail-closed architecture — preventing edge service errors (HTTP 200 with non-null `error`) from being misclassified as user policy violations.
  27. 3. **Safe Redaction Guardrails**: Strict type verification (`typeof cleaned_text === "string"`), 10,000-code-unit truncation handling, and zero-leakage replacement patterns.
  28. 4. **Resilient Production Clients**: Ready-to-use reference implementations in TypeScript and Python featuring exponential backoff with full jitter, `Retry-After` parsing on HTTP 429 minute rate limits, and fail-fast behavior on quota exhaustion.
  29. 5. **Zero-Leakage Secret Hygiene**: Guidance on server-to-server isolation, blocking browser calls (`Origin` / `Sec-Fetch-Mode`), and managing `SELKAY_API_KEY` securely.
  30. ---
  31. ## Using This Skill with AI Agents
  32. To use this skill manually:
  33. 1. Keep the `skills/selkay-moderation/` directory intact.
  34. 2. Link or copy `skills/selkay-moderation/` into your agent's skill directory (e.g. `~/.gemini/antigravity/skills/selkay-moderation` or `.agents/skills/selkay-moderation`).
  35. 3. Agents will automatically discover `selkay-moderation` whenever you ask to integrate, configure, review, or debug server-side moderation calls to Selkay.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.