Pannelai Web Search
Web search through pannelAI. Covers POST /api/v1/search, how the provider is named, the query and max_results fields, and the normalized results envelope with its cost and timing. Use when a client needs live web results from the gateway.
Install
npx skills add rusmanadodi2598/pannelAI --skill pannelai-web-searchgit clone --depth 1 https://github.com/rusmanadodi2598/pannelAI.git /tmp/pannelAI
mkdir -p ~/.claude/skills
cp -r /tmp/pannelAI/skills/pannelai-web-search ~/.claude/skills/pannelai-web-searchPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# pannelAI: Web Search
One route: `POST /api/v1/search`, gateway-key auth.
```bash
curl -s $PANNELAI_URL/api/v1/search \
-H "Authorization: Bearer $PANNELAI_KEY" \
-H "content-type: application/json" \
-d '{"provider": "brave-search", "query": "golang generics", "max_results": 5}'
```
## Naming the provider
Search is the one media kind that does not need a model: its providers read a query and a result count,
so there is no `provider/model` string to resolve. Name the provider one of two ways:
- `provider` names it directly, which is the shorter path.
- `model` names it through its first segment, `provider/anything`.
Neither field present answers `VALIDATION_ERROR` with "provider (or model) is required". A provider that
is not in the registry answers `MODEL_NOT_FOUND` (404), and one that declares no search support answers
`PROVIDER_NOT_ROUTABLE` (400).
## Fields
| Field | Required | Notes |
|---|---|---|
| `query` | yes | 1 to 400 characters. |
| `provider` | no | The registry id of a search-capable provider. |
| `model` | no | Alternative to `provider`; its first segment names the provider. |
| `max_results` | no | A positive whole number. |
| `search_type`, `country`, `language` | no | Forwarded to providers that declare them. |
## The answerDetails
- Skill name
pannelai-web-search- Repository
- rusmanadodi2598/pannelAI
- Path
skills/pannelai-web-search/SKILL.md- License
- MIT
- Repo updated
- 24 October 2026
FAQ
What does the Pannelai Web Search skill do?
Web search through pannelAI. Covers POST /api/v1/search, how the provider is named, the query and max_results fields, and the normalized results envelope with its cost and timing. Use when a client needs live web results from the gateway.
How do I install the Pannelai Web Search skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add rusmanadodi2598/pannelAI --skill pannelai-web-search. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Pannelai Web Search popular?
It lives in rusmanadodi2598/pannelAI, which has 49 GitHub stars and 6 forks.
Related skills
Pannelai
49rusmanadodi2598/pannelAI
Entry point for pannelAI, a self-hosted AI gateway that speaks OpenAI, Anthropic, and OpenAI Responses wire formats for chat, image generation, text-to-speech, speech-to-text, embeddings, and web search. Use when the user mentions pannelAI, a gateway base URL, or wants one key in front of several providers. Covers setup, gateway-key auth, model discovery, and links to one skill per capability.
Pannelai Chat
49rusmanadodi2598/pannelAI
Chat and code generation through pannelAI, in the OpenAI chat completions, Anthropic messages, or OpenAI Responses wire format, streamed or not. Covers the model field, streaming, combo routing, and the vision adapter. Use when a client needs an LLM answer from the gateway.
Pannelai Embeddings
49rusmanadodi2598/pannelAI
Embeddings through pannelAI. Covers POST /api/v1/embeddings, the provider/model string, the input field, and the OpenAI embeddings answer with its usage block. Use when a client needs vectors for RAG or semantic search from the gateway.
App Store Submission Auditor
33itsncki-design/app-store-submission-auditor
Scans an iOS app project for App Store rejection risks. Reads source code directly — no back-and-forth. Auto-detects vibe coder vs developer and adapts language. Detects mid-build apps and asks before switching modes. Outputs a risk register, detailed findings with dynamic copy-paste fixes, reviewer experience checklist, draft App Store Connect reviewer notes, and a post-scan manual checklist. TRIGGER THIS SKILL for any of these — even if not explicitly asked: "audit my app" / "is my app ready" / "about to submit" / "submitting soon" / "about to launch" / "ready to ship" / "App Store review" /
Game Vibe Code
57AlterLab-IEU/AlterLab_GameForge
Runs an AI-agent build loop from idea to a playable, verified, shippable game: one-page spec, playable in the first hour, one feature per iteration with a pass/fail check, Playwright screenshots, commits and a progress.md handoff. Use for "vibe code a game", "build a game with Claude", "make a browser game fast". Not for throwaway mechanic tests (use game-prototype).
Codex Code Review
45tyrchen/claude-skills
Perform comprehensive code reviews using OpenAI Codex CLI. This skill should be used when users request code reviews, want to analyze diffs/PRs, need security audits, performance analysis, or want automated code quality feedback. Supports reviewing staged changes, specific files, entire directories, or git diffs.
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.