What makes Dazzle Photo Intelligence notable?

1.2K downloads. Trust evidence available

How should Dazzle Photo Intelligence be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Dazzle Photo Intelligence

Connects OpenClaw to Dazzle, an AI agent that deeply understands the user through their photos. Through a companion iOS app, Dazzle accesses their photos and... Skill: Dazzle Photo Intelligence Owner: dazzle Summary: Connects OpenClaw to Dazzle, an AI agent that deeply understands the user through their photos. Through a companion iOS app, Dazzle accesses their photos and... Tags: latest:0.1.9 Version history: v0.1.9 | 2026-05-21T01:06:47.494Z | user Clarify usage guidance v0.1.8 | 2026-05-20T23:04:40.284Z | user Clarify usage guidance v0.1.7 | 2026-05-20T22:45:47.544Z | use

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 11, 2026

Version

0.1.9

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 11, 2026
Latest release: 0.1.9release · observed May 21, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: medium.

clawhub skill install s17e3jhtejw51927f93bqcfd5986jqqq:dazzle-photo-intelligence

Python environment detected. Create a strict virtual environment (`python -m venv .venv`) before installing dependencies to prevent system-level package conflicts.
Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-dazzle-dazzle-photo-intelligence/snapshot"

Documentation

CLAWHUB

85,994 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: dazzle-photo-intelligence
description: Connects OpenClaw to Dazzle, an AI agent that deeply understands the user through their photos. Through a companion iOS app, Dazzle accesses their photos and can understand who they are, where they live, their preferences, people in their lives, places they've been, and other personal choices. Auth is handled transparently by the bridge.
metadata: {"openclaw": {"requires": {"bins": ["uv"]}}}
---

# Dazzle Photo Intelligence

Connects OpenClaw to Dazzle, an AI agent that deeply understands the user through their
photos. Through a companion iOS app, Dazzle accesses their photos and can understand who
they are, where they live, their preferences, people in their lives, places they've been,
and other personal choices. Consult Dazzle for any query where personalization would
meaningfully improve the answer.

## When to use this skill

Consult Dazzle whenever knowing the user — their likes, places they've been, what piques
their attention — would improve the answer. Concrete categories:

- **Photos & memories** — "find food photos from today", "show sunsets from last weekend",
  "send pictures from the user's last family vacation?"
- **Places** — "where does the user live", "what restaurants does the user enjoy", "where
  has the user been"
- **Recommendations** — "where should the user go for his/her next vacation?", "suggest a
  restaurant for tonight given what he/she usually likes"
- **Personal facts and summaries** — "What is the user's daughter's name?", "what did the
  user do last weekend?", "summarize events and activities from my year so far"
- **Context-aware decisions** — "what gift would the user's father like?", "if the user is
  in Denver, where should they go for a nicer meal?"
- **Context** — "what types of things does the user do when visiting NYC?", "what seems to
  be the user's favorite color?", "what brands of clothes does the user buy?", "what sports
  teams does the user cheer for?", "which celebrities does the user admire", "what types of
  things has the user been thinking about purchasing recently", "what sports does the user
  participate in or watch?"

Always invoke Dazzle when the user mentions it by name ("ask Dazzle to…", "what does Dazzle
know about…").

Do **not** invoke Dazzle for fully impersonal queries ("what's the capital of France",
"explain quicksort") — there's no personalization to add.

## Data access

This skill consults Dazzle on behalf of the signed-in user about *their own data* —
photos and context that user has previously shared with Dazzle. It does not access
anyone else's data.

**Why OAuth2 sign-in:** OAuth2 was chosen over static API keys specifically to avoid
long-lived secrets on disk. Tokens are short-lived, individually revocable per session,
scoped to the user's own account, and never handled or committed by the user.

Sign-in is browser-based on first use. After that, the bridge keeps the user signed
in across sessions — like a logged-in browser

README.md

# OpenClaw Bridge

Stdio MCP server that authenticates with [Dazzle](https://dazzle.ai) over OAuth2 and
forwards calls from your local agent to Dazzle's hosted MCP endpoint.

## Signing in

The first time your agent queries Dazzle you'll receive a sign-in URL and a short code.
Open the URL, enter the code, approve. Your tokens are kept in your OS keyring;
subsequent sessions are silent.

## License

[MIT](LICENSE)

_meta.json

{
  "ownerId": "kn7fp4hetweckhrknegq2yzba986ktj0",
  "slug": "dazzle-photo-intelligence",
  "version": "0.1.9",
  "publishedAt": 1779325607494
}

skill-card.md

## Description:

Connects OpenClaw to Dazzle, an AI agent that deeply understands the user through their photos.

This skill is ready for commercial/non-commercial use.

## Publisher:

[dazzle](https://clawhub.ai/user/dazzle)

### License/Terms of Use:

MIT

## Use Case:

External users and agent operators use this skill to let an MCP-capable agent query Dazzle for photo-derived personal context, memories, places, preferences, and recommendations after the user signs in.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Dazzle receives sensitive personalization queries and can use photo-derived account context after a one-time sign-in.

Mitigation: Use the skill only when photo-derived personalization is intended, prefer explicit prompts such as 'ask Dazzle' for sensitive topics, and revoke Dazzle account access when it is no longer needed.

Risk: Matched photos are returned as URLs that an agent may fetch for viewing, analysis, or inclusion in responses.

Mitigation: Fetch returned photo URLs only when the user request requires the image content, and treat those URLs as sensitive personal data.

Risk: Subsequent sessions can be silent after the first browser-based sign-in.

Mitigation: Review the registered MCP server configuration and remove the Dazzle bridge or sign out of Dazzle when silent access is no longer appropriate.

## Reference(s):

- [ClawHub skill listing](https://clawhub.ai/dazzle/skills/dazzle-photo-intelligence)
- [Dazzle](https://dazzle.ai)

## Skill Output:

**Output Type(s):** [text, json, shell commands, configuration, guidance]

**Output Format:** [MCP text responses, JSON photo URL blocks, and Markdown setup guidance with inline shell commands]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May require a browser-based OAuth sign-in; queries can take up to 60 seconds.]

## Skill Version(s):

0.1.9 (source: pyproject.toml and server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

pyproject.toml

[project]
name = "dazzle-photo-intelligence"
version = "0.1.9"
description = "OAuth device-flow CLI and stdio MCP server that lets agents query Dazzle's remote photo intelligence MCP endpoint"
license = { file = "LICENSE" }
requires-python = ">=3.12"
dependencies = [
    "mcp>=1.27",
    "httpx>=0.28",
    "keyring>=25.7",
    "keyrings.alt>=5",
]

[project.optional-dependencies]
dev = [
    "pytest>=9.0",
    "pytest-asyncio>=1.3",
    "ruff>=0.15",
]

[project.scripts]
dazzle = "dazzle_photo_intelligence.cli:main"

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.hatch.build.targets.wheel]
packages = ["dazzle_photo_intelligence"]

[tool.ruff]
line-length = 120
target-version = "py312"

[tool.pytest.ini_options]
asyncio_mode = "auto"

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.