#494 by GitHub stars

asuojun/claude-vision-skill

Use when the user shares, pastes, or references an image (local path or URL) and you need to describe, analyze, or recognize its content, especially when the current model cannot read images directly. Run the bundled vision.js helper to convert the image into text.

Claude Code Codex Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

178038711c87 → 178038711c87

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 178038711c87

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 178038711c87f4b02c313e270210605379cda8cf

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/asuojun/claude-vision-skill.git .hotskills/asuojun-claude-vision-skill && git -C .hotskills/asuojun-claude-vision-skill checkout --detach 178038711c87f4b02c313e270210605379cda8cf
# Copy each selected skill directory from .hotskills/asuojun-claude-vision-skill into .claude/skills/<skill-name>/

Version-pinned installation · Codex

git clone --filter=blob:none --no-checkout https://github.com/asuojun/claude-vision-skill.git .hotskills/asuojun-claude-vision-skill && git -C .hotskills/asuojun-claude-vision-skill checkout --detach 178038711c87f4b02c313e270210605379cda8cf
# Copy each selected skill directory from .hotskills/asuojun-claude-vision-skill into .agents/skills/<skill-name>/

2.3kGitHub stars

-4stars in 7 days

1skill in this repository

2commits in 30 days

Heat

2.7

Star growth, last 7 daysAhead of 2% of tracked repositories
Star growth, last 24 hoursAhead of 70% of tracked repositories
Rank movement, last 7 daysAhead of 30% of tracked repositories
Commits, last 30 daysAhead of 60% of tracked repositories
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

claude-vision-skill /

How it works

claude-vision-skill

When your agent uses it

Use when the user shares, pastes, or references an image (local path or URL) and you need to describe, analyze, or recognize its content, especially when the current model cannot read images directly. Run the bundled vision.js helper to convert the image into text.

What it loads into context

Frontmatter

66 tokens

Always available to the agent

SKILL.md

660 tokens

When the skill is activated

Reference documents

2,018 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Scripts executed separately

clipboard.ps1
test/vision.test.js
vision.js
vision.py

Files

.gitignoreasset19 bytes
AGENTS.mddoc1,067 bytes
CLAUDE.mddoc1,293 bytes
README.mddoc3,380 bytes
SKILL.mdcore2,855 bytes
SKILL.mdcore2,855 bytes
SKILL.mdcore2,855 bytes
SKILL.mdcore2,855 bytes
SKILL.mdcore2,855 bytes
clipboard.ps1runs369 bytes
clipboard.swiftasset785 bytes
cyberboss-setup.mddoc1,722 bytes
test/vision.test.jsruns1,062 bytes
vision.jsruns6,926 bytes
vision.pyruns3,964 bytes

No excerpt is shown for this license. Read the source on GitHub.

View the complete source on GitHub

Skills included

claude-vision-skill

Repository facts

License: No license detected
Created: May 2, 2026
Last pushed: Oct 22, 2026
Forks: 122
Open issues: 3
Project activity: Active

Rank over the last 12 weeks

Now #494 · best #369 · down 65 in 30 days

#487 on Nov 2
#490 on Nov 3
#493 on Nov 4
#492 on Nov 5
#495 on Nov 6
#494 since Nov 7

66 earlier periods

#674 on Aug 2
#437 on Aug 7
#428 on Aug 8
#413 on Aug 9
#414 on Aug 10
#406 on Aug 11
#393 on Aug 12
#385 on Aug 13
#379 on Aug 14
#375 on Aug 15
#378 on Aug 16
#373 on Aug 17
#380 on Aug 18
#377 on Aug 19
#375 on Aug 20
#373 on Aug 21
#371 on Aug 22
#375 on Aug 23
#377 from Aug 24 to Aug 25
#378 on Aug 26
#381 on Aug 27
#382 on Aug 28
#375 on Aug 29
#369 on Aug 30
#380 on Aug 31
#388 on Sep 1
#382 on Sep 2
#386 on Sep 3
#377 on Sep 4
#381 on Sep 5
#377 on Sep 6
#387 on Sep 7
#388 on Sep 8
#387 on Sep 9
#389 on Sep 10
#386 on Sep 11
#390 from Sep 12 to Sep 13
#395 on Sep 14
#397 on Sep 15
#401 on Sep 16
#395 on Sep 17
#399 on Sep 18
#390 on Sep 19
#399 on Sep 20
#395 on Sep 21
#403 on Sep 22
#395 on Sep 23
#393 on Sep 25
#387 on Sep 26
#399 on Sep 27
#404 on Sep 28
#415 on Sep 30
#422 on Oct 7
#429 on Oct 8
#435 on Oct 9
#424 on Oct 11
#433 on Oct 13
#434 on Oct 14
#436 on Oct 15
#433 on Oct 17
#448 on Oct 19
#471 on Oct 25
#479 on Oct 28
#482 on Oct 29
#484 from Oct 30 to Oct 31
#485 on Nov 1

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 3, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 4 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
16 network referencesin 3 files: vision.py:11 vision.js:34 README.md:63
No hidden or obfuscated text
No instruction overrides
4 executable scriptsin 4 files: clipboard.ps1:1 test/vision.test.js:1 vision.js:1 and 1 more
25 references to secretsin 6 files: vision.py:10 vision.js:10 test/vision.test.js:13 and 3 more
No requests to vote in Hot

Show all 45 signals by file

`.gitignore`

Access to secretsline 2
```
[Credential-related source omitted]
```

`AGENTS.md`

Access to secretsline 20
```
[Credential-related source omitted]
```

`README.md`

Network accessline 63

git clone https://github.com/asuojun/claude-vision-skill.git

Network accessline 72

> 按 https://github.com/asuojun/claude-vision-skill 的 README 帮我配置识图

`SKILL.md`

Access to secretsline 64
```
[Credential-related source omitted]
```

`clipboard.ps1`

Executable scriptline 1
```
Executable file
```

`test/vision.test.js`

Executable scriptline 1
```
Executable file
```
Access to secretsline 13
```
[Credential-related source omitted]
```
Access to secretsline 19
```
[Credential-related source omitted]
```
Access to secretsline 28
```
[Credential-related source omitted]
```

`vision.js`

Executable scriptline 1
```
#!/usr/bin/env node
```
Access to secretsline 10
```
[Credential-related source omitted]
```
Access to secretsline 11
```
[Credential-related source omitted]
```
Access to secretsline 32
```
[Credential-related source omitted]
```

Network accessline 34

const BASE_URL = process.env.DASHSCOPE_BASE_URL || "https://dashscope.aliyuncs.com/compatible-mode/v1";

Access to secretsline 35
```
[Credential-related source omitted]
```
Access to secretsline 127
```
[Credential-related source omitted]
```
Access to secretsline 149
```
[Credential-related source omitted]
```

Network accessline 151

if (missing.length) {     console.error(`请设置以下配置：${missing.join(", ")}（环境变量或 .env 文件）`);     console.error("获取 Key: https://bailian.console.aliyun.com/");

Network accessline 152
```
[Credential-related source omitted]
```
Access to secretsline 152
```
[Credential-related source omitted]
```

Network accessline 153

console.error("获取 Key: https://bailian.console.aliyun.com/");

`vision.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 10
```
[Credential-related source omitted]
```
Network accessline 11
```
[Credential-related source omitted]
```
Access to secretsline 11
```
[Credential-related source omitted]
```

Network accessline 12

VISION_MODEL         视觉模型名，如 GLM-4.6V-FlashX / qwen-vl-max / gpt-4o-mini     DASHSCOPE_BASE_URL   API 地址，如 https://open.bigmodel.cn/api/paas/v4/ """

Network accessline 13

DASHSCOPE_BASE_URL   API 地址，如 https://open.bigmodel.cn/api/paas/v4/

Access to secretsline 30
```
[Credential-related source omitted]
```
Access to secretsline 31
```
[Credential-related source omitted]
```
Access to secretsline 35
```
[Credential-related source omitted]
```
Access to secretsline 36
```
[Credential-related source omitted]
```
Network accessline 39
```
[Credential-related source omitted]
```
Access to secretsline 39
```
[Credential-related source omitted]
```
Access to secretsline 40
```
[Credential-related source omitted]
```
Access to secretsline 41
```
[Credential-related source omitted]
```

Network accessline 58

url = BASE_URL.rstrip("/") + "/chat/completions"     # 拼出完整接口     body = json.dumps(payload).encode("utf-8")     req = urllib.request.Request(url, data=body, headers={

Network accessline 59
```
[Credential-related source omitted]
```

Network accessline 60

req = urllib.request.Request(url, data=body, headers={

Access to secretsline 61
```
[Credential-related source omitted]
```

Network accessline 62

"Content-Type": "application/json",     })     with urllib.request.urlopen(req, timeout=60) as resp:

Network accessline 63

})     with urllib.request.urlopen(req, timeout=60) as resp:         data = json.loads(resp.read().decode("utf-8"))

Network accessline 64

with urllib.request.urlopen(req, timeout=60) as resp:

Access to secretsline 82
```
[Credential-related source omitted]
```
Access to secretsline 83
```
[Credential-related source omitted]
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Declared and executed: 3 facts

Contacts dashscope.aliyuncs.com, which SKILL.md, the README and the plugin manifest do not mentionvision.js:34High confidence
Contacts bailian.console.aliyun.com, which SKILL.md, the README and the plugin manifest do not mentionvision.js:153High confidence
Contacts open.bigmodel.cn, which SKILL.md, the README and the plugin manifest do not mentionvision.py:39High confidence

Signal confidence: 44 facts

Access to secrets in prose of documentationAGENTS.md:20Low confidence
Network access in code of documentationREADME.md:63Low confidence
Network access in prose of documentationREADME.md:72Low confidence
Access to secrets in prose of the SKILL.mdSKILL.md:64Low confidence
Executable script in code of a file that runsclipboard.ps1:1High confidence
Executable script in code of a testtest/vision.test.js:1Low confidence
Access to secrets in code of a testtest/vision.test.js:13Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valuetest/vision.test.js:19Low confidence
Access to secrets in code of a testtest/vision.test.js:28Low confidence
Executable script in code of a file that runsvision.js:1High confidence
Access to secrets in a comment of a file that runsvision.js:10Low confidence
Access to secrets in a comment of a file that runsvision.js:11Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.js:32Low confidence
Network access in code of a file that runsvision.js:34High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.js:35Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.js:127Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.js:149Low confidence
Network access in code of a file that runsvision.js:151High confidence
Network access in code of a file that runsvision.js:152High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.js:152Low confidence
Network access in code of a file that runsvision.js:153High confidence
Executable script in code of a file that runsvision.py:1High confidence
Access to secrets in prose of a file that runsvision.py:10Low confidence
Network access in prose of a file that runsvision.py:11Low confidence
Access to secrets in prose of a file that runsvision.py:11Low confidence
Network access in prose of a file that runsvision.py:12Low confidence
Network access in prose of a file that runsvision.py:13Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.py:30Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.py:31Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.py:35Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.py:36Low confidence
Network access in code of a file that runsvision.py:39High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.py:39Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.py:40Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.py:41Low confidence
Network access in code of a file that runsvision.py:58High confidence
Network access in code of a file that runsvision.py:59High confidence
Network access in code of a file that runsvision.py:60High confidence
Access to secrets in code of a file that runsvision.py:61High confidence
Network access in code of a file that runsvision.py:62High confidence
Network access in code of a file that runsvision.py:63High confidence
Network access in code of a file that runsvision.py:64High confidence
Access to secrets in code of a file that runsvision.py:82High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuevision.py:83Low confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Path CLAUDE.md	`.claude/skills/<skill-name>/`
Codex	Native	Manifest AGENTS.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

[![asuojun/claude-vision-skill on hotskills](https://hotskills.dev/badge/asuojun-claude-vision-skill.svg)](https://hotskills.dev/skill/asuojun-claude-vision-skill/)

asuojun/claude-vision-skill

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

claude-vision-skill

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Rank over the last 12 weeks

Before you install

.gitignore

AGENTS.md

README.md

SKILL.md

clipboard.ps1

test/vision.test.js

vision.js

vision.py

How the signals fit together

Works with

You might also use

mattpocock/skills

obra/superpowers

NousResearch/hermes-agent

multica-ai/andrej-karpathy-skills

anthropics/skills

DietrichGebert/ponytail

Explore alternatives and comparisons

Add this badge to your README

`SKILL.md`

`.gitignore`

`AGENTS.md`

`README.md`

`SKILL.md`

`clipboard.ps1`

`test/vision.test.js`

`vision.js`

`vision.py`