OS Agent Survey
This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral).
Supply asset profile
Coding and developer agents
Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.
Scenario
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Agent fit
Claude Code + Browser agents + CLI
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add OS-Agent-Survey/OS-Agent-Survey
Maintenance
stable
10mo since push
Risk
Needs review
License is unclear
GitHub quality
485
61/100 quality · 74/100 trust
Coverage tags
Review notes
License is unclear · Quality score needs review
Agent adoption scorecard
Trust, audit, and install readiness at a glance
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
PromisingUseful candidate, but compare it with alternatives before adopting.
Trust
Strong shortlistGood trust signals with a few areas worth checking before rollout.
Audit
Needs reviewInstall readiness, security metadata, maintenance, and adoption risk.
Trust Score v3
Human review before install
Test in a sandbox workflow and compare its install path with close alternatives.
Stars
485 GitHub stars
Repo activity
485 stars, 21 forks
Maintenance
10mo since push
License
Unknown
Install
npx skills add OS-Agent-Survey/OS-Agent-Survey
Install safety
standard package or runtime install path
Permission surface
filesystem or document access, network or browser access
Docs
Strong README/SKILL.md context
Risk summary
Review before production
- License is unclear
- Quality score needs review
- Stars/forks activity: 485 stars, 21 forks; issue activity unavailable in current metadata
- License clarity: Unknown
Install readiness
Install path available
- Install path is available
- Repository evidence is available
- License is unclear
- 10mo since push
Agent-readable metadata
Machine-readable decision data for this skill.
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
- Local desktop workflows
- Claude Code teams
- builders willing to evaluate younger projects
- Navigate local resources
- Run repeatable desktop actions
Suited agents
Trust and risk
- Trust score
- 74/100
- Risk level
- Needs review
- Auto install
- review
Do not use when
- teams that need a vendor-supported SLA
- high-compliance environments without internal security review
- No OpenAgentSkill engagement data yet
- License is unclear
- Quality score needs review
Agent safety v2
51/100 · Avoid automatic install
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
medium
Browser automation
Skill may drive a browser or interact with web pages.
medium
Network access
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Filesystem access
Skill may read or write project files, documents, generated artifacts, or local workspace state.
- License is unclear
Install targets
Install this skill in your agent workflow
Copy the registry command or an agent-specific install prompt for Codex, Claude Code, and Cursor.
OpenAgentSkill CLI
Use the registry command when your workflow supports the OpenAgentSkill installer.
$ npx skills add OS-Agent-Survey/OS-Agent-SurveyAgent resolve plan
Let an agent verify fit before installing.
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Resolve JSON
/api/agent/resolve?task=Use%20OS%20Agent%20Survey%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20OS%20Agent%20Survey%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/os-agent-survey-os-agent-survey/install
Agent should check
- Task fit and alternatives from Resolve API.
- Audit score, trust score, and safety policy warnings.
- Install target compatibility for Codex, Claude Code, Cursor, or CLI.
Copy prompt
Task: Use OS Agent Survey in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20OS%20Agent%20Survey%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/os-agent-survey-os-agent-survey/install
Install command: npx skills add OS-Agent-Survey/OS-Agent-Survey
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Give an agent the install path, not another directory page.
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/os-agent-survey-os-agent-survey/install
LLM text format
/api/skills/os-agent-survey-os-agent-survey/install?format=text
Find alternatives
/api/skills/search?q=OS%20Agent%20Survey&limit=3
Agent prompt
Use OS Agent Survey for this task. Review https://www.openagentskill.com/api/skills/os-agent-survey-os-agent-survey/install, then install with: npx skills add OS-Agent-Survey/OS-Agent-SurveyRegistry metadata
Agent-readable profile for automatic skill selection.
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/os-agent-survey-os-agent-survey
LLM text
/api/registry/manifest/os-agent-survey-os-agent-survey?format=text
Install alias
/api/registry/install/os-agent-survey-os-agent-survey
Recommend
/api/registry/recommend?task=Use%20OS%20Agent%20Survey%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Computer Use, Claude Code, Browser agents
Audit report
Needs review · 71/100
Review install readiness, maintenance, trust, quality, and metadata warnings before adding this skill to an agent workflow.
Agent decision cockpit
Needs validation for Local desktop
Do a manual repository review before adding this to an agent workflow.
Role in stack
Needs validation
Primary fit
Local desktop
Trust label
Needs manual review
Install path
Command ready
Use when
- Local desktop workflows
- Claude Code teams
- builders willing to evaluate younger projects
Evidence
- install command or GitHub repo available
- 61/100 quality profile
Review first
- No OpenAgentSkill engagement data yet
Implementation path
- 1Install it in a sandbox agent and run one Local desktop task end to end.
- 2Compare output quality, latency, and failure behavior against at least one alternative.
- 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.
Trust profile
Strong shortlist
Good trust signals with a few areas worth checking before rollout.
GitHub adoption
INFO485 GitHub stars
Stars/forks activity
CHECK485 stars, 21 forks; issue activity unavailable in current metadata
Recent maintenance
INFO10mo since push
License clarity
CHECKUnknown
Good signals
- AI review approved
- Install path is available
- Repository evidence is available
- Install command has no obvious high-risk pattern
Review before install
- License is unclear
- Quality score needs review
- Stars/forks activity: 485 stars, 21 forks; issue activity unavailable in current metadata
- License clarity: Unknown
Recommended action
Test in a sandbox workflow and compare its install path with close alternatives.
Quality profile
Promising candidate for agent workflows
Useful candidate, but compare it with alternatives before adopting.
Workflow fit
Use this skill in these scenarios
Operate local tools
Local desktop
I need my agent to operate local files and desktop apps in a repeatable workflow.
Operate web apps
Browser automation
I need my agent to control a browser, fill forms, and verify web app workflows.
Build and ship code
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Stack fit
Add it to a complete workflow
Operate and verify web apps
Browser QA agent
A stack for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
Turn skills into distribution
Content growth agent
A stack for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Inspect, patch, and verify code
Coding review agent
A stack for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Alternative shortlist
Compare before you install
Similar skills in this category, ranked with the same readiness and quality signals.
MoneyPrinterTurbo
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
Huginn
Create agents that monitor and act on your behalf. Your agents are standing by!
Fastlane
🚀 The easiest way to automate building and releasing your iOS and Android apps
Overview
This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral).
Imported by the skill-only GitHub discovery pipeline because it matches agent skill, automation, domain workflow, RAG, document-processing, data, finance, security, or developer-tool signals. Protocol-server projects are excluded from automated imports.
Platform Compatibility
Technical Details
- Version
- 1.0.0
- License
- Unknown
- Last Updated
- 6/16/2026
- Published
- 6/16/2026
Frameworks & Tools
Decision snapshot
Needs validation
install command or GitHub repo available
Audit Snapshot
Install and adoption review
- Security
- 79/100
- Maintenance
- 62/100
- Install
- 92/100
Growth loop
Share this skill
Scenario-led draft for OS Agent Survey, with the OpenAgentSkill Update theme and canonical URL.
OpenAgentSkill Update Today: OS Agent Survey Use it when you need an agent to browse, extract, or monitor web pages without building a scraper f... 485 stars - automation Link: https://www.openagentskill.com/skills/os-agent-survey-os-agent-survey?ref=x #AIAgents #OpenAgentSkill
Optional reply with install command
Link for OS Agent Survey: https://www.openagentskill.com/skills/os-agent-survey-os-agent-survey?ref=x Install: npx skills add OS-Agent-Survey/OS-Agent-Survey
Listing source
Community indexed
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
- Creator
- OS-Agent-Survey
- Indexed by
- OpenAgentSkill community index
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
Claim this skill listing
This community indexed listing is attributed to OS-Agent-Survey but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
README badge
Add this badge to your GitHub README to show the listing, trust score, and install handoff.
[](https://www.openagentskill.com/skills/os-agent-survey-os-agent-survey)Author
OS-Agent-Survey
@os-agent-survey
Tags
Platform Fit
Health Signals
- GitHub stars
- 485
- Quality score
- 42/100
- Last GitHub push
- Aug 16, 2025
- Framework hints
- 1
- OpenAgentSkill views
- 0
- Install copies
- 0
- Outbound clicks
- 0
Community Signal
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Trust & Safety
Strong shortlist
- GitHub adoption485 GitHub starsINFO
- Stars/forks activity485 stars, 21 forks; issue activity unavailable in current metadataCHECK
- Recent maintenance10mo since pushINFO
- License clarityUnknownCHECK
- README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
- Dependency/runtime risknetwork or browser surfacePASS
Related Skills
MoneyPrinterTurbo
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
88.5K stars · 0 installsHuginn
Create agents that monitor and act on your behalf. Your agents are standing by!
49.5K stars · 0 installsFastlane
🚀 The easiest way to automate building and releasing your iOS and Android apps
41.7K stars · 0 installs