opencli-autofix
The opencli-autofix skill provides a structured workflow for AI agents to diagnose and repair broken OpenCLI adapters. It guides the agent through trace collection, root cause analysis, code patching, verification, and upstream issue reporting.
Is opencli-autofix safe to install?
Review the source first: our audit of opencli-autofix's source files found 11 shell commands, 2 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands, performs network requests via the browser tool, and modifies local adapter source files.
How we audit skills: our security review methodology.
Who is this skill for?
AI agents assisting developers or users who encounter failures while using OpenCLI to scrape or interact with websites.
What can you do with it?
- Diagnosing SELECTOR errors caused by DOM changes
- Fixing EMPTY_RESULT errors due to API schema changes
- Updating adapter logic for changed API endpoints
- Adding wait conditions to resolve TIMEOUT errors
- Filing GitHub issues for verified adapter fixes
How good is this skill?
Quality score: 5/10. The skill provides clear, step-by-step instructions with specific safety boundaries and constraints. It includes robust logic for determining when to stop and how to verify fixes.
What does the skill file contain?
# OpenCLI AutoFix — Automatic Adapter Self-Repair When an `opencli` command fails because a website changed its DOM, API, or response schema, **automatically diagnose, fix the adapter, and retry** — don't just report the error. ## Safety Boundaries **Before starting any repair, check these hard stops:** - **`AUTH_REQUIRED`** (exit code 77) — **STOP.** Do not modify code. Tell the user to log into the site in Chrome. - **`BROWSER_CONNECT`** (exit code 69) — **STOP.** Do not modify code. Tell the user to run `opencli doctor`. - **CAPTCHA / rate limiting** — **STOP.** Not an adapter issue. *...
Frequently asked questions
When should I avoid modifying the adapter code?
Avoid modifications if the failure is caused by AUTH_REQUIRED, BROWSER_CONNECT, CAPTCHA, or rate limiting. These are environment or platform issues, not adapter bugs.
What is the maximum number of repair attempts allowed?
The skill limits repairs to 3 rounds of diagnose, fix, and retry per failure.
How do I determine which file to patch?
Read the adapterSourcePath from the front matter of the trace summary.md file.
Should I update the verification fixtures if the test fails?
No. Do not relax fixtures to silence failures. Only update fixtures if the site itself has migrated its structure, and document the change in the site's notes.md.
Related skills
find-skills
2.3MUsers seeking to extend agent capabilities with specialized tools, workflows, or knowledge packages
The find-skills skill enables agents to search for, discover, and install modular packages from the open agent skills ecosystem using the Skills CLI.
agent-browser
506.7KAI agents and developers requiring programmatic web interaction, exploratory testing, or automation of Electron desktop applications
The agent-browser CLI provides browser automation for AI agents using Chrome or Chromium via CDP. It supports page navigation, form interaction, data extraction, and testing. The tool utilizes accessibility-tree snapshots and element references for interaction.
image-to-video
355.0KDevelopers and users who need to automate video generation from images using the RunComfy platform
The image-to-video skill routes user requests to specific RunComfy animation models based on intent. It selects HappyHorse 1.0 I2V for general animation, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition. The skill executes the RunComfy CLI to process inputs and download generated video files.
video-edit
338.7KUsers of the RunComfy CLI who need to automate video editing tasks like restyling, background swapping, or motion transfer
The video-edit skill acts as a router for the RunComfy CLI, selecting between Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, and Lucy Edit Restyle models based on user intent to perform video transformations.