agentsclimarketplace

1password credential lookup

Skill bg-szy/TOP-SKILLS/skills/marketplace/1password-credential-lookup

全球最大的 Claude Code 技能聚合库 · 收录 3900+ 来自 12+ 来源的技能,提供在线搜索与趋势分析看板 / The world's largest Claude Code skill aggregation hub — 3900+ skills from 12+ sources with online search and trend dashboard

Install
npx -y skills add bg-szy/TOP-SKILLS --skill 1password-credential-lookup

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

This skill should be used when agents need to log into websites, retrieve passwords, or access credentials. CRITICAL - always use find_credential with the website URL, never guess item names.

SKILL.md

3.0 KB, as published. Nobody here has run it

1Password Credential Lookup

CRITICAL: Use URL, Not Item Names

WRONG:

get_credential(item_name="github.com")  ← NEVER DO THIS
get_credential(item_name="GitHub")      ← NEVER DO THIS

RIGHT:

find_credential(url="github.com")                           ← CORRECT
find_credential(url="github.com", username="clementwalter") ← EVEN BETTER

The One Rule

When logging into a website, use find_credential with the domain.

1Password items have arbitrary names that don't match URLs. The find_credential tool searches by the URL field stored in 1Password, which matches the website you're visiting.

Tools (in order of preference)

1. find_credential - PRIMARY TOOL

Use this for ALL credential lookups:

find_credential(url="github.com")
find_credential(url="linkedin.com", username="[email protected]")

Parameters:

  • url (required): Domain of website (e.g., "github.com", "twitter.com")
  • username (optional): Filter by username when multiple accounts exist

Returns:

  • Single match: {"username": "...", "password": "...", "item_name": "..."}
  • Multiple matches: List of accounts to choose from
  • No match: Error message

2. list_items_for_url - When unsure which account

list_items_for_url(url="github.com")

Shows all accounts for a domain with usernames. Use before find_credential if you don't know which account to use.

3. get_credential - RARELY NEEDED

Only use if you have an exact item ID (like ct2jszznlzlp7r7jeb53rhy5li). Never pass URLs or guessed names.

Workflow Example

When logging into github.com:

# Step 1: Get credentials for the domain
find_credential(url="github.com", username="clementwalter")

# If multiple accounts and no username filter:
# → Returns list: [{"username": "[email protected]"}, {"username": "[email protected]"}]
# → Pick one and retry with username filter

# Step 2: Use returned credentials to fill login form

Domain Aliases

These domains are treated as equivalent:

  • x.comtwitter.com

Error Handling

ErrorSolution
"No items found"Check domain spelling
"Multiple items found"Add username parameter to filter
"op CLI not installed"User needs 1Password CLI
"Timed out"User needs to run op signin

Anti-Patterns

NEVER do these:

  • get_credential(item_name="github.com") - URL is not an item name
  • get_credential(item_name="GitHub") - Guessed names don't work
  • get_credential(item_name="my github") - Item names are arbitrary

ALWAYS do this:

  • find_credential(url="github.com") - Search by the website URL

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.