agentsclimarketplace

Run3 GitHub CLI Data Retrieval

Skill cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/github-repo-analytics/run3_GitHub-CLI-Data-Retrieval

Used to query, filter, and extract metadata from GitHub PRs and Issues using the `gh` command line tool with appropriate search qualifiers and pagination limits.From its SKILL.md

Install
npx -y skills add cxcscmu/SkillLearnBench --skill run3_GitHub-CLI-Data-Retrieval

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

SKILL.md

1.2 KB, 252 tokens by cl100k_base, as published. Nobody here has run it

To retrieve data from GitHub using the gh CLI, follow these standards:

  1. Broaden Scope: Always use the -s all flag (or state:all) to ensure the command retrieves merged, closed, and open items.
  2. Apply Search Qualifiers: Use the -S flag with the search query created:2024-12-01..2024-12-31. Do not use date ranges that exceed the repository activity window.
  3. Lift Limits: Explicitly set the --limit flag to a high value (e.g., --limit 1000) to avoid the default truncation of results, which causes inaccurate counts.
  4. Select Fields Carefully: When using --json, always verify the object path. For user names, use author.login. For dates, use createdAt, mergedAt, and closedAt to ensure accurate time calculations.
  5. JSON Formatting: Rely on jq to process raw JSON output from gh. Ensure all calculations (averages, counts) handle empty arrays by providing default values (e.g., 0) to prevent null-pointer or syntax errors in the final output file.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. 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.