fetch-pr-feedback

Solid

Fetch unresolved review comments from a PR and evaluate with receive-feedback skill

AI & Automation 61 stars 8 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 87/100

Stars 20%
60
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Fetch PR Feedback Fetch review comments from all reviewers on the current PR, format them, and evaluate using the receive-feedback skill. Excludes the PR author and current user by default. Line-specific comments belonging to resolved review threads are also excluded by default. ## Usage ```bash /beagle-core:fetch-pr-feedback [--pr <number>] [--include-author] [--include-resolved] ``` **Flags:** - `--pr <number>` - PR number to target (default: current branch's PR) - `--include-author` - Include PR author's own comments (default: excluded) - `--include-resolved` - Include line-specific comments from resolved review threads (default: excluded) ## Instructions ### Gates (sequence; do not skip) Advance only after each **Pass when** is satisfied. 1. **PR context** — **Pass when:** `$PR_NUMBER` is set to a positive integer and `gh pr view` / `gh api` for that PR completed with exit code **0**, **or** you stop in **Get PR Context** with only the failure given there (“No PR found for current branch…”). 2. **Fetch** — **Pass when:** the resolved-thread GraphQL call (skipped if `--include-resolved`) and both paginated `gh api … | jq -s -f …` runs (issue comments + review comments) exit **0** and parse as JSON (empty `[]` is valid). On non-zero exit or jq error, stop; surface command stderr—do not invent comments. 3. **Formatted artifact** — **Pass when:** output is either (a) markdown matching **Format Feedback Document** (header `# PR #$PR_NUMBER Review Feedback`, per-revie...

Details

Author
existential-birds
Repository
existential-birds/beagle
Created
5 months ago
Last Updated
today
Language
Shell
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category