analyze-plan-feedback
Feedback Analysis & Prioritization
Step 1: Parse arguments
$ARGUMENTS
Parse $ARGUMENTS for:
- Plan path (optional): The first argument that looks like a file path. Resolve to absolute and read it.
- Reviewer count (optional): A number (1-10). Defaults to 3 if not provided.
If no plan path is provided, auto-detect candidates and present an interactive selection:
-
Detect candidates (run these in parallel):
- Check if a plan file was recently created, read, or discussed in this session
- Check
git diff --name-onlyandgit log --oneline -5 --diff-filter=AM -- 'docs/plans/**/*.md'for recently added/modified plans - Look for plan files/directories matching
docs/plans/**/*.md
-
ALWAYS present an
AskUserQuestionmultiple-choice UI with up to 4 detected candidates. Never just ask a text question — always use the interactive chip UI. Example:
More from skinnyandbald/fish-skills
simplify-parallel
Run code simplification across entire codebase using parallel agents with automatic segmentation and coordination
38critic-review
Unified plan review — stack detection, Context7 staleness scan, multi-model counselors dispatch, and prioritized triage. Three modes: full pipeline (default), --dry-run (copyable prompt), --feedback (analyze external input).
36pr-resolution
Resolve PR review comments. Use when asked to fix PR feedback, given a PR URL, or on '/pr-resolution'.
34ceo-briefing
Research any topic and produce a structured executive briefing optimized for rapid CEO decision-making.
32counselors
Fan out a prompt to multiple AI coding agents in parallel and synthesize their responses.
32capture-learning
Capture comprehensive problem-solving narratives from work sessions, documenting the journey of discovery
32