Menu
Review the day's prompts for effectiveness using the 6-criteria rubric. Scores work-initiating prompts, surfaces patterns, and suggests rewrites. Use when asked for prompt review, prompt retro, or prompt quality check.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Research products on amazon.com.au (Australia) and return options with title-verified links, indicative AUD prices, and stock status. Use when asked to research a product, "find me options for X", compare prices, or for help shopping or buying something on Amazon. Australian marketplace only — this skill does not cover amazon.com or other marketplaces.
Create a Git worktree for a new task. This skill should be used when the user asks to "start working on", "implement", "fix", "add", "refactor", "migrate", or otherwise begin a code task that requires a new branch. Do not use for trivial tasks like reading files, answering questions, or changes to the current dotfiles repo.
Drive Apple Reminders as a GTD system from the command line — capture to an inbox, read and search across lists, enrich items with notes, complete, delete, and triage with the 2-minute rule. Use when asked to add/capture a task or idea, "add to my inbox / Stuff list", reschedule or move an item, process/triage the inbox, find 2-minute items, or write research findings into a reminder's note. macOS + iCloud only, via the `reminders` CLI (keith/reminders-cli). Read/capture/enrich is fully supported; moving between lists and rescheduling due dates are not (see Gaps).
Append a timestamped, super-condensed summary of the current session — plus any open loops to close later — to today's dump file at ~/.me/quick-dumps/YYYY-MM-DD.md. Use when asked to "dump state", "dump the session", "jot this down", "save where we're at", or invokes /dump-state.
Review one or more GitHub PRs and write a per-PR findings file (with a go/no-go call at the top) into ~/Developer/ai-workspace/code-reviews/. Use when asked to "review this PR", "review my PRs", "write review notes", or given a PR URL / a search criteria for PRs to review. Produces documents for later human review or handoff to another agent that posts the comments — it does NOT post anything to GitHub.
Check CI status for PRs and Buildkite builds, diagnose failures, auto-fix when possible. Use when asked to "check CI", "check PR status", "how's the build", "monitor CI", "what's failing", or given a Buildkite build URL. Also use after pushing code when the user wants to track the build.
| name | prompt-retro |
| description | Review the day's prompts for effectiveness using the 6-criteria rubric. Scores work-initiating prompts, surfaces patterns, and suggests rewrites. Use when asked for prompt review, prompt retro, or prompt quality check. |
| argument-hint | ["YYYY-MM-DD"] |
| allowed-tools | Read, Glob, Write, Edit, Bash(date:*), Bash(wc:*), Bash(ls:*) |
Review today's prompts for effectiveness. Score work-initiating prompts against the 6-criteria rubric. Surface patterns and suggest rewrites for the weakest prompts.
Arguments: $ARGUMENTS
If arguments contain a date (YYYY-MM-DD), review that day's log. If empty, review today's log.
Rubric reference: ~/.me/prompting-guide.md
Work-initiating prompt: A prompt that starts a new task, requests a change, or asks for analysis. These are what the rubric applies to.
Conversational prompt: A short reply, confirmation, clarification, or follow-up. Examples: "yes", "do it", "looks good", "the second one", "what about X?". These are excluded from scoring — they're valid as-is.
Threshold: A prompt under 15 words that doesn't contain a file path, function name, or technical reference is likely conversational. Don't score it, but do count it.
Score each work-initiating prompt 0 or 1 on:
A score of 5-6 is strong, 3-4 is decent, 0-2 needs a rewrite.
$ARGUMENTS or use date +"%Y-%m-%d".~/.me/prompts/log/YYYY-MM-DD.md.~/.me/prompting-guide.md (for reference, don't quote it back).Read through all logged prompts. Classify each as work-initiating or conversational.
For each work-initiating prompt, score it against the 6 criteria. Be honest — the point is to surface weaknesses, not validate.
Write to: ~/.me/prompts/retros/YYYY-MM-DD.md
Create directories with mkdir -p as needed.
Structure:
# Prompt Retro — YYYY-MM-DD
**Total prompts:** N | **Work-initiating:** N | **Conversational:** N
**Average score:** X.X / 6
## Summary
[2-3 sentences: overall quality, dominant pattern, one thing to change tomorrow]
## Weakest Prompts
[For each prompt scoring 0-3, show:]
### HH:MM:SS — Score: N/6
> [The original prompt, truncated to ~100 chars if long]
| Criterion | Score | Note |
|-----------|-------|------|
| Context | 0/1 | [Why it missed] |
| Intent | 0/1 | ... |
| ... | | |
**Suggested rewrite:**
> [A concrete rewrite that would score 5-6]
## Strongest Prompts
[List 1-3 prompts scoring 5-6 with a one-line note on what made them good.
If none scored that high, say so.]
## Patterns
[Recurring weaknesses across prompts. Examples:]
- "You rarely specify acceptance criteria — 80% of prompts scored 0 on this."
- "Scope is your strongest criterion — you naturally bound your requests."
## Trend
[If previous retros exist in ~/.me/prompts/retros/, compare today's average
to the last 3 retros. Show direction: improving, flat, or declining.
If no history, skip this section.]
---
*Generated by `/prompt-retro`. Rubric: ~/.me/prompting-guide.md*
After writing the file, print a short summary:
Prompt retro saved to ~/.me/prompts/retros/YYYY-MM-DD.md
Total: N | Scored: N | Avg: X.X/6 | Weakest: N/6 | Strongest: N/6
Top pattern: [one-line dominant weakness]
Be direct and constructive. Don't soften findings. The user asked for this feedback — deliver it clearly.