agentleFS
EbrahimElbagoryEbrahimElbagory/claude-fba/skills/review-automation/SKILL.md

review-automation

Skill17 starsChanged 4 months agoMITView on GitHub

Backfill Amazon review requests for every eligible order via the SP-API Solicitations API and keep a daily job running. Use when the user says "request reviews", "set up review automation", "why do I have so few reviews", or during a store audit that finds low review velocity.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Verify API access (read-only probe): fetch one recent order via GET /orders/v0/orders, then GET /solicitations/v1/orders/{id} — if …

    line 14
  2. Distinctive:

    Verify dedupe: immediately rerun → expect "0 sent, N already logged".

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review-request automation (Solicitations API)

Amazon lets you request a review ONCE per order, 5–30 days after delivery, via the official Solicitations API — identical to Seller Central's "Request a Review" button, but scriptable. Most sellers never systematize this; a store doing ~500 orders/month forgoes thousands of asks per year.

One-time backfill

  1. Verify API access (read-only probe): fetch one recent order via GET /orders/v0/orders, then GET /solicitations/v1/orders/{id} — if productReviewAndSellerFeedback appears in _links.actions, the app has the Solicitations role and orders are waiting.
  2. python3 scripts/solicit_reviews.py --dry-run — counts eligible orders, sends nothing. Show the user the count and get an explicit go.
  3. python3 scripts/solicit_reviews.py — sends for real. ~1 req/s throttle; a 400-order backfill takes ~15 min. Results log to data/solicitations_log.json (dedupe store — reruns skip known orders).
  4. Verify dedupe: immediately rerun → expect "0 sent, N already logged".

Keep it running

  • Install automation/com.example.solicit-reviews.plist (macOS launchd, daily 10:00; runs on wake if the machine was asleep). Linux: equivalent cron line 0 10 * * * python3 /path/to/scripts/solicit_reviews.py.
  • Health check on every audit: job loaded (launchctl list | grep solicit), log fresh (<48h), log growing.

Notes & guardrails

  • Sending is idempotent-safe: once sent, the action disappears from _links.actions and the order logs as ineligible — no duplicate emails possible.
  • This is Amazon's own compliant mechanism. Do NOT combine with manual buyer messaging asking for reviews (that path has ToS landmines; this one doesn't).
  • Expect effects in review counts 1–3 weeks after the backfill; measure with impact-tracker + the audit's review-count diff, and expect roughly a 3–5% request→review conversion.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.