Install
$ agentstack add skill-baobao2333-prd-agent-kit-prd-08-risk-debt-review ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
PRD Risk & Debt Review
Purpose
Expose the risks that AI-written PRDs usually hide: historical debt, unclear ownership, old behavior, compatibility, abuse, cost, operations burden, and responsibility transfer.
Inputs
- All previous PRD artifacts.
- Known system history, if available.
- Known legal, finance, risk-control, or operations constraints, if available.
Review principles
- Do not assume old systems are clean.
- Do not assume existing data can support new logic.
- Do not assume old clients behave correctly.
- Do not move product decisions to engineering by using vague wording.
- Do not hide business risk behind “optimize later”.
- Every high-risk item must have an owner or an explicit decision gap.
- Run a confidence loop before finalizing the review: ask whether the strategy is factually strong enough to defend. If not, find all known loopholes, propose fixes, loop back to the owning artifact, and repeat until no delivery-blocking loopholes remain. Do not finish with a list of blockers unless the missing item truly requires user or stakeholder input.
Process
- Review scope creep.
- Review undefined rules.
- Review compatibility and historical data.
- Review abuse and cost risk.
- Review operations burden.
- Review responsibility boundaries.
- Review legal / finance / risk-control dependency if relevant.
- Run the confidence loop: list loopholes, propose fixes, re-check the revised strategy, and preserve any remaining uncertainty.
- Recommend delete, simplify, confirm, keep, or loop back to an earlier stage.
Loop-back rules
- If the risk depends on product scope or version boundary, return to
prd-02-business-boundary. - If the risk depends on missing conditions, thresholds, states, permissions, or conflict handling, return to
prd-03-rule-modeler. - If the risk depends on unclear user/system behavior, return to
prd-04-flow-modeler. - If the risk depends on missing user-visible states or copy, return to
prd-05-page-interaction. - If the risk is caused by speculative controls or missing operations ownership, return to
prd-06-admin-config. - If the risk depends on vague metrics, alert triggers, logging, attribution, or QA evidence, return to
prd-07-data-acceptance. - Use
prd-09-prd-compressoronly when blocking items are resolved. - If a blocking item cannot be resolved from existing evidence with high confidence, ask the user for the specific missing decision, then continue after the answer.
Output format
# 07 Risk & Debt Review: {Feature Name}
## 1. Review conclusion
| Status | Meaning |
|---|---|
| Ready for compression / Loop-back required / User decision required |
## 2. Scope creep check
| Item | Problem | Recommendation |
|---|---|---|
## 3. Rule gaps
| Gap | Why it blocks execution | Owner |
|---|---|---|
## 4. Historical debt / compatibility risks
| Area | Risk | Impact | Who confirms | Recommended handling |
|---|---|---|---|---|
## 5. Abuse, cost, and operations risks
| Risk | Abuse / cost path | Impact | Mitigation | Must-have this version? |
|---|---|---|---|---|
## 6. Responsibility boundary risks
| Wording or decision | Why risky | Rewrite or decision needed |
|---|---|---|
## 7. Sign-off defaults
| Decision | Options considered | Recommended default | Sign-off owner |
|---|---|---|---|
## 8. Handoff to next stage
| Condition | Recommended next skill | Reason |
|---|---|---|
| Ready for compression | `prd-09-prd-compressor` | Compress into a delivery-grade PRD |
| Loop-back required | Relevant earlier skill | Fix the owning artifact and re-run affected later stages |
| User decision required | Ask user | Only for choices the agent cannot responsibly decide |
Definition of done
The review is complete when the product manager can see what they would be signing and where they could get blamed later.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: baobao2333
- Source: baobao2333/prd-agent-kit
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.