Prd Gap Detector
Detect missing sections, ambiguous assumptions, measurement gaps, and hidden engineering or operational requirements in PRDs.
Install
$ agentstack add skill-caiaffa-claude-code-ultimate-engineering-system-prd-gap-detector ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-caiaffa-claude-code-ultimate-engineering-system-prd-gap-detector) 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
Mission
Find the omissions that turn promising PRDs into expensive surprises.
When to use
- Checking PRD completeness.
- Looking for hidden engineering cost.
- Validating measurement and rollout quality.
- Surfacing operational, data, support, or security gaps.
Handoff
- Receives from: prd-challenger (after initial challenge).
- Hands off to: engineering-economics (cost assessment), principal-engineer (for revision).
Completeness scan
Check whether the PRD explicitly addresses each item. "Implied" is not "addressed":
| Section | Present? | Quality | |---|---|---| | Problem statement with evidence | | | | Baseline metric(s) with source | | | | Non-goals (explicit scope boundary) | | | | Primary success metric | | | | Secondary metrics | | | | Guardrail metrics (what must NOT get worse) | | | | Target with timeline | | | | Owner after launch | | | | Rollout plan | | | | Rollback plan | | | | Support impact assessment | | | | Security implications | | | | Data/migration requirements | | | | Observability requirements | | | | Decision rule (when to stop or pivot) | | |
Hidden cost areas that PRDs almost always miss
- Data migration — does the feature require backfilling old data?
- Observability — new dashboards, alerts, SLOs needed?
- Support burden — new failure modes that support team needs to handle?
- Security — new auth rules, permission changes, data exposure?
- API compatibility — does this break existing consumers?
- Operational burden — who monitors this at 3 AM?
- Documentation — API docs, user guides, internal wiki?
Output format
- Completeness score (X/15 sections addressed)
- Critical gaps (missing items that block approval)
- Hidden engineering work (undisclosed cost areas)
- Ambiguity risks (things that could be interpreted multiple ways)
- Required additions (specific sections to write, with guidance)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: caiaffa
- Source: caiaffa/claude-code-ultimate-engineering-system
- 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.