nfr-review
Review an existing HLD against NFR reference and generate gap report
npx skills add majiayu000/claude-skill-registry --skill nfr-review --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# /nfr-review Review an existing HLD from Confluence against the NFR YAML reference and generate a gap report with scoring and remediation recommendations. Uses parallel sub-agents for efficient analysis. ## Usage ``` /nfr-review ERPSystem /nfr-review "AlertHub" CS1 /nfr-review 664765269 CS2 confluence /nfr-review https://britishairways.atlassian.net/wiki/spaces/BDOC/pages/12345 CS2 ``` ## Data Source NFR reference data: `.claude/data/nfr-reference.yaml` — single source of truth for all 66 NFRs. ## Scoring Rubric (0-3 Scale) | Score | Rating | Meaning | |-------|---------------------|--------------------------------------------------------------------------------------------------| | **3** | Explicitly Addressed | NFR requirement clearly documented with specific evidence, links, or implementation details | | **2** | Mentioned | NFR topic discussed but lacking evidence, specifics, or measurable targets | | **1** | Implied | Related concept mentioned but NFR not explicitly addressed; may be inferred from context | | **0** | Not Covered | NFR not mentioned at all; no evidence of consideration | | **N/A** | Not Applicable | NFR section does not apply to this system (e.g., PCI for non-p
- Usage
- Data Source
- Scoring Rubric (0-3 Scale)
- Instructions
- Phase 1: Load NFR Reference
- Phase 2: Fetch the HLD
- Phase 3: Parallel Analysis (Sub-agents)
- Phase 4: Synthesise Results
- Phase 5: Generate Gap Report
- Output Template
- Post-Generation Actions
- Related
What does the nfr-review skill do?
Review an existing HLD against NFR reference and generate gap report
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill nfr-review --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.