agentsclimarketplace

Spec risk complexity analysis

Skill agent-ix/quoin/skills/spec-risk-complexity-analysis

Identify technical risks and volatility in requirements before tasking.From its SKILL.md

Install
npx -y skills add agent-ix/quoin --skill spec-risk-complexity-analysis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 20 stars20 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.8 KB, as published. Nobody here has run it

Risk & Complexity Analysis

Surface the requirements that are most likely to fail, slip, or churn — so they can be sliced smaller, prototyped first, or hedged with extra verification.

When to use

  • After dependency, scope, and evidence analysis but before spec-to-plan decomposes tasks.
  • After any major external change (new compliance regime, new SLA, new vendor).

Risk dimensions

Each FR/StR/NFR is scored on two independent axes.

Technical risk

Flag a requirement as high risk if it involves any of:

  • Novel technology — first time this team or system uses it (new database engine, new protocol, new language runtime).
  • Concurrency / distributed coordination — multi-writer state, consensus, leader election, exactly-once semantics.
  • Security or compliance constraint — regulated data, cryptographic primitives, auth boundary changes.
  • Hard performance guarantee — quantified latency/throughput/availability bounds (p99, RPO/RTO).

Otherwise medium (one of the above is tangentially involved) or low.

Volatility

Flag a requirement as high volatility if it is likely to change due to:

  • Policy evolution — regulatory or org policy not yet stable.
  • External contracts — depends on a third-party API we don't control.
  • Product discovery — UX or business rules expected to shift as users are observed.

Otherwise medium or low.

Process

  1. Score every FR/StR/NFR on both axes.
  2. Mitigate high-risk, low-volatility items by spiking/prototyping early and adding contract/property tests.
  3. Mitigate high-volatility items by slicing into smaller iterative tasks and avoiding deep dependencies on them.
  4. Cross-check failure domains — see spec-failure-domain-analysis for extension, identity, purity, and topology gaps that also increase risk.
  5. Produce the risk register below.

Deliverable template

Record output in spec/analysis/risk-register.md.

# Risk Register

| Req | Tech Risk | Volatility | Drivers | Mitigation |
|-----|-----------|------------|---------|------------|
| FR-018 | High | Low | Distributed lock, exactly-once payout | Spike + property tests + contract test against ledger |
| FR-022 | Medium | High | UX flow under product discovery | Slice into 3 iterative tasks; avoid downstream coupling |
| NFR-005 | High | Low | p99 < 50ms across 100rps | Load test as quality gate; budget allocated in FR-018 |
| FR-030 | Low | High | Tax rules change quarterly | Move rule table behind config; ship update path |

## Top hazards

1. FR-018 — distributed exactly-once payout (see mitigation above).
2. NFR-005 — perf budget owns FR-018's success; if perf fails, payout slips.

## Failure-domain gaps

See `spec-failure-domain-analysis` deliverable. Open gaps: none / list FR IDs.

Acceptance Criteria

  • Every FR/StR/NFR has both axes scored (no blanks).
  • Every High on either axis has a named mitigation.
  • The "Top hazards" section names the 3–5 items the team should review live before plan generation.
  • Cross-reference to spec-failure-domain-analysis deliverable is present and current.

Output contract

This skill emits one SpecReview under reviews/YY-MM-DD-<slug>.md with analysis: risk-complexity in its frontmatter.

Stated here because nothing checked it. The module declares an analysis vocabulary of eleven values; five of them named a skill that never said it emitted under them, so a skill and its declared output were unlinked and drift between the two was invisible. tests/skill-contracts.test.ts now asserts the pairing in both directions.

The document must carry a ## Summary and a ## Findings table — the two sections SpecReview's body_extraction requires — and must pass quire validate.

Keep looking

Skills are one crate of 611,919. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.